Claude Code Skills Marketplace

Professional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows.

📑 Table of Contents

• 🌟 Essential Skill: skill-creator
• 🚀 Quick Installation
• 🇨🇳 Chinese User Guide
• 📦 Other Available Skills
• 🎬 Interactive Demo Gallery
• 🎯 Use Cases
• 📚 Documentation
• 🛠️ Requirements
• ❓ FAQ
• 🤝 Contributing
• 📄 License

🌟 Essential Skill: skill-creator

⭐ Start here if you want to create your own skills!

The skill-creator is the meta-skill that enables you to build, validate, and package your own Claude Code skills. It's the most important tool in this marketplace because it empowers you to extend Claude Code with your own specialized workflows.

Why This skill-creator?

This is a production-hardened fork of Anthropic's official skill-creator, born from building real skills and hitting every wall the official version doesn't warn you about.

The official skill-creator tells you what to build. Ours also tells you what not to try — and why.

Full methodology: skill-creator/references/skill-development-methodology.md

Quick Install

In Claude Code (in-app):

/plugin marketplace add daymade/claude-code-skills

Then:

1. Select Browse and install plugins
2. Select daymade/claude-code-skills
3. Select skill-creator
4. Select Install now

From your terminal (CLI):

claude plugin marketplace add https://github.com/daymade/claude-code-skills
# Marketplace name: daymade-skills (from marketplace.json)
claude plugin install daymade-skill@daymade-skills

What You Can Do

After installing skill-creator, simply ask Claude Code:

"Create a new skill called my-awesome-skill in ~/my-skills"

"Validate my skill at ~/my-skills/my-awesome-skill"

"Package my skill at ~/my-skills/my-awesome-skill for distribution"

Claude Code, with skill-creator loaded, will guide you through the entire skill creation process - from understanding your requirements to packaging the final skill.

📚 Full documentation: daymade-skill/skill-creator/SKILL.md

Live Demos

📝 Initialize New Skill

✅ Validate Skill Structure

📦 Package Skill for Distribution

🚀 Quick Installation

Install Inside Claude Code (In-App)

/plugin marketplace add daymade/claude-code-skills

Then:

1. Select Browse and install plugins
2. Select daymade/claude-code-skills
3. Select the plugin you want
4. Select Install now

Automated Installation (Recommended)

macOS/Linux:

curl -fsSL https://raw.githubusercontent.com/daymade/claude-code-skills/main/scripts/install.sh | bash

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/daymade/claude-code-skills/main/scripts/install.ps1 | iex

Manual Installation

Add the marketplace:

claude plugin marketplace add https://github.com/daymade/claude-code-skills

Marketplace name is daymade-skills (from marketplace.json). Use @daymade-skills when installing plugins.
Do not use the repo path as a marketplace name (e.g. @daymade/claude-code-skills will fail).
In Claude Code, use /plugin ... slash commands. In your terminal, use claude plugin ....

Essential Skill (recommended first install):

# skill-creator ships inside the daymade-skill suite
claude plugin install daymade-skill@daymade-skills

Documentation Suite (shared namespace for document workflows):

claude plugin install daymade-docs@daymade-skills

This suite exposes related skills under one namespace, including:

/daymade-docs:docs-router
/daymade-docs:doc-to-markdown
/daymade-docs:mermaid-tools
/daymade-docs:pdf-creator
/daymade-docs:ppt-creator
/daymade-docs:docs-cleaner
/daymade-docs:excel-automation
/daymade-docs:read-docx-review

These skills ship as a bundle — there are no separate single-skill plugins. All documentation skills live under daymade-docs/ and install together from the suite.
The router handles automatic selection. The specialist commands remain available for manual use;
ppt-creator is manual-only. New presentation creation uses deck-creator when installed.

Apple Platform Suite (shared namespace for macOS and iOS development/operations):

claude plugin install daymade-macos@daymade-skills

/daymade-macos:capture-screen
/daymade-macos:developing-ios-apps
/daymade-macos:macos-cleaner
/daymade-macos:macos-load-doctor
/daymade-macos:macos-permissions
/daymade-macos:macos-watchdog

These skills are bundle-only under daymade-macos.

Codex Suite (shared namespace for Codex workstation setup, assisted coding, and visual exploration):

claude plugin install daymade-codex@daymade-skills

Codex CLI and Desktop users can install the same suite through Codex's plugin
marketplace:

codex plugin marketplace add daymade/claude-code-skills
codex plugin add daymade-codex@daymade-skills

/daymade-codex:codex-image-gallery
/daymade-codex:local-codex
/daymade-codex:design-style-picker
/daymade-codex:interaction-design-board
/daymade-codex:codex-1m-context-window-setup

These skills are bundle-only under daymade-codex.

Claude Code Operations Suite (shared namespace for Claude Code power-user workflows):

claude plugin install daymade-claude-code@daymade-skills

This suite bundles the skills that extend Claude Code itself — cross-project prior-work retrieval across code, docs, Skills, meetings, WeChat archives, and conversation history; fast local conversation discovery across Claude Code and Codex; session recovery; CLAUDE.md tuning; version-synced Lark CLI routing; troubleshooting; statusline configuration; export repair; marketplace development and suite consolidation; terminal screenshot rendering; usage analysis; and multi-provider model switching:

/daymade-claude-code:claude-code-ops-router
/daymade-claude-code:local-conversation-history
/daymade-claude-code:read-claude-code-history
/daymade-claude-code:read-codex-history
/daymade-claude-code:continue-claude-code-work
/daymade-claude-code:continue-codex-work
/daymade-claude-code:claude-skills-troubleshooting
/daymade-claude-code:claude-md-progressive-disclosurer
/daymade-claude-code:statusline-generator
/daymade-claude-code:fixing-claude-export-conversations
/daymade-claude-code:marketplace-dev
/daymade-claude-code:terminal-screenshot
/daymade-claude-code:claude-usage-analyst
/daymade-claude-code:claude-switch-models-setup
/daymade-claude-code:read-claude-web-conversation
/daymade-claude-code:claude-migrate-memory-to-doc
/daymade-claude-code:claude-code-hooks
/daymade-claude-code:prior-work-retrieval
/daymade-claude-code:lark-cli-router
/daymade-claude-code:claude-code-ping-start-5h-quota
/daymade-claude-code:agent-web-search-setup
/daymade-claude-code:tech-selection

Installed names render as daymade-claude-code:<skill> under a single shared namespace. These skills are bundle-only — install the suite to get all members.

Financial Data Suite (shared namespace for investment-research and financial data workflows):

claude plugin install daymade-financial@daymade-skills

This suite bundles the skills that fetch and analyze financial data — Bigdata.com (RavenPack) structured financials and sentiment, US equity fundamentals via yfinance, Gangtise (岗底斯) OpenAPI research suite orchestration, A-share news and policy aggregation, A-share pharmaceutical sector daily reporting, structured devil's-advocate pressure-testing of investment theses, and adversarial due diligence on inflated benchmark claims:

/daymade-financial:financial-router
/daymade-financial:bigdata-skill
/daymade-financial:financial-data-collector
/daymade-financial:gangtise-copilot
/daymade-financial:ashare-news-fetcher
/daymade-financial:daymade-sector-research
/daymade-financial:pharma-daily-report
/daymade-financial:devils-advocate
/daymade-financial:benchmark-due-diligence

Installed names render as daymade-financial:<skill> under a single shared namespace. These skills are bundle-only — install the suite to get all members.

Install Other Skills:

# GitHub operations
claude plugin install github-ops@daymade-skills

# Teams communication
claude plugin install teams-channel-post-writer@daymade-skills

# Local Claude/Codex agent messaging
claude plugin install peer-message@daymade-skills

# Ghostty terminal session snapshot/restore
claude plugin install ghostty-use@daymade-skills

# Repomix extraction
claude plugin install repomix-unmixer@daymade-skills

# AI/LLM icons
claude plugin install llm-icon-finder@daymade-skills

# CLI demo generation
claude plugin install cli-demo-generator@daymade-skills

# Cloudflare diagnostics
claude plugin install cloudflare-troubleshooting@daymade-skills

# UI design system extraction
claude plugin install ui-designer@daymade-skills

# YouTube video/audio downloading
claude plugin install youtube-downloader@daymade-skills

# Secure repomix packaging
claude plugin install repomix-safe-mixer@daymade-skills

# Full audio suite (ASR + transcript correction + meeting minutes + TTS)
claude plugin install daymade-audio@daymade-skills


# Video comparison and quality analysis
claude plugin install video-comparer@daymade-skills

# QA testing infrastructure with autonomous execution
claude plugin install qa-expert@daymade-skills

# Prompt optimization using EARS methodology
claude plugin install prompt-optimizer@daymade-skills

# CCPM skill registry search and management
claude plugin install daymade-skill@daymade-skills

# Promptfoo LLM evaluation framework
claude plugin install promptfoo-evaluation@daymade-skills

# Twitter/X content fetching
claude plugin install twitter-reader@daymade-skills

# Skill quality review and improvement
claude plugin install daymade-skill@daymade-skills

# GitHub contribution strategy
claude plugin install github-contributor@daymade-skills

# Windows Remote Desktop / AVD connection diagnosis
claude plugin install windows-remote-desktop-connection-doctor@daymade-skills

# Product analysis and optimization
claude plugin install product-analysis@daymade-skills

# Scrapling CLI extraction and troubleshooting
claude plugin install scrapling-skill@daymade-skills

# Tencent IMA knowledge base companion and installer
claude plugin install ima-copilot@daymade-skills

# Export Douban (豆瓣) book/movie/music/game collections to CSV
claude plugin install douban-skill@daymade-skills

# Terraform operational traps and multi-environment reliability patterns
claude plugin install terraform-skill@daymade-skills

# Evaluate any LLM endpoint across speed, concurrency, protocol, and quality
claude plugin install llm-eval-harness@daymade-skills

# Video/GIF memes with motion-tracked image overlays
claude plugin install meme-creator@daymade-skills

Standalone plugins can be installed independently; suite members install together with their suite.

🇨🇳 Chinese User Guide

For Chinese users: We highly recommend using CC-Switch to manage Claude Code API provider configurations.

CC-Switch enables you to:

• ✅ Quickly switch between different API providers (DeepSeek, Qwen, GLM, etc.)
• ✅ Test endpoint response times to find the fastest provider
• ✅ Manage MCP server configurations
• ✅ Auto-backup and import/export settings
• ✅ Cross-platform support (Windows, macOS, Linux)

Setup: Download from Releases, install, add your API configs, and switch via UI or system tray.

Complete Chinese Documentation

For full documentation in Chinese, see README.zh-CN.md.

📦 Other Available Skills

github-ops - GitHub Operations Suite

GitHub operations through gh CLI and GitHub APIs, with explicit targets, impact previews, and
independent state verification.

When to use:

• Creating, viewing, or managing pull requests
• Managing issues and repository settings
• Managing collaborators, teams, organization permissions, and 2FA enforcement
• Querying GitHub API endpoints
• Working with GitHub Actions workflows
• Automating GitHub operations

Key features:

• Verified mutation workflow for PRs, issues, repositories, and Actions
• Parallel and superseded PR convergence
• Organization access, member privileges, and 2FA preflight
• REST, GraphQL, and documented UI-path selection
• Enterprise GitHub support

🎬 Live Demo

docs-router - Daymade Document Routing

Install: claude plugin install daymade-docs@daymade-skills (suite-only — invoked as daymade-docs:docs-router)

Selects the bundled specialist for document conversion, Word and PDF production,
Mermaid images, macOS Excel automation, scanned PDFs, DOCX review extraction, or
documentation cleanup. It reads the selected specialist's full instructions and
required references. Specialist slash commands remain available for manual use.
New presentation creation uses deck-creator when installed; ppt-creator is manual-only.

doc-to-markdown - Document Conversion Suite

Install: claude plugin install daymade-docs@daymade-skills (suite-only — invoked as daymade-docs:doc-to-markdown)

Converts documents to markdown with Windows/WSL path handling and PDF image extraction.

When to use:

• Converting .doc/.docx/PDF/PPTX to markdown
• Converting saved HTML/HTM with source-link checks and explicit heading offsets
• Extracting images from PDF files
• Processing Confluence exports
• Handling Windows/WSL path conversions

Key features:

• Multi-format document conversion
• PDF image extraction using PyMuPDF
• Windows/WSL path automation
• Confluence export processing
• Helper scripts for path conversion and image extraction

🎬 Live Demo

mermaid-tools - Diagram Generation

Install: claude plugin install daymade-docs@daymade-skills (suite-only — invoked as daymade-docs:mermaid-tools)

Extracts Mermaid diagrams from markdown and generates high-quality PNG images.

When to use:

• Converting Mermaid diagrams to PNG
• Extracting diagrams from markdown files
• Processing documentation with embedded diagrams
• Creating presentation-ready visuals

Key features:

• Automatic diagram extraction
• High-resolution PNG generation
• Smart sizing based on diagram type
• Customizable dimensions and scaling
• WSL2 Chrome/Puppeteer support

🎬 Live Demo

claude-code-ops-router - Claude Code Setup Router

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:claude-code-ops-router)

Routes plugin and Skill repair, marketplace work, statusline, model profiles and source sync, 1M context-window repair, usage and quota timers, memory migration, and exported .txt repair to one bundled specialist. The selected Skill's full instructions are read at use time; its original slash command remains available for manual use.

statusline-generator - Statusline Customization

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:statusline-generator)

Configures Claude Code statuslines with multi-line layouts and cost tracking.

When to use:

• Customizing Claude Code statusline
• Adding cost tracking (session/daily)
• Displaying git status
• Multi-line layouts for narrow screens
• Color customization

Key features:

• Multi-line statusline layouts
• ccusage cost integration
• Git branch status indicators
• Customizable colors
• Portrait screen optimization

🎬 Live Demo

teams-channel-post-writer - Teams Communication

Creates educational Teams channel posts for internal knowledge sharing.

When to use:

• Writing Teams posts about features
• Sharing Claude Code best practices
• Documenting lessons learned
• Creating internal announcements
• Teaching effective prompting patterns

Key features:

• Post templates with proven structure
• Writing guidelines for quality content
• "Normal vs Better" example patterns
• Emphasis on underlying principles
• Ready-to-use markdown templates

🎬 Live Demo

peer-message - Local Claude/Codex Agent Communication

Follow the local coordination workflow
for task/resource declarations, native preflight installation, recovery and receiver checks.

An experimental paired-network route adds invitations and cited answers from owner-selected documents through existing Claude/Codex hosts. It requires an operator-provided relay; the public hosted network and user-adoption claims are not part of this preview.

Install: claude plugin install peer-message@daymade-skills

Follow the routing contract for native communication and transport gaps.

When to use:

• Sending a dependency, pause, handoff, or completion notice to an independently identified target outside the current native tools' scope
• Finding replies to a specific coordination message without manually inspecting local message stores
• Reaching a Claude inbox from a script or another product when native tools do not cover it; a third-party provider alone is not a reason to use the fallback
• Unblocking messages held for per-message manual approval on an unattended endpoint (crossSessionInbound)
• An inbound peer message asserting facts about your session or shared state, or asking you to pause/release — verify the premise against its own authority before acting
• Another session's uncommitted edits, lock, or branch is in your way on a shared checkout — verify it is live, then ask the owner before waiting or working around it
• Broadcasting one explicit coordination message to a reviewed target list

📚 Execution entry and detailed SOPs.

repomix-unmixer - Repository Extraction

Extracts files from repomix-packed repositories and restores directory structures.

When to use:

• Unmixing repomix output files
• Extracting packed repositories
• Restoring file structures
• Reviewing repomix content
• Converting repomix to usable files

Key features:

• Multi-format support (XML, Markdown, JSON)
• Auto-format detection
• Directory structure preservation
• UTF-8 encoding support
• Comprehensive validation workflows

🎬 Live Demo

llm-icon-finder - AI/LLM Brand Icon Finder

Access 100+ AI model and LLM provider brand icons from lobe-icons library.

When to use:

• Finding brand icons for AI models/providers
• Downloading logos for Claude, GPT, Gemini, etc.
• Getting icons in multiple formats (SVG/PNG/WEBP)
• Building AI tool documentation
• Creating presentations about LLMs

Key features:

• 100+ AI/LLM model icons
• Multiple format support (SVG, PNG, WEBP)
• URL generation for direct access
• Local download capabilities
• Searchable icon catalog

🎬 Live Demo

cli-demo-generator - CLI Demo Generation

Generate professional animated CLI demos and terminal recordings with VHS automation.

When to use:

• Creating demos for documentation
• Recording terminal workflows as GIFs
• Generating animated tutorials
• Batch-generating multiple demos
• Showcasing CLI tools

Key features:

• Automated demo generation from command lists
• Batch processing with YAML/JSON configs
• Interactive recording with asciinema
• Smart timing based on command complexity
• Multiple output formats (GIF, MP4, WebM)
• VHS tape file templates

🎬 Live Demo

cloudflare-troubleshooting - Cloudflare Diagnostics

Investigate and resolve Cloudflare configuration issues using API-driven evidence gathering.

When to use:

• Site shows ERR_TOO_MANY_REDIRECTS
• SSL/TLS configuration errors
• DNS resolution problems
• Email Routing aliases, destination verification and forwarding delivery
• Cloudflare-related issues

Key features:

• Evidence-based investigation methodology
• Comprehensive Cloudflare API reference
• SSL/TLS mode troubleshooting (Flexible, Full, Strict)
• DNS, cache, and firewall diagnostics
• Agentic approach with optional helper scripts

🎬 Live Demo

ui-designer - UI Design System Extractor

Extract design systems from reference UI images and generate implementation-ready design prompts.

When to use:

• Have UI screenshots/mockups to analyze
• Need to extract color palettes, typography, spacing
• Building MVP UI matching reference aesthetics
• Creating consistent design systems
• Generating multiple UI variations

Key features:

• Systematic design system extraction from images
• Color palette, typography, component analysis
• Interactive MVP PRD generation
• Template-driven workflow (design system → PRD → implementation prompt)
• Multi-variation UI generation (3 mobile, 2 web)
• React + Tailwind CSS + Lucide icons

🎬 Live Demo

ppt-creator - Professional Presentation Creation

Install: claude plugin install daymade-docs@daymade-skills (suite-only — invoked as daymade-docs:ppt-creator)

Create persuasive, audience-ready slide decks from topics or documents with data-driven charts and dual-format PPTX output.

When to use:

• Creating presentations, pitch decks, or keynotes
• Need structured content with professional storytelling
• Require data visualization and charts
• Want complete PPTX files with speaker notes
• Building business reviews or product pitches

Key features:

• Pyramid Principle structure (conclusion → reasons → evidence)
• Assertion-evidence slide framework
• Automatic data synthesis and chart generation (matplotlib)
• Dual-path PPTX creation (Marp CLI + document-skills:pptx)
• Complete orchestration: content → data → charts → PPTX with charts
• 45-60 second speaker notes per slide
• Quality scoring with auto-refinement (target: 75/100)

🎬 Live Demo

youtube-downloader - YouTube Video & Audio Downloader

Download YouTube videos and audio using yt-dlp with robust error handling and automatic workarounds for common issues.

When to use:

• Downloading YouTube videos or playlists
• Extracting audio from YouTube videos as MP3
• Experiencing yt-dlp download failures or nsig extraction errors
• Need help with format selection or quality options
• Working with YouTube content in regions with access restrictions

Key features:

• Auto PO Token provider (Docker-first, browser fallback) for high-quality access
• Browser-cookie verification for “not a bot” prompts (privacy-friendly)
• Audio-only download with MP3 conversion
• Format listing and custom format selection
• Output directory customization
• Proxy-aware downloads for restricted environments

🎬 Live Demo

repomix-safe-mixer - Secure Repomix Packaging

Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing.

When to use:

• Packaging code with repomix for distribution or sharing
• Creating reference packages from proprietary codebases
• Security concerns about accidentally exposing credentials
• Pre-commit security checks for hardcoded secrets
• Auditing codebases for credential exposure

Key features:

• Detects 20+ credential patterns (AWS, Supabase, Stripe, OpenAI, etc.)
• Scan → Report → Pack workflow with automatic blocking
• Standalone security scanner for pre-commit hooks
• Environment variable replacement guidance
• JSON output for CI/CD integration
• Exclude patterns for false positive handling

🎬 Live Demo

Coming soon

transcript-fixer - ASR Transcription Correction

Install: claude plugin install daymade-audio@daymade-skills (suite-only — invoked as daymade-audio:transcript-fixer)

Correct speech-to-text (ASR/STT) errors with a Stage 1 dictionary pre-filter, a required Native AI whole-transcript pass, and an audio-backed human gate for unresolved wording, names, numbers, and entities.

When to use:

• Correcting meeting notes, lecture recordings, or interview transcripts
• Fixing Chinese/English homophone errors and technical terminology
• Reviewing one exact transcript with its original audio instead of searching a global queue
• Improving future transcripts without turning one-off fixes into broad dictionary rules
• Collaborating with teams on shared correction knowledge bases

Key features:

• Stage 1 + Native AI correction pipeline; Stage 1 alone is never completion
• Frozen review packets and checked file/segment coverage for split or resumed Native reviews; malformed results stay unready and valid work can be reused
• Exact-file review queue, deep-linked dashboard, timestamped audio playback, and machine-readable zero-pending readback
• Conservative pattern learning: file-only, dictionary, roster, and context have separate admission rules
• Domain-specific dictionaries (general, embodied_ai, finance, medical)
• SQLite-based correction repository
• Team collaboration with import/export
• GLM API integration for AI corrections
• Cost optimization through dictionary promotion

Example workflow:

# Initialize and add corrections
uv run scripts/fix_transcription.py --init
uv run scripts/fix_transcription.py --add "错误词" "正确词" --domain general

# Run full correction pipeline
uv run scripts/fix_transcription.py --input meeting.md --stage 3

# Open only this transcript's unresolved items and listen before deciding
uv run scripts/review-dashboard/server.py --file "/absolute/meeting.md"

# Read the human verdicts back; pending_total must be 0 before final delivery
uv run scripts/fix_transcription.py \
  --list-review --review-file "/absolute/meeting.md" \
  --review-status all --json

📚 Documentation: See daymade-audio/transcript-fixer/references/ for workflow guides, SQL queries, troubleshooting, best practices, team collaboration, and API setup.

Requirements: Python 3.10+ and uv. Native AI correction uses the active agent; an external API key is needed only for the optional agent-less API route.

video-comparer - Video Comparison and Quality Analysis

Compare two videos and generate interactive HTML reports with quality metrics and frame-by-frame visual comparisons.

When to use:

• Comparing original and compressed videos
• Analyzing video compression quality and efficiency
• Evaluating codec performance or bitrate reduction impact
• Assessing before/after compression results
• Quality analysis for video encoding workflows

Key features:

• Quality metrics calculation (PSNR, SSIM)
• Frame-by-frame visual comparison with three viewing modes:
  • Slider mode: Drag to reveal differences
  • Side-by-side mode: Simultaneous display
  • Grid mode: Compact 2-column layout
• Video metadata extraction (codec, resolution, bitrate, duration, file size)
• Self-contained HTML reports (no server required, works offline)
• Security features (path validation, resource limits, timeout controls)
• Multi-platform FFmpeg support (macOS, Linux, Windows)

Example usage:

# Basic comparison
python3 scripts/compare.py original.mp4 compressed.mp4

# Custom output and frame interval
python3 scripts/compare.py original.mp4 compressed.mp4 -o report.html --interval 10

# Batch processing
for original in originals/*.mp4; do
    compressed="compressed/$(basename "$original")"
    output="reports/$(basename "$original" .mp4).html"
    python3 scripts/compare.py "$original" "$compressed" -o "$output"
done

🎬 Live Demo

Coming soon

📚 Documentation: See video-comparer/references/ for quality metrics interpretation, FFmpeg commands, and configuration options.

Requirements: Python 3.8+, FFmpeg/FFprobe (install via brew install ffmpeg, apt install ffmpeg, or winget install ffmpeg)

qa-expert - Comprehensive QA Testing Infrastructure

Establish world-class QA testing processes with autonomous LLM execution, Google Testing Standards, and OWASP security best practices.

When to use:

• Setting up QA infrastructure for new or existing projects
• Writing standardized test cases following Google Testing Standards (AAA pattern)
• Implementing security testing (OWASP Top 10 coverage)
• Executing comprehensive test plans with automatic progress tracking
• Filing bugs with proper P0-P4 severity classification
• Calculating quality metrics and enforcing quality gates
• Enabling autonomous LLM-driven test execution
• Preparing QA documentation for third-party team handoffs

Key features:

• One-command initialization: Complete QA infrastructure with templates, CSVs, and documentation
• Autonomous execution: Master prompt enables LLM to auto-execute all tests, auto-track results, auto-file bugs
• Testing standards and quality gates: Follow qa-expert for the canonical policy
• Ground Truth Principle: Prevents doc/CSV sync issues (test docs = authoritative source)
• Bug tracking: P0-P4 classification with detailed repro steps and environment info
• Onboarding: Guide for new QA engineers
• LLM prompts: Ready-to-use prompts for specific QA tasks
• Metrics dashboard: Test execution progress, pass rate, bug analysis, quality gates status

Example usage:

# Initialize QA project (creates full infrastructure)
python3 scripts/init_qa_project.py my-app ./

# Calculate quality metrics and gates status
python3 scripts/calculate_metrics.py tests/TEST-EXECUTION-TRACKING.csv

# For autonomous execution, copy master prompt from:
# references/master_qa_prompt.md → paste to LLM → execute the project's approved test plan

🎬 Live Demo

Coming soon

📚 Documentation: See qa-expert/references/ for:

• master_qa_prompt.md - Autonomous execution entry
• google_testing_standards.md - AAA pattern, coverage thresholds, OWASP testing
• day1_onboarding.md - Onboarding timeline for new QA engineers
• ground_truth_principle.md - Preventing doc/CSV sync issues
• llm_prompts_library.md - 30+ ready-to-use QA prompts

Requirements: Python 3.8+

💡 Innovation: The autonomous execution capability (via master prompt) enables LLM to execute entire test suites 100x faster than manual execution, with zero human error in tracking. Perfect for third-party QA handoffs - just provide the master prompt and they can start testing immediately.

prompt-optimizer - Prompt Engineering with EARS Methodology

Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) - a methodology created by Rolls-Royce for converting natural language into testable requirements.

Methodology inspired by: 阿星AI工作室 (A-Xing AI Studio), which pioneered combining EARS with domain theory grounding for practical prompt enhancement.

When to use:

• Converting loose requirements into structured specifications
• Optimizing prompts for AI code generation or content creation
• Breaking down vague feature requests into atomic, testable statements
• Adding domain theory grounding to technical requirements
• Transforming "build X" requests into detailed implementation specs
• Learning prompt engineering best practices with proven frameworks

Key features:

• EARS transformation: 5 sentence patterns (ubiquitous, event-driven, state-driven, conditional, unwanted behavior)
• 6-step optimization workflow: Analyze → Transform → Identify theories → Extract examples → Enhance → Present
• Domain theory catalog: 40+ frameworks mapped to 10 domains (productivity, UX, gamification, learning, e-commerce, security)
• Structured prompt framework: Role/Skills/Workflows/Examples/Formats template
• Advanced techniques: Multi-stakeholder requirements, non-functional specs, complex conditional logic
• Complete examples: Procrastination app, e-commerce product page, learning dashboard, password reset
• Theory grounding: GTD, BJ Fogg Behavior Model, Gestalt Principles, AIDA, Zero Trust, and more
• Progressive disclosure: Bundled references (ears_syntax.md, domain_theories.md, examples.md)

Example usage:

# Before (vague)
"Build me a password reset feature"

# After EARS transformation (7 atomic requirements)
1. When user clicks "Forgot Password", the system shall display email input field
2. When user submits valid email, the system shall send password reset link valid for 1 hour
3. When user clicks reset link, the system shall verify token has not expired
4. When token is valid, the system shall display password creation form requiring minimum 12 characters, 1 uppercase, 1 number, 1 special character
5. When user submits new password meeting requirements, the system shall hash password with bcrypt and invalidate reset token
6. When user attempts password reset more than 3 times in 1 hour, the system shall block further attempts for 1 hour
7. If reset token has expired, the system shall display error message and option to request new link

# Enhanced with domain theories
- Zero Trust Architecture (verify at each step)
- Defense in Depth (rate limiting + token expiration + password complexity)
- Progressive Disclosure (multi-step UX flow)

# Full prompt includes Role, Skills, Workflows, Examples, Formats

🎬 Live Demo

Coming soon

📚 Documentation: See prompt-optimizer/references/ for:

• ears_syntax.md - Complete EARS patterns and transformation rules
• domain_theories.md - 40+ theories mapped to domains with selection guidance
• examples.md - Full transformation examples with before/after comparisons

💡 Innovation: EARS methodology eliminates ambiguity by forcing explicit conditions, triggers, and measurable criteria. Combined with domain theory grounding (GTD, BJ Fogg, Gestalt, etc.), it transforms "build a todo app" into a complete specification with behavioral psychology principles, UX best practices, and concrete test cases - enabling test-driven development from day one.

local-conversation-history - Cross-Provider History Entry Point

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:local-conversation-history)

See the Skill's usage and routing contract
for history recall, interrupted work and conversation-backup health checks.

read-claude-code-history - Read Local Claude Code History

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:read-claude-code-history)

Read, search, and export Claude Code history across all active config homes and
the long-term archives registered in ~/.claude/history-sources.json, without
resuming or modifying the old task.

When to use:

• Recovering deleted or lost files from previous Claude Code sessions
• Reconstructing one known Session as a chronological user/assistant handoff
• Listing what the human actually typed, including queued mid-turn corrections
• Searching for specific code across conversation history
• Tracking file modifications across multiple sessions
• Finding sessions containing specific keywords or implementations
• Finding which session ran a given command or tool call in a known time window, or when hook runs happened (outcome, duration, exit code)
• Verifying date-bounded topics after a machine migration without trusting mtime

Key features:

• Complete source set: Search active homes and registered archives by default
• Provider boundary: Claude-only by default; Codex requests route to read-codex-history
• Cross-project sweep: --all-projects searches every Claude project when the project is unknown; --exclude-session skips self-matches
• Copy-safe union: Search distinct records from every copy of a session ID without double-counting identical records
• Internal-time search: Filter matching records by JSONL timestamps, never file mtime
• Structured search: Cover messages, thinking, tools, results, queues, attachments, summaries, and original file-history paths
• Exact checkpoint recovery: Union same-session copies and companion roots, then restore captured bytes after Write/Edit/shell changes, including binaries and pre-deletion checkpoints
• Fail-visible fidelity: Label Write-only checkpoints as lower fidelity and abort when exact metadata points to missing bytes instead of silently guessing
• Statistics analysis: Message counts, tool usage breakdown, file operations
• Batch operations: Process multiple sessions with keyword filtering
• Streaming processing: Handle large session files (>100MB) efficiently
• Read/continue separation: Produces an evidence receipt and never resumes work itself

Example usage:

# List recent sessions for a project
python3 scripts/analyze_sessions.py list /path/to/project

# Read one Session chronologically, preserving queued human input
python3 scripts/read_claude_session.py --session <session-id> --project /path/to/project --full

# Export recent human wording grouped by Session
python3 scripts/extract_user_messages.py ./user-words --days 7 --group-by session

# Search sessions for keywords
python3 scripts/analyze_sessions.py search /path/to/project \
  "ComponentName" "featureX" --from-date 2026-03-01 --to-date 2026-04-30

# Recover deleted files from the exact path printed by search
python3 scripts/recover_content.py <printed-session-path> -k DeletedComponent -o ./recovered/

# Search every project for multiple vanished job artifacts
python3 scripts/analyze_sessions.py search --all-projects \
  artifact-a.html artifact-b.html \
  --exclude-session <current-session-id>

# Get session statistics
python3 scripts/analyze_sessions.py stats /path/to/session.jsonl --show-files

🎬 Live Demo

Coming soon

📚 Documentation: See daymade-claude-code/read-claude-code-history/references/ for:

• session_file_format.md - JSONL structure and extraction patterns
• workflow_examples.md - Detailed recovery and analysis workflows

docs-cleaner - Documentation Consolidation

Install: claude plugin install daymade-docs@daymade-skills (suite-only — invoked as daymade-docs:docs-cleaner)

Consolidate redundant documentation while preserving all valuable content.

When to use:

• Cleaning up documentation bloat across projects
• Merging redundant docs covering the same topics
• Reducing documentation sprawl after rapid development
• Consolidating multiple files into authoritative sources

Key features:

• Content preservation: Never lose valuable information during cleanup
• Redundancy detection: Identify overlapping documentation
• Smart merging: Combine related docs while maintaining structure
• Validation: Ensure consolidated docs are complete and accurate

🎬 Live Demo

Coming soon

skills-search - Local Repositories and CCPM Search

Find Skills in configurable local repositories first, then approved sources and the CCPM registry. Preserve existing CCPM installation and management commands.

When to use:

• Finding skills for specific tasks (e.g., "find PDF skills")
• Installing skills by name
• Listing currently installed skills
• Getting detailed information about a skill
• Managing your Claude Code skill collection

Key features:

• Local-first discovery: Persist repository paths and trust tiers outside the Skill package; inspect every configured owned source before expanding
• Progressive reading: Search cached name/description metadata, then open the selected Skill at its exact Git commit
• Registry search: Search CCPM registry with ccpm search <query>
• Skill installation: Install skills with ccpm install <skill-name>
• Version support: Install specific versions with @version syntax
• Bundle installation: Install pre-configured skill bundles (web-dev, content-creation, developer-tools)
• Multiple formats: Supports registry names, GitHub owner/repo, and full URLs
• Skill info: Get detailed skill information with ccpm info <skill-name>

Example usage:

# Search configured local repositories first (<skill-dir> is this loaded Skill)
uv run --script <skill-dir>/scripts/local_sources.py search pdf --tier owned

# Expand to the external registry when needed
ccpm search pdf              # Find PDF-related skills
ccpm search "code review"    # Find code review skills

# Install skills
ccpm install skill-creator                # From registry
ccpm install daymade/skill-creator        # From GitHub
ccpm install skill-creator@1.0.0          # Specific version

# List and manage
ccpm list                    # List installed skills
ccpm info skill-creator      # Get skill details
ccpm uninstall pdf-processor # Remove a skill

# Install bundles
ccpm install-bundle web-dev  # Install web development skills bundle

🎬 Live Demo

Coming soon

📚 Documentation: See daymade-skill/skills-search/SKILL.md for configuration, coverage and commands

Requirements: Python 3.10+, Git and uv for local search; CCPM CLI only for external registry/install/manage operations

pdf-creator - PDF Creation with Chinese Font Support

Install: claude plugin install daymade-docs@daymade-skills (suite-only — invoked as daymade-docs:pdf-creator)

Create professional PDF documents from markdown with proper Chinese typography using WeasyPrint.

When to use:

• Converting markdown to PDF for sharing or printing
• Generating formal documents (legal filings, reports)
• Ensuring correct Chinese font rendering

Key features:

• pandoc + WeasyPrint conversion pipeline (dual backend: WeasyPrint or headless Chrome)
• Built-in Chinese/Japanese/Korean (CJK) font fallbacks with auto CJK code-block rendering
• Theme system (default for formal docs, cjk-auto for content-driven tables, warm-terra for training materials, mobile for phone reading)
• A4 layout defaults with print-friendly margins
• Batch conversion scripts

Example usage:

uv run --with weasyprint scripts/md_to_pdf.py input.md output.pdf

🎬 Live Demo

Coming soon

📚 Documentation: See daymade-docs/pdf-creator/SKILL.md for setup and workflow details.

Requirements: Python 3.8+, pandoc (system install), weasyprint (or Chrome as fallback backend)

claude-md-progressive-disclosurer - CLAUDE.md Optimization

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:claude-md-progressive-disclosurer)

Optimize user CLAUDE.md files using progressive disclosure to reduce context bloat while preserving critical rules.

When to use:

• CLAUDE.md is too long or repetitive
• Need to move detailed procedures into references
• Want to extract reusable workflows into skills

Key features:

• Section classification (keep/move/extract/remove)
• Before/after line-count reporting
• Reference file and pointer formats
• Best-practice optimization workflow

Example usage:

"Optimize my ~/.claude/CLAUDE.md using progressive disclosure and propose a plan."

🎬 Live Demo

Coming soon

📚 Documentation: See claude-md-progressive-disclosurer/SKILL.md.

promptfoo-evaluation - Promptfoo LLM Evaluation

Configure and run LLM evaluations with Promptfoo for prompt testing and model comparisons.

When to use:

• Setting up prompt tests and eval configs
• Comparing LLM outputs across providers
• Adding custom assertions or LLM-as-judge grading

Key features:

• promptfooconfig.yaml templates
• Python custom assertions
• llm-rubric scoring guidance
• Built-in preview (echo provider) workflows

Example usage:

npx promptfoo@latest init
npx promptfoo@latest eval
npx promptfoo@latest view

🎬 Live Demo

Coming soon

📚 Documentation: See promptfoo-evaluation/references/promptfoo_api.md.

Requirements: Node.js (Promptfoo via npx promptfoo@latest)

developing-ios-apps - iOS App Development

Install: claude plugin install daymade-macos@daymade-skills (suite-only — invoked as daymade-macos:developing-ios-apps)

Build, configure, and debug iOS apps with XcodeGen, SwiftUI, and Swift Package Manager.

When to use:

• Setting up XcodeGen project.yml
• Fixing SPM dependency or embed issues
• Handling code signing and device deployment errors
• Debugging camera/AVFoundation problems

Key features:

• XcodeGen project templates
• SPM dynamic framework embedding fixes
• Code signing and provisioning guidance
• Device deployment and troubleshooting checklists

Example usage:

xcodegen generate
xcodebuild -destination 'platform=iOS Simulator,name=iPhone 17' build

🎬 Live Demo

Coming soon

📚 Documentation: See developing-ios-apps/references/xcodegen-full.md.

Requirements: macOS + Xcode, XcodeGen

twitter-reader - Twitter/X Content Fetching

Fetch Twitter/X post and article content. Single-post text goes through the
fxtwitter mirror API (login-free, key-free, full long-form body); X Articles
with images go through fetch_article.py; the Jina API path remains as a
fallback with a known intermittent-ban risk.

When to use:

• Retrieving tweet content for analysis or documentation
• Fetching X Articles (long-form) with all images downloaded locally
• Extracting images and media from posts
• Batch downloading multiple tweets for reference

Key features:

• Single posts: fxtwitter mirror — no key, no login, full tweet.text body including note_tweet long-form
• No JavaScript rendering or browser automation needed
• No Twitter authentication required
• Returns markdown-formatted content with metadata
• Supports both individual and batch fetching
• Includes author, timestamp, post text, images, and replies
• Environment variable configuration for secure API key management

Example usage:

# Single post text (preferred): fxtwitter mirror, no key needed
curl -sS "https://api.fxtwitter.com/USER/status/TWEET_ID" \
  | python3 -c "import json,sys; t=json.load(sys.stdin)['tweet']; print(t['text'])"

# X Article with images (full mode)
uv run --with pyyaml python scripts/fetch_article.py \
  "https://x.com/USER/status/TWEET_ID" ./Clippings

# Jina fallback (intermittent — see SKILL.md risk note)
export JINA_API_KEY="your_api_key_here"
curl "https://r.jina.ai/https://x.com/USER/status/TWEET_ID" \
  -H "Authorization: Bearer ${JINA_API_KEY}"

# Batch fetch multiple tweets
scripts/fetch_tweets.sh \
  "https://x.com/user/status/123" \
  "https://x.com/user/status/456"

# Fetch to file using Python script
python scripts/fetch_tweet.py https://x.com/user/status/123 output.md

🎬 Live Demo

Coming soon

📚 Documentation: See twitter-reader/SKILL.md for full details and URL format support.

Requirements:

• curl (pre-installed on most systems) — single-post path needs nothing else
• Python 3.6+ (for Python scripts)
• Jina.ai API key (only for the Jina fallback; intermittent-ban risk, and the shared repo key is currently out of balance / 402)

macos-cleaner - Intelligent macOS Disk Space Recovery

Install: claude plugin install daymade-macos@daymade-skills (suite-only — invoked as daymade-macos:macos-cleaner)

The safest way to reclaim disk space on macOS. Start with targeted read-only diagnosis when a subsystem is already suspect—including Apple Content Caching—then analyze caches, application remnants, large files, and development environments only as needed.

Why macos-cleaner stands out:

• Safety-First Philosophy: Never deletes without explicit user confirmation. Every operation includes risk assessment (🟢 Safe / 🟡 Caution / 🔴 Keep).
• Intelligence Over Automation: Analyzes first, explains thoroughly, then lets you decide. Unlike one-click cleaners that blindly delete, we help you understand what you're removing and why.
• Developer-Friendly: Deep analysis of Docker, Homebrew, npm, pip caches - tools that generic cleaners miss.
• Transparent & Educational: Every recommendation includes an explanation of what the file is, why it's safe (or not), and what happens if you delete it.
• Professional Quality: Built by developers who know the pain of accidentally deleting important files. Includes comprehensive safety checks and Time Machine backup recommendations.

Our design principles:

1. User Control First: You make the decisions, we provide the insights
2. Explain Everything: No mysterious deletions - full transparency on impact
3. Conservative Defaults: When uncertain, we preserve rather than delete
4. Developer Context: Understand development tool caches, not just system files
5. Hybrid Approach: Combine script precision with visual tools (Mole integration)

When to use:

• Your Mac is running out of disk space (>80% full)
• You're a developer with Docker/npm/pip/Homebrew caches piling up
• Apple Content Caching reports Caching needs more space, an unlimited cache, or unexpectedly high ActualCacheUsed
• You want to understand what's consuming space, not just delete blindly
• You need to clean up after uninstalled applications
• You prefer understanding over automation

Key features:

• Smart Cache Analysis: Categorizes system caches, app caches, logs by safety level
• Apple Content Caching: Separates logical CacheUsed from physical ActualCacheUsed, verifies peers and protected services, and uses Apple's supported limit/deactivate/flush controls
• Application Remnant Detection: Finds orphaned data from uninstalled apps with confidence scoring
• Large & Duplicate File Discovery: Intelligent categorization plus optional read-only fdupes scans inside exact approved paths
• Development Environment Cleanup: Docker images/containers/volumes, OrbStack, Homebrew, npm, and pip; Docker build cache is measured but prune-based deletion is out of scope
• Interactive Safe Deletion: Batch confirmation, selective deletion, undo-friendly (uses Trash when possible)
• Before/After Reports: Track space recovery with detailed breakdown
• Mole Integration: Seamless workflow with visual cleanup tool for GUI preferences
• Risk Categorization: Every item labeled with safety level and explanation
• Time Machine Awareness: Recommends backups before large deletions (>10 GB)

What makes us different:

• ✅ Trust Through Transparency: Other cleaners hide what they delete. We show everything and explain why.
• ✅ Developer-Centric: We clean Docker, not just browser caches. We understand .git directories, node_modules, and build artifacts.
• ✅ Safety Checks Built-In: Protection against deleting system files, user data, credentials, active databases, or files in use.
• ✅ Educational: Learn what's safe to delete and why, so you can maintain your Mac confidently.
• ❌ Not a One-Click Solution: Nothing changes until you approve a scoped command plan. When you ask Claude to execute it, only those confirmed actions run, followed by before/after verification.

Example usage:

# Install the Apple platform suite
claude plugin install daymade-macos@daymade-skills

# Ask Claude Code to analyze your Mac
"My Mac is running out of space, help me analyze what's using storage"

# Claude will:
# 1. Route a named suspect to targeted read-only diagnosis; scan broadly only if the source is unknown
# 2. Present categorized findings with safety levels
# 3. Explain each category (caches, remnants, large files, dev tools)
# 4. Recommend cleanup approach
# 5. Execute ONLY what you confirm

# Example analysis output:
📊 Disk Space Analysis
━━━━━━━━━━━━━━━━━━━━━━━━
Total:     500 GB
Used:      450 GB (90%)
Available:  50 GB (10%)

🟢 Safe to Clean (95 GB):
  - System caches:     45 GB (apps regenerate automatically)
  - Homebrew cache:     5 GB (reinstalls when needed)
  - npm cache:          3 GB (safe to clear)
  - Old logs:           8 GB (diagnostic data only)
  - Trash:             34 GB (already marked for deletion)

🟡 Review Recommended (62 GB):
  - Large downloads:   38 GB (may contain important files)
  - App remnants:       8 GB (verify apps are truly uninstalled)
  - Docker images:     12 GB (may be in use)
  - Old .git repos:     4 GB (verify project is archived)

🔴 Keep Unless Certain (0 GB):
  - No high-risk items detected

Recommendation: Start with 🟢 Safe items (95 GB), then review 🟡 items together.

🎬 Live Demo

Coming soon

📚 Documentation: See macos-cleaner/references/ for:

• apple_content_caching.md - Targeted Apple Content Caching diagnosis and supported repair
• cleanup_targets.md - Detailed explanations of every cleanup target
• mole_integration.md - How to combine scripts with Mole visual tool
• safety_rules.md - Comprehensive safety guidelines and what to never delete

Requirements:

• Python 3.6+ (pre-installed on macOS)
• macOS (tested on macOS 10.15+)
• Optional: Mole for visual cleanup interface

fact-checker - Document Fact-Checking

Verify factual claims in documents using web search and official sources, then propose corrections with user confirmation.

When to use:

• Fact-checking documents for accuracy
• Verifying AI model specifications and technical documentation
• Updating outdated information in documents
• Validating statistical claims and benchmarks
• Checking API capabilities and version numbers

Key features:

• Web search integration with authoritative sources
• AI model specification verification
• Technical documentation accuracy checks
• Statistical data validation
• Automated correction reports with user confirmation
• Supports general factual statements and technical claims

Example usage:

# Install the skill
claude plugin install fact-checker@daymade-skills

# Fact-check a document
"Please fact-check this section about AI model capabilities"

# Verify technical specs
"Check if these Claude model specifications are still accurate"

# Update outdated info
"Verify and update the version numbers in this documentation"

🎬 Live Demo

Coming soon

📚 Documentation: See fact-checker/SKILL.md for full workflow and claim types.

Requirements:

• Web search access (via Claude Code)

skill-reviewer - Skill Quality Review & Improvement

Review and improve Claude Code skills against official best practices with three powerful modes.

When to use:

• Validating your own skills before publishing
• Evaluating others' skill repositories
• Contributing improvements to open-source skills via auto-PR
• Ensuring skills follow marketplace standards

Key features:

• Self-review mode: Run the bundled reviewer backed by canonical skill-creator validation
• External review mode: Clone, analyze, and generate improvement reports
• Auto-PR mode: Fork → improve → submit PR with additive-only changes
• Evaluation checklist: Frontmatter, instructions, resources verification
• Additive-only principle: Never delete files when contributing to others
• PR guidelines: Tone recommendations and professional templates
• Reliable automation: Distinguishes review findings from invocation/runtime failures with structured JSON output
• Evidence-based design review: Score six dimensions with exact source citations; keep documented design quality separate from measured task benefit
• Read-only batch review: Inventory collections against declared host contracts, prepare complete selected-source packets, and export JSON/CSV/Markdown with explicit coverage and invalid decisions quarantined

Example usage:

# Install the skill
claude plugin install daymade-skill@daymade-skills

# Self-review your skill
"Validate my skill at ~/my-skills/my-awesome-skill"

# Review external skill repository
"Review the skills at https://github.com/user/skill-repo"

# Auto-PR improvements
"Fork, improve, and submit PR for https://github.com/user/skill-repo"

🎬 Live Demo

Coming soon

📚 Documentation: See daymade-skill/skill-reviewer/references/ for:

• evaluation_checklist.md - Complete skill evaluation criteria
• pr_template.md - Professional PR description template

github-contributor - GitHub Contribution Strategy

Strategic guide for becoming an effective GitHub contributor and building your open-source reputation.

When to use:

• Looking for projects to contribute to
• Learning contribution best practices
• Building your GitHub presence and reputation
• Understanding how to write high-quality PRs

Key features:

• Four contribution types: Documentation, Code Quality, Bug Fixes, Features
• Project selection criteria: What makes a good first project vs red flags
• PR excellence workflow: Before → During → After submission checklist
• Reputation building ladder: Documentation → Bug Fixes → Features → Maintainer
• GitHub CLI commands: Quick reference for fork, PR, issue operations
• Conventional commit format: Type, scope, description structure
• Common mistakes: What to avoid and best practices

Contribution types explained:

Level 1: Documentation fixes (lowest barrier, high impact)
    ↓ (build familiarity)
Level 2: Code quality (medium effort, demonstrates skill)
    ↓ (understand codebase)
Level 3: Bug fixes (high impact, builds trust)
    ↓ (trusted contributor)
Level 4: Feature additions (highest visibility)
    ↓ (potential maintainer)

Example usage:

# Install the skill
claude plugin install github-contributor@daymade-skills

# Find good first issues
"Help me find projects with good first issues in Python"

# Write a high-quality PR
"Guide me through creating a PR for this bug fix"

# Build contribution strategy
"Help me plan a contribution strategy for building my GitHub profile"

🎬 Live Demo

Coming soon

📚 Documentation: See github-contributor/references/ for:

• pr_checklist.md - Complete PR quality checklist
• project_evaluation.md - How to evaluate projects for contribution
• communication_templates.md - Issue and PR communication templates

i18n-expert - Internationalization & Localization

Complete internationalization/localization setup and auditing for UI codebases. Configure i18n frameworks, replace hard-coded strings with translation keys, ensure locale parity between en-US and zh-CN, and validate pluralization and formatting.

When to use:

• Setting up i18n for new React/Next.js/Vue applications
• Auditing existing i18n implementations for key parity and completeness
• Replacing hard-coded strings with translation keys
• Ensuring proper error code mapping to localized messages
• Validating pluralization, date/time/number formatting across locales
• Implementing language switching and SEO metadata localization

Key features:

• Library selection and setup (react-i18next, next-intl, vue-i18n)
• Key architecture and locale file organization (JSON, YAML, PO, XLIFF)
• Translation generation strategy (AI, professional, manual)
• Routing and language detection/switching
• SEO and metadata localization
• RTL support for applicable locales
• Key parity validation between en-US and zh-CN
• Pluralization and formatting validation
• Error code mapping to localized messages
• Bundled i18n_audit.py script for key usage extraction

Example usage:

# Install the skill
claude plugin install i18n-expert@daymade-skills

# Setup i18n for a new project
"Set up i18n for my React app with English and Chinese support"

# Audit existing i18n implementation
"Audit the i18n setup and find missing translation keys"

# Replace hard-coded strings
"Replace all hard-coded strings in this component with i18n keys"

🎬 Live Demo

Coming soon

📚 Documentation: See i18n-expert/SKILL.md for complete workflow and architecture guidance.

Requirements:

• Python 3.6+ (for audit script)
• React/Next.js/Vue (framework-specific i18n library)

claude-skills-troubleshooting - Plugin & Skill Troubleshooting

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:claude-skills-troubleshooting)

Diagnose and resolve Claude Code plugin and skill configuration issues. Debug plugin installation, enablement, and activation problems with systematic workflows.

When to use:

• Plugins installed but not showing in available skills list
• Skills not activating as expected despite installation
• Troubleshooting enabledPlugins configuration in settings.json
• Debugging "plugin not working" or "skill not showing" issues
• Understanding plugin state architecture and lifecycle

Key features:

• Quick diagnosis via diagnostic script (detects installed vs enabled mismatch)
• Plugin state architecture documentation (installed_plugins.json vs settings.json)
• Marketplace cache freshness detection and update guidance
• Known GitHub issues tracking (#17832, #19696, #17089, #13543, #16260)
• Batch enable script for missing plugins from a marketplace
• Skills vs Commands architecture explanation
• Comprehensive diagnostic commands reference

Example usage:

# Run diagnostic
python3 scripts/diagnose_plugins.py

# Batch enable missing plugins
python3 scripts/enable_all_plugins.py daymade-skills

🎬 Live Demo

Coming soon

📚 Documentation: See claude-skills-troubleshooting/SKILL.md for complete troubleshooting workflow and architecture guidance.

Requirements: None (uses Claude Code built-in Python)

audio-router - StepFun Speech and Meeting-Minutes Routing

Install: claude plugin install daymade-audio@daymade-skills (suite-only — invoked as daymade-audio:audio-router)

Selects the installed StepFun ASR, StepFun TTS, or transcript-to-minutes specialist and reads its full instructions at use time. Their original slash commands remain available manually. General audio transcription and transcript correction retain direct automatic entries.

meeting-minutes-taker - Meeting Minutes Generator

Install: claude plugin install daymade-audio@daymade-skills (suite-only — invoked as daymade-audio:meeting-minutes-taker)

Transform meeting transcripts into high-fidelity, structured meeting minutes with iterative human review.

When to use:

• Meeting transcript provided and minutes/notes/summaries requested
• Multiple versions of meeting minutes need merging without content loss
• Existing minutes need review against original transcript for missing items

Key features:

• Multi-pass parallel generation with UNION merge strategy
• Evidence-based recording with speaker quotes
• Mermaid diagrams for architecture discussions
• Iterative human-in-the-loop refinement workflow
• Cross-AI comparison for bias reduction
• Completeness checklist for systematic review

Example usage:

# Install the full audio suite (includes meeting-minutes-taker)
claude plugin install daymade-audio@daymade-skills

# Then provide a meeting transcript and request minutes

🎬 Live Demo

Coming soon

📚 Documentation: See daymade-audio/meeting-minutes-taker/SKILL.md for complete workflow and template guidance.

Requirements: None

deep-research - Research Reports and Provider Runs

Generate research reports from a durable study record: original sources, claim-level citations, rejected leads, and prior studies remain available for the next question. When several AI products or modes investigate one decision, coordinate their existing Skills and agents in parallel, preserve original outputs, and synthesize against the underlying sources and business question.

When to use:

• Need a structured research report, literature review, or market/industry analysis
• Require strict section formatting or a template to be enforced
• Need evidence mapping, citations, and source quality review
• Want multi-pass synthesis to avoid missing key findings

Key features:

• Report spec and format contract workflow
• Evidence table with source quality rubric
• Multi-pass complete drafting with UNION merge
• Citation verification and conflict handling
• Project-local source and claim records for single-route and multi-route studies, with a searchable catalog for reuse
• Exact seed-document handoff, persistent session aliases, and verified-source-first catalog search
• Local provider × mode task and artifact ledger with provenance and hash checks
• Read-only parallel dispatch board that separates shared app control, active tasks, completed reports and held routes; actual provider calls follow their own Skills and authorization rules
• Ready-to-use report template and formatting rules

Example usage:

# Install the skill
claude plugin install deep-research@daymade-skills

# Then provide a report spec or template and request a deep research report

🎬 Live Demo

Coming soon

📚 Documentation: See deep-research/SKILL.md, research-asset-contract.md, and research_report_template.md.

Requirements: None

competitors-analysis - Evidence-Based Competitor Intelligence

Discover, clone, update, and analyze competitor repositories with evidence-based competitive intelligence. Repository-backed findings must come from local cloned code; market-landscape claims must cite their source and volatility.

When to use:

• Track and analyze competitor products or technologies
• Discover GitHub competitors for a product or market
• Create evidence-based competitor profiles
• Generate competitive landscape and opportunity reports
• Check whether competitor code has changed
• Need to document technical decisions with cited sources

Key features:

• Durable competitor workspace convention using $HOME/workspace/competitors/{product}/
• GitHub discovery workflow for shortlisting relevant repositories
• Repository ingest/update flow with remote + commit recording
• Required source citation format for repository facts (file:line_number)
• Landscape synthesis for positioning, strengths, weaknesses, opportunities, and risks
• Tech stack analysis guides for Node.js, Python, Rust projects
• Bundled templates: profile template, analysis checklist
• Management script for discover/clone-url/clone/pull/status operations

Example usage:

# Install the skill
claude plugin install competitors-analysis@daymade-skills

# Then ask Claude to analyze a competitor
"分析竞品 https://github.com/org/repo"
"添加竞品到 flowzero 产品的竞品列表"
"看看 claude-flow-viewer 这个方向最近有哪些竞品更新"

🎬 Live Demo

Coming soon

📚 Documentation: See competitors-analysis/SKILL.md and competitors-analysis/references/ for templates.

Requirements: Git (for cloning repositories)

tunnel-doctor - Tailscale + Proxy/VPN Conflict Fixer

Diagnose and fix conflicts when using Tailscale alongside proxy/VPN tools (Shadowrocket, Clash, Surge) on macOS. Covers four independent conflict layers with specific guidance for SSH access to WSL instances.

When to use:

• Tailscale ping works but SSH/TCP connections time out
• Proxy tools hijack the Tailscale CGNAT range (100.64.0.0/10)
• Browser returns HTTP 503 but curl and SSH work
• git push/pull fails with "failed to begin relaying via HTTP"
• Setting up Tailscale SSH to WSL and encountering operation not permitted
• Need to make Tailscale and Shadowrocket/Clash/Surge coexist on macOS

Key features:

• Four-layer diagnostic model: route hijacking, HTTP env vars, system proxy bypass, SSH ProxyCommand double tunneling
• Per-tool fix guides for Shadowrocket, Clash, and Surge
• SSH ProxyCommand double tunnel detection and fix (git push/pull failures)
• Tailscale SSH ACL configuration (check vs accept)
• WSL snap vs apt Tailscale installation (snap sandbox breaks SSH)
• Remote development SOP with proxy-safe Makefile patterns

Example usage:

# Install the skill
claude plugin install tunnel-doctor@daymade-skills

# Then ask Claude to diagnose
"Tailscale ping works but SSH times out"
"Fix Tailscale and Shadowrocket route conflict on macOS"
"git push fails with failed to begin relaying via HTTP"
"Set up Tailscale SSH to my WSL instance"

🎬 Live Demo

Coming soon

📚 Documentation: See tunnel-doctor/references/proxy_conflict_reference.md for per-tool configuration and conflict architecture.

windows-remote-desktop-connection-doctor - AVD/W365 Connection Quality Diagnostician

Diagnose Windows App (Microsoft Remote Desktop / Azure Virtual Desktop / W365) connection quality issues on macOS, with focus on transport protocol optimization (UDP Shortpath vs WebSocket fallback).

When to use:

• VDI connection is slow with high RTT (>100ms)
• Transport Protocol shows WebSocket instead of UDP
• RDP Shortpath fails to establish
• Connection quality degraded after changing network location
• Need to identify VPN/proxy interference with STUN/TURN

Key features:

• 5-step diagnostic workflow from connection info collection to fix verification
• Transport protocol analysis (UDP Shortpath > TCP > WebSocket hierarchy)
• VPN/proxy interference detection (ShadowRocket TUN mode, Tailscale exit node)
• Windows App log parsing for health check failures, certificate errors, FetchClientOptions timeouts
• ISP UDP restriction testing with STUN connectivity checks
• Chinese ISP-specific guidance for UDP throttling issues
• Working vs broken log comparison methodology

Example usage:

# Install the skill
claude plugin install windows-remote-desktop-connection-doctor@daymade-skills

# Then ask Claude to diagnose
"My VDI connection shows WebSocket instead of UDP, RTT is 165ms"
"Diagnose why RDP Shortpath is not working"
"Windows App transport protocol stuck on WebSocket"

🎬 Live Demo

Coming soon

📚 Documentation: See windows-remote-desktop-connection-doctor/references/ for log analysis patterns and AVD transport protocol details.

product-analysis - Multi-Path Product Analysis & Optimization

Run a scalable, evidence-driven product audit using parallel Claude Code agents and optional Codex CLI parallelization. Covers UX, API, architecture, and competitive benchmark workflows with quantified findings and priority recommendations.

When to use:

• Product launch readiness reviews
• Multi-perspective codebase and UX audits before release
• API quality checks with endpoint and consumption consistency reviews
• Competitive benchmarking against selected competitor repos

Key features:

• Auto-detects tool context (project stack + optional codex availability)
• Parallel analysis across dimensions: full, ux, api, arch, compare
• Multi-agent synthesis with quantified findings and P0/P1/P2 recommendations
• Built-in comparison hooks with competitors-analysis
• Cross-validation workflow to reduce overfitting from a single model perspective

Example usage:

# Install the skill
claude plugin install product-analysis@daymade-skills

# Then ask Claude for analysis
"Run product-analysis in full mode for launch audit"
"Do a UX audit and report quantified navigation findings"
"Run API audit and identify unused endpoints"
"Compare this product with our top competitors"

🎬 Live Demo

Coming soon

📚 Documentation: See product-analysis/SKILL.md and product-analysis/references/analysis_dimensions.md for dimension definitions and workflow guidance.

Requirements: Optional codex CLI (for multi-model parallel mode). Skill runs with Claude only if codex is not installed.

financial-data-collector - Financial Data Collection for US Equities

Install: claude plugin install daymade-financial@daymade-skills (suite-only — invoked as daymade-financial:financial-data-collector)

Collect real financial data for any US publicly traded company from free public sources (yfinance). Output structured JSON with market data, historical financials (income statement, cash flow, balance sheet), WACC inputs, and analyst estimates - ready for downstream DCF modeling, comps analysis, or earnings review.

When to use:

• Collecting structured financial data before building DCF or valuation models
• Pulling market data (price, shares, beta, market cap) for any US equity ticker
• Gathering historical income statement, cash flow, and balance sheet data
• Getting risk-free rate (10Y Treasury) and analyst consensus estimates

Key features:

• Robust yfinance field mapping with alias chains (handles API instability across versions)
• NaN year detection and transparent reporting (never fills with estimates)
• 9-check validation: field completeness, market cap cross-check, CapEx sign convention, net debt consistency
• NO FALLBACK principle: missing data returns null with _source attribution, never default values
• FCF definition mismatch flagging (yfinance FCF ≠ investment bank FCF due to SBC)

Example usage:

# Install the suite
claude plugin install daymade-financial@daymade-skills

# Then ask Claude to collect data
"Collect financial data for META"
"Get financials for AAPL --years 3"
"Pull DCF inputs for NVDA"

🎬 Live Demo

Coming soon

📚 Documentation: See financial-data-collector/SKILL.md, output-schema.md, and yfinance-pitfalls.md.

Requirements: Python 3.11+, yfinance, pandas (auto-installed via uv inline dependencies).

excel-automation - Excel Creation, Parsing, and macOS Control

Install: claude plugin install daymade-docs@daymade-skills (suite-only — invoked as daymade-docs:excel-automation)

Create professionally formatted Excel files, parse complex .xlsm models with stdlib XML/ZIP workflows, and control Microsoft Excel windows on macOS via AppleScript.

When to use:

• Building finance-ready spreadsheets with consistent formatting rules
• Parsing complex bank/broker .xlsm files that fail in openpyxl
• Extracting targeted sheet/cell data without loading huge workbooks
• Automating Excel window operations (zoom, scroll, select) on macOS

Key features:

• Production template for formatted workbook generation via openpyxl
• Complex workbook parser using zipfile + xml.etree (no heavy dependencies)
• Corrupted definedNames repair workflow for problematic files
• Verified AppleScript command patterns with timeout safeguards
• Bundled formatting reference for colors, number formats, and table patterns

Example usage:

# Install the documentation suite
claude plugin install daymade-docs@daymade-skills

# Then ask Claude to automate Excel workflows
"Create a formatted valuation template workbook"
"Parse this .xlsm and extract the DCF sheet"
"Generate an AppleScript sequence to zoom and scroll Excel before screenshot"

🎬 Live Demo

Coming soon

📚 Documentation: See excel-automation/SKILL.md and formatting-reference.md.

Requirements: Python 3.8+, uv, openpyxl (auto via uv run --with openpyxl), macOS for AppleScript window control.

capture-screen - Programmatic macOS Screenshot Capture

Install: claude plugin install daymade-macos@daymade-skills (suite-only — invoked as daymade-macos:capture-screen)

Capture application windows by CGWindowID with a reliable three-step workflow: discover window IDs via Swift, control app state via AppleScript, and capture outputs with screencapture.

When to use:

• Automating repeatable screenshot workflows for documentation
• Capturing specific app windows instead of full-screen screenshots
• Producing multi-shot sequences after scripted scroll/zoom changes
• Building visual evidence capture pipelines on macOS

Key features:

• Bundled Swift script to resolve accurate window IDs (CGWindowListCopyWindowInfo)
• Verified AppleScript patterns for app activation and window preparation
• Window-scoped capture commands with silent mode, delays, and format control
• Multi-shot workflow pattern for section-by-section capture
• Clear anti-pattern notes for methods that fail on macOS

Example usage:

# Install the Apple platform suite
claude plugin install daymade-macos@daymade-skills

# Then ask Claude to capture windows programmatically
"Find the Excel window ID and capture it silently"
"Create a multi-shot capture workflow for this workbook"
"Capture Chrome window sections with scripted scrolling"

🎬 Live Demo

Coming soon

📚 Documentation: See capture-screen/SKILL.md.

macos-permissions - Diagnose and Repair macOS Privacy Permissions

Install: claude plugin install daymade-macos@daymade-skills (suite-only — invoked as daymade-macos:macos-permissions)

Use for repeated TCC prompts, silent denials, and background jobs that cannot read protected files. It identifies the actual requester, checks for a usable existing grant, and verifies the repair through the real job. The Skill contains the diagnostic and Full Disk Access repair procedure.

📚 Documentation: See macos-permissions/SKILL.md.

Requirements: macOS. Reading TCC.db also requires Full Disk Access for the process doing the read.

continue-claude-code-work - Resume Interrupted Claude Work

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:continue-claude-code-work)

Continue a verified Claude Code Session without reopening the old interactive
session. The continuation layer first consumes read-claude-code-history, then
reconstructs the original business outcome, unfulfilled requests, corrections,
proven prior assets, and one next action that directly advances the goal.

When to use:

• A user provides a Claude session ID and wants the task continued
• You need to inspect local .claude JSONL files instead of running claude --resume
• A previous session was interrupted and the next concrete step must be reconstructed
• A multi-agent workflow was interrupted and you need to know which subagents completed

Key features:

• Requires a chronological read receipt rather than separate user/assistant tail lists
• Restores original outcome, remaining work, rejected routes, and successful assets
• Verifies current files, git state, external writes, and background work before duplicating anything
• Makes the business result—not parser success, review completion, or subprocess exit—the completion unit

Example usage:

# Then ask Claude to resume from local artifacts
"continue work from session 123e4567-e89b-12d3-a456-426614174000"
"don't resume, just read the .claude files and continue"
"check what I was working on in the last session and keep going"

📚 Documentation: See continue-claude-code-work/SKILL.md.

Requirements: Python 3.8+, git for workspace reconciliation.

scrapling-skill - Reliable Scrapling CLI Workflows

Install, troubleshoot, and use Scrapling CLI with a verified static-first workflow for extracting HTML, Markdown, or text from webpages. Includes a diagnostic script for broken extras installs, Playwright browser runtime checks, and smoke tests against real URLs.

When to use:

• Users mention Scrapling, uv tool install scrapling, or scrapling extract
• You need to choose between static and browser-backed fetching
• You need to extract article bodies from WeChat public pages (mp.weixin.qq.com)
• A Scrapling install works partially but fails on missing extras, browser runtime, or TLS verification

Key features:

• Bundled diagnose_scrapling.py script for CLI, browser runtime, and live URL smoke tests
• Verified default path: start with extract get, escalate to extract fetch only when needed
• WeChat extraction pattern using #js_content for clean article Markdown
• Troubleshooting guidance for missing click, Playwright runtime setup, and curl: (60) trust-store failures
• Output validation workflow using file size and content checks instead of exit-code assumptions

Example usage:

# Install the skill
claude plugin install scrapling-skill@daymade-skills

# Then ask Claude to work through Scrapling for you
"Install Scrapling CLI and verify the setup"
"Extract this WeChat article into Markdown with Scrapling"
"Decide whether this page needs static or browser-backed fetching"

🎬 Live Demo

Coming soon

📚 Documentation: See scrapling-skill/SKILL.md and scrapling-skill/references/troubleshooting.md.

Requirements: Python 3.6+, uv, Scrapling CLI, and Playwright browser runtime for browser-backed fetches.

ima-copilot - Tencent IMA Companion & Installer

One-stop wrapper for the official Tencent IMA skill (ima.qq.com). Installs upstream ima-skill to Claude Code, Codex, and OpenClaw via npx skills add, guides API key setup, detects and repairs known upstream issues under user consent, and implements a personalized fan-out search strategy that floats priority knowledge bases to the top.

When to use:

• Users mention IMA, 腾讯 IMA, ima.qq.com, or need to install the official ima-skill
• Users report Skipped loading skill(s) due to invalid SKILL.md warnings related to ima-skill
• You need to search across IMA knowledge bases with KB-priority boosting
• You need to configure or rotate IMA API credentials
• Upstream ima-skill ships a known issue (e.g., missing YAML frontmatter in submodule files)

Key features:

• Zero-config installation to Claude Code / Codex / OpenClaw via vercel-labs/skills with auto-detection and default symlink mode (fix or upgrade once, every agent sees it)
• XDG-style credential management at ~/.config/ima/{client_id, api_key} with env-var fallback
• scripts/diagnose.sh read-only health check (install presence, credential liveness, known issues)
• scripts/search_fanout.py client-side cross-KB search with priority lists, subset-skip lists, and 100-hit silent-truncation detection
• Wrapper-only architecture: never vendors upstream files, never forks — every repair is a runtime instruction executed with explicit consent and automatic timestamped backups
• Two user-selectable repair strategies for the frontmatter issue (rename to MODULE.md or prepend minimal frontmatter)
• Personalization via ~/.config/ima/copilot.json with illustrative-only template values

Example usage:

# Install the skill
claude plugin install ima-copilot@daymade-skills

# Then ask Claude to drive the flow
"Install ima-skill and configure my IMA API key"
"Run diagnose on my ima-skill and fix whatever is broken"
"Search my IMA knowledge bases for embedding model comparisons, priority to my curated KB"

🎬 Live Demo

Coming soon

📚 Documentation: See ima-copilot/SKILL.md and ima-copilot/references/known_issues.md.

Requirements: Node.js 18+ (for npx skills), curl, unzip, Python 3.6+. IMA OpenAPI credentials from https://ima.qq.com/agent-interface.

claude-export-txt-better - Fix Claude Code Export Formatting

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:fixing-claude-export-conversations)

Reconstruct broken line wrapping in Claude Code exported .txt conversation files. Rebuilds tables, paragraphs, paths, and tool calls that were hard-wrapped at fixed column widths, and ships with an automated 53-check validation suite (file-agnostic, catches over- and under-merging regressions).

When to use:

• Users have a Claude Code export file where tables, paths, or tool output got mangled by line wrapping
• Users mention "fix export", "fix conversation", "make export readable"
• Users reference a file matching YYYY-MM-DD-HHMMSS-*.txt
• Users want to post-process /export output before sharing or archiving it

Key features:

• Deterministic Python script (fix-claude-export.py) with --stats mode for before/after metrics
• 53-check automated validator (validate-claude-export-fix.py) that catches regressions
• Evals directory with real fixture cases
• No external dependencies beyond uv and Python 3.8+

Example usage:

# Fix and show stats
uv run daymade-claude-code/claude-export-txt-better/scripts/fix-claude-export.py broken.txt --stats

# Custom output path
uv run daymade-claude-code/claude-export-txt-better/scripts/fix-claude-export.py broken.txt -o fixed.txt

# Validate the fix
uv run daymade-claude-code/claude-export-txt-better/scripts/validate-claude-export-fix.py broken.txt fixed.txt

🎬 Live Demo

Coming soon

📚 Documentation: See claude-export-txt-better/SKILL.md and the bundled evals/ fixtures.

Requirements: Python 3.8+, uv package manager.

douban-skill - Douban Collection Export & Sync

Export and sync Douban (豆瓣) book / movie / music / game collections to local CSV files via the reverse-engineered Frodo API. Full export covers all history; RSS incremental sync keeps daily updates current. No login, no cookies, no browser — just a user ID and it works.

When to use:

• Users want to back up their Douban reading/watching/listening/gaming history
• Users mention 豆瓣, douban, 读书记录, 观影记录, 书影音
• Users need incremental sync of recent Douban activity
• Users want CSV output compatible with Excel (UTF-8 BOM)

Key features:

• Full export of all 4 categories (books/movies/music/games) via Frodo API
• RSS incremental sync for daily updates (last ~10 items per feed)
• Pre-flight user-ID validation (fail-fast on wrong ID)
• UTF-8 BOM CSV output, Excel-compatible, cross-platform
• Bundled troubleshooting log documenting 7 tested scraping approaches and why each failed (Douban PoW challenges block every web-scraping approach — only Frodo API works)
• .gitleaks.toml allowlist for the public Android APK credentials

Example usage:

# Full export of user's collections
uv run douban-skill/scripts/douban-frodo-export.py <douban-user-id>

# Incremental RSS sync (last ~10 items per category)
uv run douban-skill/scripts/douban-rss-sync.py <douban-user-id>

🎬 Live Demo

Coming soon

📚 Documentation: See douban-skill/SKILL.md and douban-skill/references/troubleshooting.md for the complete failure log of rejected approaches.

Requirements: Python 3.8+, uv package manager. No login or cookies required.

terraform-skill - Terraform Operational Traps

Designs and diagnoses safe Terraform releases as well as the provisioner traps learned from real incidents. It keeps staging and production on one required configuration schema, validates exact candidate bytes + the Compose-rendered environment + the immutable runtime before live mutation, and binds saved plans to staging evidence, source provenance, explicit production authorization, and independent readback.

When to use:

• Writing null_resource provisioners or remote-exec blocks that SSH into fresh instances
• Setting up multi-environment (prod/staging/dev) Terraform with shared modules
• Debugging containers that are Restarting/unhealthy after terraform apply
• Hitting "docker: not found" in remote-exec, rsync connection drops in local-exec, or TLS cert errors
• Troubleshooting drift or provisioner failures during re-runs
• Configuring Caddy/gateway resources with Cloudflare credentials
• Reviewing a saved plan or broad deploy resource that may also mutate a shared gateway
• Closing staging/production config drift, receipt, provenance, or production-approval gaps

Key features:

• One required-key contract for every environment; values may differ, requiredness may not
• Exact-bundle prevalidation for every normal and recovery writer before any live write/restart
• Saved-plan, staging-receipt, remote-main provenance, production-approval, and live-readback gates
• Corrected provider/provisioner patterns for cloud-init, Docker, DNS, TLS, snapshots, and fresh hosts

Example usage:

# Trigger the skill naturally during Terraform work
"I'm getting 'docker: not found' in my null_resource provisioner after apply"
"My rsync local-exec is failing with 'connection unexpectedly closed'"
"Help me write a multi-env Terraform setup without snapshot cross-contamination"
"Staging has this Caddy variable but production leaves it empty — how do I validate both safely?"

🎬 Live Demo

Coming soon

📚 Documentation: See terraform-skill/SKILL.md and the bundled references/ for detailed remediation patterns.

Requirements: None (Terraform-adjacent knowledge only; no runtime dependencies).

slides-creator - Narrative-First Slide Deck Creation

Guides users through structured narrative design (ABCDEFG model), then delegates visual generation to baoyu-slide-deck. Focuses on what machines can't do — narrative co-design with humans.

When to use:

• Creating presentations, slide decks, or PPTs from user content
• Turning articles, transcripts, or notes into visual slides
• Designing narrative arcs for talks and workshops

Key features:

• Phase 0: Source material collection (user's own words first)
• Phase 1: Narrative structure discussion using ABCDEFG model
• Phase 2: Content structuring for machine-readable input
• Phase 3-5: Delegates visual generation to baoyu-slide-deck
• Phase 6: Post-processing with directory reorganization and speaker notes extraction

Example usage:

# Trigger the skill naturally
"Help me turn my article into a slide deck"
"Create a presentation from my talk transcript"
"I need a 20-minute deck for a workshop"

Requirements: baoyu-slide-deck skill for visual generation.

excalidraw-use - Place Images onto an Excalidraw Board

Batch-place existing images onto an Excalidraw whiteboard, laid out on a generous grid so nobody has to drag them apart afterwards. Also turns a slide deck into clean per-slide images first, and inspects what is inside a .excalidraw file. The available Excalidraw MCP servers and skills cover element CRUD and export but document no image element type, no dataURL handling, and no files map — embedding your own pictures is the gap this fills.

When to use:

• Putting screenshots, a picture library, or deck slides onto a whiteboard
• Spacing many images out so they never need manual adjustment
• Turning a Vite/React slide deck into images you can draw over
• Inspecting a scene file: element mix, embedded payload size, occupied extent

Key features:

• Content-hash dedupe and --exclude for images already on the board
• --template-from copies the image-element field set out of your own board — Excalidraw's published schema stops before fileId/status/scale/crop
• Write-back verification: fails on a missing file entry, a distorted aspect ratio, or any overlap
• Deck capture hides presenter chrome, expands staged reveals, and reports fragments that never rendered
• Documents the two silent destroyers: Open and drag-and-drop replace a scene (only the clipboard merges), and a stale build removes a source feature while innerText still reads hidden fragments as present

Example usage:

# Trigger the skill naturally
"Put these screenshots on my Excalidraw board"
"Add my old workshop images to the canvas, spaced out"
"Turn this deck into images I can draw on"

Note: Not for generating a diagram from a text description — that is a different job.

debugging-network-issues - Evidence-Driven Network Investigation

Falsification-first methodology for network, streaming, and protocol-layer bugs where the obvious cause is probably wrong. Built from a real 5-hour SSE incident where assumption-stacking wasted hours that a 10-minute layered experiment would have resolved.

When to use:

• Connection resets (ECONNRESET, HTTP/2 RST_STREAM, INTERNAL_ERROR)
• SSE / long-polling stalls or fixed-time drops (60s, 100s, 130s)
• CDN / proxy / CGNAT idle-timeout incidents
• Client-side proxy / VPN / TUN misrouting (e.g. ERR_CONNECTION_CLOSED, SSL_ERROR_SYSCALL, fake TUN DNS IPs, CNAME-based rule overrides)
• Certificate-verification errors (UNKNOWN_CERTIFICATE_VERIFICATION_ERROR, wrong-site certificate)
• Any "works sometimes / fails after N seconds" pattern
• LAN-layer mysteries: unknown devices on the local network, devices silenced by a subnet change, hosts "dead" on one segment but alive on another
• Multi-hop systems (client → CDN → LB → reverse proxy → app → upstream) where a symptom could plausibly come from several layers

Key features:

• Layered isolation experiments: run the same logical request through three or more paths differing by exactly one hop
• Env-gated runtime instrumentation patterns (no production-code mutation)
• Counter-review four-question filter to challenge single-cause assumptions
• Bundled probe scripts (layered-isolation-probe.sh, mock-idle-upstream.py)
• Real case studies: SSE RST_STREAM at 130s caused by CGNAT idle timeout; proxy/TUN CNAME rule override causing ERR_CONNECTION_CLOSED

Requirements: None (methodology + portable shell/Python probes).

stepfun-tts - StepFun StepAudio 2.5 Contextual TTS

Install: claude plugin install daymade-audio@daymade-skills (suite-only — invoked as daymade-audio:stepfun-tts)

Generate Chinese / Japanese speech with stepaudio-2.5-tts. Captures the two non-obvious TTS pitfalls that cost hours otherwise: voice_label removal (replaced by natural-language instruction) and stricter 2.5-era censorship (死/消失/political terms).

When to use:

• Chinese / Japanese TTS with emotional and prosody control (whisper, pause, stress, mid-sentence pivot)
• Batch-generating game / app voice lines with per-line censorship_block fallback
• Migration from step-tts-2 to stepaudio-2.5-tts (voice_label → instruction breaking change)
• Hitting StepFun censorship blocks on previously-fine content

Key features:

• stepaudio-2.5-tts with instruction (≤200 chars natural-language mood) + inline () prosody
• Bundled tts_generate.py (with --batch <jsonl>) and ab_compare.sh
• API key resolution: $STEPFUN_API_KEY → ${CLAUDE_PLUGIN_DATA}/config.json fallback
• Censorship rewrite playbook in references/migration_from_v2.md

Requirements: StepFun API key, "Normal" tier (https://platform.stepfun.com/). For ASR / transcription, use the sibling stepfun-asr skill below.

stepfun-asr - StepFun StepAudio 2.5 ASR (SSE Endpoint)

Install: claude plugin install daymade-audio@daymade-skills (suite-only — invoked as daymade-audio:stepfun-asr)

Transcribe Chinese / English audio with stepaudio-2.5-asr. Hides the #1 trap of the 2.5 ASR family: it does NOT live on /v1/audio/transcriptions — the wrong endpoint returns a misleading model stepaudio-2.5-asr not supported error that looks identical to a permission/whitelist failure.

When to use:

• Long audio transcription (up to ~30 minutes single-call, 32K context, ~85-101× RTF — no client-side chunking)
• Migration from step-asr / step-asr-1.1 (different endpoint, different body shape, SSE response)
• Hitting the misleading model stepaudio-2.5-asr not supported error (= wrong endpoint, not permission)
• Silent 4xx auth failures on audio endpoints (= using a "Plan" key instead of a "Normal" key)

Key features:

• /v1/audio/asr/sse SSE streaming with base64 audio + nested JSON body (the script handles all four traps)
• Bundled asr_transcribe.py — pure-stdlib CLI, auto-detects mp3/wav/ogg/opus/pcm by extension
• Handles SSE error events (censorship can fire on ASR side too — rare but real)
• API key resolution: $STEPFUN_API_KEY → ${CLAUDE_PLUGIN_DATA}/config.json fallback
• Suggests transcript-fixer (ASR error correction) and meeting-minutes-taker (structured minutes) as natural downstream skills

Requirements: StepFun API key, "Normal" tier (https://platform.stepfun.com/). Plan keys cannot call audio endpoints.

auto-repo-setup - Automated Repository Setup & Environment Repair

Make a repository runnable and handoff-ready without guessing its stack or changing how collaborators normally work. The skill reads project authority first, repairs the verified gap, and treats startup instructions, lifecycle hooks, and Git mutation as different mechanisms with different safety boundaries.

When to use:

• Someone says "跑不起来", "怎么启动", "环境怎么配", or "帮我设置代码库"
• Setting up a new machine or creating a durable repository handoff
• Adding routine startup sync for Claude Code/Codex without auto-stashing local work
• Diagnosing repeated SessionStart output before changing hook configuration
• Adding a lifecycle hook only when behavior must occur before the first prompt
• Sanitizing git history after accidental secret/path leaks
• Handling merge conflicts or git push failures with explicit safety gates

Key features:

• Outcome router: separates environment repair, routine sync, handoff, hook diagnosis, and explicit pre-prompt automation
• Stack-aware inventory: check_env.py infers only declared toolchains from manifests/lockfiles; it does not assume ffmpeg, uv, Python, or .env
• Startup boundary: defaults stable behavior to AGENTS.md/CLAUDE.md or a normal Agent request; the Claude hook manager is guarded, dry-runnable, idempotent, and removable
• Safety guardrails: Push Safety (visibility verification before any push), PII Guard (4-layer secret scanning), NO FALLBACK principle for env vars, Git Hook Bypass ban
• Counter-review boundary: reserves multi-agent review for material shared-config/security/destructive changes, not ordinary setup checks
• Bundled scripts: stack-aware inventory, guarded Claude startup-nudge manager, and read-only history candidate scan

Example usage:

# Install the skill
claude plugin install auto-repo-setup@daymade-skills

# Then ask Claude naturally
"我跑不起来这个仓库"
"帮我设置一下这个项目的环境"
"进入项目先同步远端；本地有改动不要自动 stash"
"为什么同一个 SessionStart 输出了三次？先查清来源"
"只有首条消息前必须注入动态提醒时，才帮我装 hook"
"git push 被拒了"

Requirements: The guidance itself has no runtime dependency. Bundled Python utilities require Python 3.10+; no external API key is required.

terminal-screenshot - See the Real Visual Result of Terminal Output

Render a terminal CLI program's colored output to a PNG so Claude can actually see the rendered result — color contrast, alignment, background blocks, highlighting — instead of only reading plain text and raw ANSI escape codes. Reading a hex value is guessing; seeing the rendered contrast on the real terminal background is verification.

When to use:

• Right after changing any CLI color config (delta / bat / themes / lazygit pager) to visually confirm the result
• Verifying git diff (delta) add/remove contrast, bat syntax highlighting, starship prompt, eza/ls colors, ripgrep matches
• Any time you need to judge "does this color look right / is the contrast enough" instead of guessing from hex codes

Key features:

• Capture-then-render discipline: captures full-fidelity ANSI in a normal shell first, then renders — never lets the renderer run complex CLIs (which degrade in a child pty and drop background blocks)
• freeze-first, zero-dependency fallback: prefers charmbracelet/freeze for faithful rendering; falls back to a bundled stdlib ANSI→HTML converter + headless Chrome when freeze is unavailable
• Real terminal background: renders on the actual terminal background color so dark themes are judged accurately
• Per-CLI capture recipes: delta, git, bat, eza, ls, ripgrep, and a generic forced-color path
• Bundled scripts: render_ansi.sh (freeze/Chrome auto-select), ansi2html.py (stdlib renderer)

Example usage:

# terminal-screenshot lives in the daymade-claude-code suite
claude plugin install daymade-claude-code@daymade-skills

# Then ask Claude naturally
"verify my delta diff colors"
"看一下这个终端配色的真实效果"
"is the add/remove contrast in git diff strong enough?"

Requirements: macOS. charmbracelet/freeze (preferred renderer) or Google Chrome (fallback). Python 3 for the fallback renderer.

pdf-to-html - Read a PDF as Faithful HTML (with Optional Translation)

Convert a PDF into one self-contained, readable HTML file that preserves images, charts and reading order — optionally translating it into another language while keeping every figure. A PDF is a layout, not just a text stream, so the workflow renders each page for you to see before building, and renders the HTML for visual verification before delivery.

When to use:

• Reading a PDF as a clean web page or document (especially on a phone)
• Turning a report or whitepaper PDF into styled HTML without losing its figures
• Translating a PDF into another language while keeping its images, charts and tables in place

Key features:

• Structured extraction (PyMuPDF): text blocks with font sizes + images, with decorative images (footer logos, rules) auto-detected and dropped
• Data-driven build: heading levels inferred from font size, content images compressed and base64-inlined into one portable file
• Optional parallel translation: a Dynamic Workflow translates pages concurrently, captions data charts, and reconciles terminology — with fidelity rules (never invent a translated name; copy numbers and proper nouns verbatim)
• Mandatory visual verification: adaptive headless-Chrome screenshot sliced into readable segments (works around Chrome's ~16384px screenshot cap)
• Bundled failure-cases reference: the real traps (verification, rendering limits, fidelity) so they are not re-discovered

Example usage:

# pdf-to-html lives in the daymade-docs suite
claude plugin install daymade-docs@daymade-skills

# Then ask Claude naturally
"把这个 PDF 转成中文网页版"
"make this report readable as HTML"
"translate this PDF to English but keep the charts"

Requirements: uv, Google Chrome or Chromium (visual verification). Python packages (PyMuPDF, Pillow, numpy) auto-install via uv run --with.

asr-transcribe-to-text - Audio/Video Transcription with Qwen3-ASR

Install: claude plugin install daymade-audio@daymade-skills (suite-only — invoked as daymade-audio:asr-transcribe-to-text)

Transcribe audio and video files to text using Qwen3-ASR via two interchangeable inference paths: local MLX on macOS Apple Silicon (no API key, 15-27x realtime) or a remote vLLM/OpenAI-compatible API for any platform. Auto-detects the platform and recommends the best path, persisting the choice in ${CLAUDE_PLUGIN_DATA}/config.json.

When to use:

• Transcribing meeting recordings, lectures, interviews, podcasts, or screen recordings
• Converting any audio/video file to text (speech-to-text)
• Local, free transcription on an Apple Silicon Mac, or remote API when local is unavailable
• The first stage of a transcribe → correct → minutes pipeline

Key features:

• Dual inference paths — local MLX (15-27x realtime, free) and remote API, with automatic platform detection
• Bundled transcribe_local_mlx.py loads the model once and processes files sequentially (no GPU contention)
• Uses low-energy ~20-minute chunks with an 8192-token per-chunk bound, atomic checkpoints/resume, and full process-tree cleanup so one bad chunk cannot become an unbounded GPU job
• Remote fallback overlap_merge_transcribe.py splits into 18-minute chunks with 2-minute overlap and fuzzy-merges
• ffmpeg video→16kHz mono WAV extraction, truncation verification, and proxy-bypass handling
• Proactively suggests transcript-fixer to clean ASR recognition errors on the output

Example usage:

# asr-transcribe-to-text lives in the daymade-audio suite
claude plugin install daymade-audio@daymade-skills

# Then ask Claude naturally
"transcribe this meeting recording to text"
"把这个录音转成文字"
"convert lecture.mp4 to a transcript"

Requirements: uv, ffmpeg/ffprobe. Local MLX path needs macOS Apple Silicon; remote path needs a reachable vLLM/OpenAI-compatible ASR endpoint. No API key for local mode.

marketplace-dev - Skills Repo → Plugin Marketplace

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:marketplace-dev)

Create and maintain Claude Code plugin marketplaces: convert a repository, consolidate standalone skills into a new or existing suite, move skills between suites, validate real installation/cache boundaries, and ship the result through a PR.

When to use:

• Making a skills repo installable via claude plugin install
• Generating or fixing a marketplace.json (plugin distribution, one-click install, auto-update)
• Adding a new plugin to an existing marketplace and bumping the right versions
• Putting existing skills into a suite, moving a skill between suites, or making members suite-only
• Debugging schema rejections like Unrecognized key: "$schema" or duplicate plugin names

Key features:

• Evidence-intake phase that mines docs and local session history instead of guessing from a template
• Encodes non-obvious schema rules: $schema is rejected, metadata has only 3 valid fields, strict: false semantics, single-skill vs suite source/skills patterns
• Bundled check_marketplace.sh runs four checks (JSON syntax → claude plugin validate → source/skills resolution → reverse sync) and exits non-zero on failure
• Installation, cache-footprint, and GitHub-install test recipes to confirm source produced the intended snapshot
• Dedicated suite-consolidation workflow covering canonical moves, byte/mode preservation, repository-wide install/path drift, existing-user migration, isolated real installation, and immutable review
• Two PostToolUse hooks (validate on marketplace.json edit; warn on un-bumped version when a SKILL.md changes) that auto-activate with the plugin

Example usage:

# marketplace-dev lives in the daymade-claude-code suite
claude plugin install daymade-claude-code@daymade-skills

# Then ask Claude naturally
"turn this skills repo into a plugin marketplace"
"generate a marketplace.json for this repo and validate it"
"add my new skill to the marketplace and open a PR"
"move these standalone skills into daymade-macos and make them suite-only"

Requirements: claude CLI (for claude plugin validate / install tests), jq. Git remotes configured if opening an upstream PR.

skill-creator - Create, Improve & Benchmark Skills

Install: claude plugin install daymade-skill@daymade-skills (suite-only — invoked as daymade-skill:skill-creator)

The essential meta-skill for building your own skills. It scales verification to the change: bounded fixes get targeted checks, narrow behavior changes get sampled replays, and broad/high-risk work becomes eligible for heavier evidence without automatically starting it. Paired baselines, graders, benchmarks, and viewers require explicit authorization or a decision-bearing evidence plan plus opt-in. It also supports explicit benchmarking and optimizes a skill's description for better triggering accuracy.

When to use:

• Creating a skill from scratch, or editing/optimizing an existing one
• Running evals to test a skill, or benchmarking performance with variance analysis
• Improving a skill's description so Claude triggers it more reliably
• Wrapping a third-party CLI tool you just got working into a reusable companion skill

Key features:

• Prior-art research across the live conversation, explicitly approved prior history, local SOPs, installed plugins/MCPs, skills.sh, official plugins, npm/PyPI — to reuse infrastructure and encode only the user's unique methodology
• The inline-vs-context: fork decision guide (subagents can't spawn subagents or call skills) and composable/orthogonal skill design
• init_skill.py scaffolding, package_skill.py (auto-validates), and security_scan.py (gitleaks-based secret/PII detection)
• Existing-skill migration gate: tool-attested snapshot or verified Git-commit baseline, runtime-reachability-aware capability audit, explicit dispositions, and package-time re-verification that a clean commit or hand-written marker cannot bypass
• Risk-scaled verification router: Tier 1 targeted checks, Tier 2 sampled behavior replay, and Tier 3 broad/high-risk classification without automatic fan-out
• Separately authorized full-eval harness: with-skill + baseline runs, assertions, grading, benchmark aggregation, and an HTML viewer after an explicit request, or after a decision-bearing evidence plan receives opt-in
• Mandatory sanitization read-through for public skills — catches no-keyword leaks scanners miss
• Description-optimization loop (60/40 train/test split, selects best description by held-out score)

Example usage:

# skill-creator lives in the daymade-skill suite
claude plugin install daymade-skill@daymade-skills

# Then ask Claude naturally
"create a skill that does X"
"improve this skill's description so it triggers more reliably"
"benchmark this skill against a no-skill baseline"

Requirements: Python 3, uv, PyYAML (validation/packaging), gitleaks (security scan). claude CLI only for agent evals and description-optimization runs.

feishu-doc-scraper - Feishu/Lark → Faithful Markdown + Source-First Archive

Extract Feishu (Lark) Docs, Wiki pages/collections, spreadsheets (including cell-attachment file download), and Minutes (妙记) transcripts into faithful local Markdown. The primary path uses the lark-cli API — it extracts the document body programmatically (no model paraphrasing), recursively follows a collection's reference graph, and reads permission boundaries from error codes; a browser-DOM path is the fallback only when lark-cli cannot reach the content.

When to use:

• The source is a Feishu/Lark URL and fidelity matters (导出飞书文档/合集/妙记转写)
• Converting a Feishu wiki/knowledge base to Markdown, or archiving a Feishu collection
• Exporting a Feishu Minutes (妙记) transcript
• Converting an owner-exported .docx into faithful Markdown with heading/highlight restoration

Key features:

• Document comments and complete reply threads accompany the body, with quoted passages, source positions, author IDs, timestamps, solved scope, and explicit coverage gaps
• lark-cli API extraction writes the body to disk via jq (never retyped by the model — the single most important fidelity rule)
• Recursive reference-graph traversal (BFS) with feishu_extract_refs.py, plus a residual rich-media-tag acceptance gate so no referenced doc is silently missed
• Native Minutes transcript export (never re-runs ASR on downloaded media)
• Permission-denied path: owner-exported .docx → Markdown with font-size→heading and w:shd→highlight restoration, then visual verification
• Source-first artifact manifest + fail-closed validator: structured/searchable derivatives go to Git, raw binaries remain on Feishu or an explicitly chosen object store, and local downloads stay optional caches instead of Git LFS payloads
• LARK_CLI_NO_PROXY=1 discipline for *.feishu.cn (avoids credential leak/DNS hijack) and a U+FFFD encoding-corruption final check
• Works with both Feishu (feishu.cn) and Lark (larkoffice.com)

Example usage:

# Install the skill
claude plugin install feishu-doc-scraper@daymade-skills

# Then ask Claude naturally
"把这个飞书合集导出成 markdown"
"export this Feishu Minutes transcript"
"save this Lark wiki page as Markdown"

Requirements: lark-cli binary (npm @larksuite/cli) authenticated to the target tenant; jq. Fallback path needs a browser-automation surface; the docx path needs python-docx and a docx→md converter (the bundled doc-to-markdown skill or pandoc).

financial-router - Financial Data Routing

Install: claude plugin install daymade-financial@daymade-skills (suite-only — invoked as daymade-financial:financial-router)

Routes Bigdata/RavenPack, free US company fundamentals, A-share news, sector Top N and announcements, and Gangtise setup to one bundled specialist. Pharmaceutical reporting and general argument review keep their direct Skills; all specialist slash commands remain available for manual use.

bigdata-skill - Bigdata.com (RavenPack) SDK + REST Toolkit

Install: claude plugin install daymade-financial@daymade-skills (suite-only — invoked as daymade-financial:bigdata-skill)

Pull Bigdata.com (RavenPack) financial and news data through the official bigdata-client SDK and its public /v1/* REST endpoints — reaching the structured substrate the Bigdata MCP server doesn't hand over. The MCP returns prose chunks and pre-synthesized tearsheets; this toolkit reaches structured financials, prices, analyst estimates, a daily entity-sentiment series, annotated chunk search with sentiment + entity spans, and a screener.

When to use:

• Using Bigdata.com / RavenPack and the MCP result feels thin ("where's the sentiment score?", "I need entity-level data", "the calendar")
• Pulling forward/structured financials: analyst estimates, earnings/event calendar, surprises, ratings, price targets, statements, TTM metrics, a company screener
• Wanting annotated news chunks with numeric sentiment + entity spans, a sentiment time series, or a co-mention graph
• Mentions a bd_v2_ API key, rp_entity_id, query_unit/chunk cost, bigdata-client, or "the bigdata MCP isn't enough"

Key features:

• One BigdataClient exposing both the SDK (search + knowledge graph) and a REST escape hatch (bd._api.http) for every /v1/* endpoint the SDK never wrapped
• Routing table mapping each question to the right module; fields_values_to_records() to flatten {fields, values} responses
• Cost discipline: 1 query_unit = 10 chunks, only chunk-search billed, ChunkLimit (never a bare int), rerank thresholds, 50%-cheaper batch search, and a CostModel/CostTracker budget veto
• The "two data faces" guidance — structured financial (works for A-shares via English name/ISIN) vs unstructured Chinese NLP (a data-source-level dead end)
• rc() SSL-retry wrapper for the common first-handshake SSL: UNEXPECTED_EOF, plus a known-pitfalls reference with reproductions and fixes
• Fail-fast on a missing BIGDATA_API_KEY (no plaintext fallback); read-only, never writes/uploads

Example usage:

# Install the suite
claude plugin install daymade-financial@daymade-skills
export BIGDATA_API_KEY=bd_v2_xxxxxxxx

# Then ask Claude naturally
"pull NVIDIA's forward analyst estimates and last earnings surprise from Bigdata"
"give me a daily entity-sentiment series for this ticker"
"the bigdata MCP only gave me a tearsheet — I need the structured fields"

Requirements: A bd_v2_ Bigdata.com API key (env var, never hardcoded), uv, the official bigdata-client SDK in an isolated venv. Optional outbound/WSS proxy only if your network needs one to reach api.bigdata.com.

gangtise-copilot - Gangtise Investment-Research Suite Installer

Install: claude plugin install daymade-financial@daymade-skills (suite-only — invoked as daymade-financial:gangtise-copilot)

One-command installer, credential configurator, and diagnostic layer for the full Gangtise (岗底斯投研) OpenAPI skill suite. Installs the official Gangtise skills (data, research, utility), configures accessKey/secretAccessKey with a live auth check, and runs a read-only health diagnostic — solving the suite's core discoverability problem (no public manifest, listing-disabled OBS bucket, parallel naming lines).

When to use:

• The user mentions Gangtise / 岗底斯, or any gangtise-* skill
• Setting up Gangtise credentials (accessKey / secretAccessKey)
• Errors like token is invalid / 接口地址错误, or "my gangtise install is broken"
• Routing a data question (research reports, chief-analyst opinions, OHLC, valuation) to the right Gangtise skill

Key features:

• install_gangtise.sh downloads the declared OBS bundles → extracts skill directories → symlinks them into detected agent skills dirs (Claude Code, OpenClaw, Codex), with minimal/workshop/full/--only presets
• configure_auth.sh writes a shared XDG credential file (mode 600), runs a live auth call, and symlinks every skill's .authorization to it
• Read-only diagnose.sh reports install state, credential validity, and scoped capability tiers (auth scope vs RAG scope)
• Skill registry routing a data question by data tier and operation type
• Wrapper contract: never vendors/forks upstream files, always re-downloads the canonical OBS artifact, and asks before touching any installed skill

Example usage:

# Install the suite
claude plugin install daymade-financial@daymade-skills

# Then ask Claude naturally
"装一下 gangtise 的所有 skill 并配置好凭据"
"my gangtise skills report token is invalid — diagnose it"
"宁德时代的研报用哪个 gangtise skill 查"

Requirements: A Gangtise accessKey + secretAccessKey; bash, curl, network access to the official OBS bucket and open.gangtise.com. Works with Claude Code, OpenClaw, and Codex agent layouts.

llm-wiki-setup - Co-Create a Personal Investment-Research LLM Wiki

Co-create a personal investment-research LLM Wiki (Andrej Karpathy's pattern) where the user's OWN analysis framework becomes a living CLAUDE.md — built by interviewing them rather than handing over a template. Pure markdown + [[wikilinks]]; knowledge is compiled into pages instead of being re-retrieved from raw files on every query (Karpathy's core idea — no RAG pipeline in place of compilation; a local search engine such as qmd over the grown wiki is part of his pattern). The value is extracting the user's personal investment preferences into THEIR OWN schema, never imposing a standard one.

When to use:

• Building a compounding research knowledge base (投研第二大脑 / 投研知识库 / 个人投研 wiki)
• Instantiating Karpathy's LLM Wiki pattern for finance/investing
• Turning a stock-picking, analyst-tracking, or earnings-watching workflow into a structured markdown vault
• Ingesting research reports / earnings calls / expert notes into an existing wiki, or running post-earnings prediction→fulfillment reviews

Key features:

• Sharp mechanism-layer vs rule-layer split: the three-level directory + wikilink + lint + git hook scaffold is copyable; the analysis schema is interview-grown, never templated
• init_vault.py scaffolds the mechanism layer only (no schema), then an 8-dimension interview builds the user's own CLAUDE.md in their own words
• Anti-corrosion: git hook + lint-vault.py keep the vault consistent and fight derived-value drift
• SOPs for ingesting a real source (HITL 5-checkpoint flow) and post-earnings fulfillment reviews
• Runs inline (calls the analyst-track-record skill and Bash) and chains into analyst-track-record for analyst back-testing — without rebuilding it

Example usage:

# Install the skill
claude plugin install llm-wiki-setup@daymade-skills

# Then ask Claude naturally
"帮我搭一个投研第二大脑"
"build me a personal investment-research wiki in Karpathy's style"
"ingest this earnings call into my research vault"

Requirements: Python 3, uv (for init_vault.py / lint), git. Markdown + wikilinks; no vector DB or embedding service required (qmd is an optional local search layer once the wiki grows). Pairs with the analyst-track-record skill for back-testing.

benchmark-due-diligence - Adversarial Teardown of an Envied Benchmark

Install: claude plugin install daymade-financial@daymade-skills (suite-only — invoked as daymade-financial:benchmark-due-diligence)

Run adversarial due-diligence on a benchmark the user envies — a founder, KOL, company, or product whose claimed success looks inflated — separating marketing bubble from real signal, then mapping the validated playbook onto the user's own resources. The adversarial, decision-oriented cousin of deep-research: it assumes the picture is inflated until proven otherwise and ends in "what this means for ME", not a neutral report.

When to use:

• Wanting to 尽调/对标/拆解 a competitor or role-model, or 抄/偷师 someone's playbook
• Suspecting 水分/泡沫 in someone's claims (#1 on Product Hunt, 0-to-1M users, funding, 估值几个亿)
• Asking whether wins are 真本事 vs 运气/时机, or saying someone is 太成功了 and wanting the real story
• Preferring a debunk + replicable playbook over deep-research's neutral briefing

Key features:

• Two strictly-separated injection channels — public FACTS go to every agent; private COMMISSIONER_CONTEXT reaches only the final mapping agent (so client names never leak into open-web searches)
• Phase 0 foundation-by-evidence: verifies the benchmark's real entity graph and headline-claim attribution before any fan-out (don't reason from names/domains)
• Four-phase orchestration — collect → adversarial verify (L1-L4 grading, 坐实/存疑/证伪-水分 verdicts) → due-diligence conclusion (bubble-busting table + attribution breakdown) → commissioner resource-mapping
• Reuses existing plumbing instead of rebuilding it (deep-research fan-out, osint-investigate identity checks, the qcc family for 工商 data, agent-reach for social-platform data)
• Runs inline (it's an orchestrator — context: fork would silently break the fan-out)

Example usage:

# Install the financial research suite
claude plugin install daymade-financial@daymade-skills

# Then ask Claude naturally
"帮我尽调一下这个创始人，他到底有没有水分"
"tear down this competitor's playbook and tell me what I can actually copy"
"this KOL claims 0-to-1M users — is that real, and is it replicable for me?"

Requirements: Web access for the collection/verification agents. Optionally composes with deep-research, osint-investigate, the qcc skill family, and agent-reach; renders a shareable report via pdf-creator.

bilibili-source - Login-Free Bilibili Video Data + Danmaku Fetcher

Fetch real, citable data for any Bilibili (B站) video — title, UP follower count, publish date, tags, partition, per-part cids, live stats (view/like/coin/favorite/share/reply/danmaku), and full danmaku (bullet-comment) text — in one view/detail call, login-free. Built so engagement numbers are cheap to fetch and impossible to fake, instead of hand-typed into a doc where they rot.

When to use:

• Ingesting a Bilibili video into a knowledge base, or building a "why did this perform" case study
• Verifying a creator's claimed view/like/favorite numbers, or about to write any B站 metric into a document
• Wanting the danmaku text (qualitative audience reactions), not just a reply count
• Pasting a BVID, av number, b23.tv short link, or full URL — all normalized automatically

Key features:

• One bili-fetch.sh returns full metadata + live stats + UP fans + tags + every part's cid; metrics carry a fetched_at timestamp because they drift in real time
• bili-danmaku.sh pulls and decompresses the danmaku full text; bili-subs.sh handles the login-gated subtitle track (asks before touching browser cookies)
• bili-selftest.sh health-check verifies every endpoint against the live API, so API drift surfaces as one clear FAIL instead of a silent wrong answer
• NO-FABRICATION discipline: an unfetchable number is marked unverified, never estimated
• Strips the local proxy (Bilibili is a domestic CN service), sends UA+Referer (avoids HTTP 412), retries with backoff
• API reference includes the login-gated favorites (收藏夹) enumeration endpoints (x/v3/fav/*, verified no-WBI), the verified SESSDATA subtitle path, and the WBI request-signing algorithm for space/wbi/* extension

Example usage:

# Install the skill
claude plugin install bilibili-source@daymade-skills

# Then ask Claude naturally
"pull the real view/like/favorite counts for this B站 video so I can cite them"
"这个 B站 视频弹幕里大家在说什么？"
"grab the subtitle transcript from this bilibili video so I can summarize it"

Requirements: curl, jq, python3 (danmaku decompression). yt-dlp only for the login-gated subtitle path. No login for stats / metadata / danmaku.

ghostty-use - Ghostty Terminal Session Snapshot & Restore

Preserve and recover recorded Ghostty CLI sessions through the
canonical Skill. For scheduled metadata backups, partial
coverage and operating prerequisites, use the
automatic workflow.

claude plugin install ghostty-use@daymade-skills

# Then ask Claude naturally
"我要重启电脑更新，把终端会话都保存一下"
"恢复之前的 ghostty 窗口和会话"
"restore my ghostty tabs after the update"
"检查一下有没有会话丢了"

claude-usage-analyst - Explain Claude Code Token Usage & Quota Burn

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:claude-usage-analyst)

Turn local ccusage data into an evidence-based, human-readable explanation of where your Claude Code / Claude Desktop tokens, cost, and quota went — separating observed numbers from interpretation instead of guessing.

When to use:

• Asking why a Claude quota or 5-hour block got exhausted
• Wondering whether a model (fable / opus / sonnet) is unusually expensive for your workload
• Needing today's or a historical window's token/cost breakdown, including cache read/write pressure
• Explaining usage to a non-technical reader without unexplained jargon

Key features:

• Bundled analyze_claude_usage.py summarizes tokens, cost, input/output, and cache create/read over any date window and timezone
• Model-comparison mode (--model-a / --model-b) weighs both token volume and estimated cost — a model can be cheap per token but expensive overall
• A 5-hour-block table for quota-exhaustion questions
• Evidence discipline: every numeric claim is grounded in ccusage output; cache-read pressure is counted even when you never typed those tokens
• Scope is stated explicitly: ccusage claude measures local Claude Code logs, not a full Claude.ai chat bill

Example usage:

# Install the suite
claude plugin install daymade-claude-code@daymade-skills

# Then ask Claude naturally
"why did my Claude quota run out today?"
"is opus more expensive than sonnet for what I'm doing?"
"break down my Claude Code token usage for this month"

Requirements: ccusage (via npm i -g ccusage or npx ccusage@latest), python3.

marketplace-health-check - Full 6-Dimension Repo Health Check

claude plugin install marketplace-health-check@daymade-skills

Run a comprehensive, evidence-based health check of this skills marketplace repo with a parallel fan-out Dynamic Workflow — six inspectors cover code/script safety, documentation/SSOT consistency, security/PII leaks, open-PR triage, open-issue triage, and marketplace-manifest integrity at once — then the serious findings are Counter-Reviewed before they reach the report.

When to use:

• Before a release, or any time you want a full "is this whole repo OK across the board" sweep
• Checking whether docs/versions are consistent, PRs/issues are triaged, or PII has leaked into a public skill
• 全面体检 / 检查仓库状态 / 审计一下仓库

Key features:

• Six parallel inspectors (one per dimension) via a Dynamic Workflow — fast and focused (~15-20 min)
• Counter-Review: every high/critical finding is verified by hand before it reaches the report (agent findings are hypotheses, not conclusions) — catches false alarms AND wrong fixes
• Priority-ranked report: must-fix / backlog / optional / key insights, each item tagged real vs false-alarm
• Bundles the proven workflow script + a methodology reference (anti-target PII rule, working-copy-vs-history, scan-marker necessary-not-sufficient, the broken-install-command bug class)
• Inline orchestrator — drives the Workflow tool, so it never runs forked

Example usage:

# Install
claude plugin install marketplace-health-check@daymade-skills

# Then ask Claude naturally
"do a full health check of this repo before I cut a release"
"audit the marketplace — code, docs, PII, PRs, issues, everything"
"全面体检一下这个仓库"

Requirements: gh CLI (authenticated), git, jq, python3; opt-in to the Workflow tool (asking to run the health check is the opt-in).

claude-switch-models-setup - Multi-Provider Claude Code Profiles

claude plugin install daymade-claude-code@daymade-skills

Set up multiple isolated Claude Code CLI profiles so you can run different LLM providers (Kimi, MiniMax, GLM, DeepSeek, StepFun, Anthropic) in separate terminal windows at the same time — each profile gets its own .claude.json state while sharing skills, projects, hooks, and agents.

When to use:

• You want one terminal with Kimi and another with DeepSeek running side-by-side
• You need to switch between Anthropic and third-party models without config bleed
• You're setting up a post-workshop environment for students who want the same multi-provider workflow

Key features:

• One-click installer links its declared runtime scripts into ~/.config/claude-switch-models-setup/ and seeds an empty Codex activation manifest only when none exists
• Includes provider-specific ~/.claude/settings/<provider>.json templates with required isolation flags
• claude-profiles-init creates isolated ~/.claude-profiles/<provider>/ directories with symlinked shared resources
• Profile sync mirrors enabled plugins from the default Claude profile and shares installed plugin state
• Local source sync keeps Claude plugin caches source-backed, but links only the explicit Codex selection into ~/.agents/skills; a declared active subset may keep legacy ~/.codex/skills compatibility links
• A maintainer LaunchAgent watches the activation manifest and marketplace/install topology, while reporting non-compatible legacy links for reviewed cleanup instead of deleting them
• Built-in marketplace path pollution fixer runs automatically on every profile launch
• Includes student setup guide and troubleshooting reference

Example usage:

# Install the suite
claude plugin install daymade-claude-code@daymade-skills

# Then ask Claude naturally
"set up Claude Code profiles for Kimi and DeepSeek"
"I want to run Kimi and Anthropic in separate terminals"
"install the multi-provider profile setup from the workshop"

Requirements: claude CLI, zsh or bash, python3, plus API keys for the providers you want to use.

llm-eval-harness - Four-Dimension LLM Endpoint Evaluation

claude plugin install llm-eval-harness@daymade-skills

Evaluate any LLM behind an OpenAI- or Anthropic-compatible endpoint across four dimensions — instead of trusting a vendor's headline numbers — and report measured results separately from inferred ones.

When to use:

• Benchmarking a model, or verifying a vendor's tokens-per-second claim
• Comparing two models head-to-head under identical conditions
• Vetting a newly released or "Anthropic-compatible" endpoint before adopting it
• Probing concurrency limits before a workshop or batch job

Key features:

• Four dimensions, four scripts: speed (speed_probe.py — TTFT + thinking-aware tokens/sec), concurrency/stability (concurrency_probe.py — success rate, p50/p90, breaking point), Anthropic protocol compliance (protocol_probe.py — thinking-block trigger rate over N≥10), and quality regression (usecase_runner.py + independent blind judges)
• Thinking-aware throughput: captures reasoning_content separately so reasoning tokens don't inflate tok/s (the trap that once read a ~750 tok/s model as 4700)
• Probabilistic protocol verdicts: fully-implemented / intermittent (k/N) / not-implemented, never concluding from a single sample, with Connection: close so a load balancer can't pin all samples to one replica
• Blind-judge quality: 3 independent judges per case, majority-pass, with per-category precision to surface a systematically weak category
• Keys via env-var name only (--key-env MY_KEY) — the key never appears in ps, shell history, or a saved report
• Your use-case library lives outside the bundle (e.g. ~/.llm-eval/usecases.json) so it survives skill updates and never lands in a public repo

Example usage:

export MY_KEY=sk-...   # the key never appears in a command below

# Speed: real-task throughput + sustained decode ceiling
uv run --with openai python scripts/speed_probe.py \
  --base-url https://api.example.com/v1 --model some-model --key-env MY_KEY --mode both

# Concurrency: ramp until it breaks
uv run --with aiohttp python scripts/concurrency_probe.py \
  --url https://api.example.com/v1/chat/completions --model some-model \
  --key-env MY_KEY --format openai --concurrency 10 20 40 60

🎬 Live Demo

Coming soon

📚 Documentation: See llm-eval-harness/references/evaluation_disciplines.md for the reasoning behind each discipline and llm-eval-harness/references/quality_blind_judge.md for the blind-judge method.

Requirements: Python 3.8+, uv; openai and aiohttp (auto-installed via uv run --with); an API key for the endpoint under test. Optionally composes with promptfoo-evaluation for rubric-based gating.

read-claude-web-conversation - Extract Claude.ai Web Conversations

Install: claude plugin install daymade-claude-code@daymade-skills (suite-only — invoked as daymade-claude-code:read-claude-web-conversation)

Extract the complete active Claude.ai conversation through the Claude Code
operations suite: message text, real tool calls and outputs, uploads, generated
images, and sandbox deliverables. Render faithful Markdown locally, reconstruct
files created through tool calls, or download original bytes through the
logged-in browser session.

When to use:

• Reading a Claude.ai web conversation that is not available in local Claude Code logs
• Recovering a full web thread for handoff, audit, or archival
• Comparing browser-visible content with exported or local session artifacts
• Preserving the analysis trace from agent conversations whose tool calls are collapsed in normal exports
• Downloading uploads and assistant-produced files that belong to the active conversation branch
• Using the macOS AppleScript channel when the Chrome extension is paired to a different account

Requirements: Installed daymade-claude-code suite and a logged-in Chrome
session. The AppleScript fallback requires macOS and one user-enabled Chrome
developer-menu toggle.

setup-notifications-via-wecom - Reusable WeCom Notification Setup

claude plugin install setup-notifications-via-wecom@daymade-skills

Set up reusable WeCom (Enterprise WeChat) webhook notifications for technical status reports, alerts, and completion messages. The target is explicitly classified: the user's own channel may send automatically; every other target requires human confirmation.

For recurring reports on an existing SLS pipeline, follow the bundled adapter guide for truncation limits, evaluation dates, recipient conflicts and native delivery acceptance.

When to use:

• Configuring a reusable 企业微信 / WeCom notification channel
• Sending structured status notifications, backup reports, or alerts
• Turning a one-off webhook into a repeatable notification workflow

Requirements: WeCom bot webhook URL and shell access.

notify-wecom - One-Off WeCom Message

claude plugin install notify-wecom@daymade-skills

Send a single WeCom group-bot message using the configured target identity: self sends directly, while others requires human confirmation.

When to use:

• /notify-wecom
• 临时发一条企业微信 / 企微通知一下
• One-shot alerts that do not need templates or persistent setup

Requirements: WeCom bot webhook URL plus the explicit recipient scope/label and canonical sender binding created by the setup command.

github-sensitive-data-cleanup - GitHub Sensitive Data Cleanup

claude plugin install github-sensitive-data-cleanup@daymade-skills

Scan and remove sensitive data from GitHub repository history, with backup, visibility checks, and force-push safety gates.

When to use:

• A repo leaked secrets, private domains/IPs, API keys, or PII
• Cleaning git history before or after a public exposure
• Verifying safety before any force push to a public repository

Requirements: git, GitHub access, and the relevant scanning/history-rewrite tools for the target repository.

codex-image-gallery - Local Browser for Codex Generated Images

Install: claude plugin install daymade-codex@daymade-skills (suite-only — invoked as daymade-codex:codex-image-gallery)

Start a self-contained local web gallery for Codex-generated image outputs. The skill bundles its Node server and HTML UI, scans ~/.codex/generated_images by default, and can point at another folder with GALLERY_ROOT.

When to use:

• Browsing Codex generated images in a local UI
• Inspecting ~/.codex/generated_images
• Reviewing a custom image output directory with search, batches, and image detail view

Key features:

• Bundled scripts/server.mjs and assets/index.html
• Dynamic /api/images scan; no hardcoded manifest
• /images/<relative-path> image route with path traversal protection
• Optional GALLERY_ROOT, PORT, and HOST

Requirements: Node.js 18+ and access to the image folder.

frontend-visual-qa - Rendered Frontend and Browser Output Visual QA Gate

claude plugin install frontend-visual-qa@daymade-skills

Audit the UI users can actually see, with explicit evidence levels and no source mutation by default.

When to use:

• Auditing an already-rendered web or desktop UI after implementation
• Diagnosing typography, wrapping, clipping, overflow, responsive, route/state, overlay, map, or transient-state defects
• Comparing a rendered artifact with a named visual reference or design-system SSOT
• Checking converted Markdown figures and illustrated transcript/note image sizes inside the actual Obsidian or other recipient reading view
• Verifying export, download, share, popup, print/PDF, or Electron-shell behavior at the evidence level the claim requires
• Complementing ui-designer/design work and the broader process managed by qa-expert

Key features:

• Audit-only default with scoped profiles and verified / partial / blocked outcomes
• A–D evidence ladder that prevents headless, renderer-only, or handler-only checks from masquerading as real GUI proof
• State/viewport-first workflow, including authenticated-but-role-less branches and exact projection/deck canvases, plus inspected screenshots and DOM geometry
• Hardened Playwright-powered sweep for navigation status, effective mobile viewport, overflow, clipping, custom-control focusability, images, and section evidence
• Conditional references for core visual checks, complex journeys/page contracts, and data visualization—including units/source/time/freshness, dense collisions, runtime-label truth, and real file-dialog boundaries
• Public behavior and trigger evals with self-contained fixtures

openclaw - OpenClaw (龙虾) Config Manager

claude plugin install openclaw@daymade-skills

Manage OpenClaw (龙虾/lobster) instance configurations — audit, diff, copy, add-model, list, and switch models across openclaw.json files.

When to use:

• Managing multiple OpenClaw / Claude Code wrapper instances
• Applying DeepSeek model patches to an instance
• Auditing, diffing, or copying provider/model config between instances
• Managing default models and aliases, or validating config

Key features:

• Unified CLI: audit / diff / copy / add-model / list / switch
• Auto-audit on mutating commands with a --no-audit escape hatch
• Nickname registry for cross-config operations

download-gemini-images - Download Images from Gemini Conversations

claude plugin install download-gemini-images@daymade-skills

Download images (uploaded files or generated previews) from a Google Gemini conversation page using your logged-in Chrome session, then package them into an ordered ZIP.

When to use:

• Saving images from a Gemini chat/app page (uploaded or generated previews)
• Need the larger lightbox image, not the thumbnail
• Renaming downloaded images in order and producing a ZIP archive

Key features:

• Lightbox-first download via the Chrome plugin (uses your existing Google session)
• pageAssets fallback when lightbox automation fails
• Ordered ZIP packaging with integrity verification

wps-doc-scraper - Archive Public WPS/KDocs Documents

claude plugin install wps-doc-scraper@daymade-skills

Faithfully archive public WPS / KDocs / 金山文档 links — especially embedded ProcessOn mind maps and canvases — as raw source data, original SVG/PNG, and Markdown, without logging in.

When to use:

• Given a kdocs.cn or wps.processon.com link to scrape, save, download, or convert to Markdown
• Archiving an embedded ProcessOn mind map or canvas with source fidelity
• Need the raw payloads + original visual artifact, not just rendered text

Key features:

• Unauthenticated data-API-first extraction (no login, no account save)
• Original SVG/PNG capture for canvases and mind maps
• Markdown as a structured representation of the source

ashare-news-fetcher - A-Share Market News & Sentiment Aggregator

Install: claude plugin install daymade-financial@daymade-skills (suite-only — invoked as daymade-financial:ashare-news-fetcher)

Aggregate A-share (Chinese stock market) news, policy, and sentiment from public sources — 财联社, 华尔街见闻, 金十, 新浪 7x24, 东财快讯, regulator announcements (CSRC / PBoC / SSE), 东方财富股吧 — into structured JSON or Markdown.

When to use:

• Need recent news/policy/sentiment for a specific A-share stock or the whole market
• Aggregating 消息面 intel from multiple Chinese financial sources at once
• Producing a structured JSON or Markdown news digest

Key features:

• Multi-source public-feed aggregation (no login)
• Per-stock or market-wide filtering
• Structured JSON / Markdown output

local-codex - Local OpenAI Codex CLI Agent

Install: claude plugin install daymade-codex@daymade-skills (suite-only — invoked as daymade-codex:local-codex)

Delegate coding tasks to the local OpenAI Codex CLI agent using your ChatGPT Pro OAuth flat-rate subscription. Wraps codex exec / codex review for code generation, refactoring, and review without per-token API cha

{
  "name": "daymade-skills",
  "owner": {
    "name": "daymade",
    "email": "daymadev89@gmail.com"
  },
  "metadata": {
    "description": "Professional Claude Code and Codex skills marketplace — production-ready skills spanning GitHub and git operations (including current-base contributor PR review), document conversion and generation (Markdown, PDF, PPTX, DOCX), diagram and UI-design extraction, the full audio pipeline (ASR transcription, TTS, transcript correction, meeting minutes), financial and investment-research data, web scraping and content capture, security/PII tooling and secure repomix packaging, macOS and iOS development, CLI demo and terminal automation, evidence-backed HTML reports and data-visualization judgment, prompt and skill engineering, deep research and fact-checking, QA and LLM-evaluation infrastructure, internationalization, network/Tailscale and remote-desktop diagnostics, local inter-agent messaging, Claude Code operations, technology selection and build-vs-buy decisions, and model-aware Codex workstation setup. Suite plugins bundle related skills under shared namespaces, including the StepFun StepAudio 2.5 audio family. See the Available Skills list in the README for the authoritative per-skill breakdown.",
    "version": "3.21.0"
  },
  "plugins": [
    {
      "name": "bilibili-source",
      "description": "Fetches real, citable Bilibili (B站) video data — stats, metadata, tags, and full danmaku text — via login-free API calls, never hand-typed or estimated. Use when citing view/like/favorite counts, analyzing why a video performed, or archiving a Bilibili source into a knowledge base. Accepts BVID, av numbers, b23.tv links, or full URLs; subtitles and 收藏夹 (favorites) enumeration need the user's Bilibili login.",
      "source": "./bilibili-source",
      "strict": false,
      "version": "1.4.1",
      "category": "developer-tools",
      "keywords": [
        "bilibili",
        "b站",
        "bilibili-api",
        "video-stats",
        "danmaku",
        "view-count",
        "content-analysis",
        "web-data",
        "claude-code"
      ]
    },
    {
      "name": "kimi-use",
      "description": "Drives Kimi.app via computer-use for Work/Agent data-plugin queries and Chat 深度研究 reports, using the user's logged-in session; also the kimi-cu macOS desktop-automation playbook (channel reliability tiers, foregrounding, AX-tree recovery, form & dialog recipes) for driving any desktop app. Use for \"用 Kimi 查\" / \"操作 Kimi 客户端\" / \"Kimi 插件\" / \"Kimi 深度研究\" / kimi-cu desktop automation. Not for kimi.com browser automation or direct iFinD API access.",
      "source": "./kimi-use",
      "strict": false,
      "version": "1.8.0",
      "category": "developer-tools",
      "keywords": [
        "kimi",
        "kimi-app",
        "computer-use",
        "天眼查",
        "同花顺",
        "ifind",
        "data-source",
        "financial-data",
        "gui-automation"
      ]
    },
    {
      "name": "peer-message",
      "description": "Bridge local Claude Code and Codex sessions only when the current host's native communication tools do not cover the target. Use for cross-product messages, hooks/scripts posting to sessions, fallback reply lookup and delivery verification, or diagnosing Held peer messages. Also use its coordination guidance when shared-work ownership or an inbound peer assertion needs verification. For ordinary parent/subagent, teammate, or independent-session communication, first discover and use available native tools; do not load this skill merely to send a native message. The bundled network preview for cross-machine pairing is deprecated (existing deployments only; invitations use the peer-message:v1 format). Never bypass a denied or Held message with another transport. Not for spawning agents, moving full history, or granting user approval. Triggers: 跨产品通信、原生工具未覆盖的会话、脚本回帖、peer 送达排查、共享在制品归属核实、peer-message:v1 邀请（既有部署）。",
      "source": "./peer-message",
      "strict": false,
      "version": "1.21.1",
      "category": "communication",
      "keywords": [
        "agent-communication",
        "cross-session",
        "peer-message",
        "claude-code",
        "codex",
        "codex-queue",
        "uds",
        "multi-agent",
        "broadcast",
        "session-coordination",
        "crossSessionInbound",
        "inbound-assertions"
      ]
    },
    {
      "name": "cli-demo-generator",
      "description": "Generate professional animated CLI demos and terminal recordings with VHS. Supports automated generation, batch processing, and interactive recording for documentation and tutorials",
      "source": "./cli-demo-generator",
      "strict": false,
      "version": "1.1.0",
      "category": "developer-tools",
      "keywords": [
        "cli",
        "demo",
        "terminal",
        "vhs",
        "gif",
        "recording",
        "animation",
        "documentation"
      ]
    },
    {
      "name": "cloudflare-troubleshooting",
      "description": "Investigate and resolve Cloudflare configuration issues using API-driven evidence gathering. Use when troubleshooting ERR_TOO_MANY_REDIRECTS, SSL errors, DNS issues, or any Cloudflare-related problems. Focus on systematic investigation using Cloudflare API to examine actual configuration rather than making assumptions.",
      "source": "./cloudflare-troubleshooting",
      "strict": false,
      "version": "1.1.0",
      "category": "developer-tools",
      "keywords": [
        "cloudflare",
        "troubleshooting",
        "ssl",
        "dns",
        "api",
        "debugging",
        "devops"
      ]
    },
    {
      "name": "competitors-analysis",
      "description": "Discover, clone, update, and analyze competitor repositories with evidence-based competitive intelligence. Use when tracking competitors, reviewing competitor source code, adding a competitor repository, comparing product capabilities, building a competitor landscape, checking latest competitor code, or when the user says 竞品分析, competitor scan, analyze competitor, or compare with X. Repository-backed findings must come from local cloned code with file:line citations; market-landscape claims must cite their source and volatility.",
      "source": "./competitors-analysis",
      "strict": false,
      "version": "1.5.2",
      "category": "productivity",
      "keywords": [
        "competitors",
        "competitive-analysis",
        "competitor-tracking",
        "evidence-based",
        "market-research",
        "竞品分析",
        "code-analysis"
      ]
    },
    {
      "name": "daymade-claude-code",
      "description": "Claude Code operations suite that bundles cross-project prior-work retrieval across code, docs, Skills, meetings, WeChat archives, and conversation history; provider-separated Claude Code and Codex history readers; identity- and lineage-gated continuation workflows; plugin/skill troubleshooting; CLAUDE.md progressive disclosure optimization; version-synced Lark CLI routing; statusline configuration; exported .txt repair; full claude.ai conversation extraction with tool-call rendering and file download; plugin marketplace development and suite consolidation; writing/testing/debugging Claude Code hooks; multi-provider profile isolation; personal-memory migration into tool-agnostic AGENTS.md reference docs; one-shot local timers that ping Claude right after subscription quota reset to start a fresh 5-hour usage window; working web search installed on an agent whose relayed model backend cannot execute the built-in one; and terminal-output-to-PNG rendering for visual CLI verification under one shared namespace. Install once to get the full Claude Code power-user toolkit.",
      "source": "./daymade-claude-code",
      "strict": false,
      "version": "4.27.0",
      "category": "suite",
      "keywords": [
        "suite",
        "claude-code",
        "session-recovery",
        "conversation-history",
        "local-history",
        "prior-work",
        "retrieval",
        "reuse",
        "claude-md",
        "statusline",
        "troubleshooting",
        "marketplace-dev",
        "local-source-sync",
        "codex",
        "terminal-screenshot",
        "usage-analyst",
        "quota-ping",
        "web-conversation-export",
        "conversation-file-download",
        "memory-migration"
      ],
      "skills": [
        "./claude-code-ops-router",
        "./local-conversation-history",
        "./read-claude-code-history",
        "./read-codex-history",
        "./continue-claude-code-work",
        "./continue-codex-work",
        "./claude-skills-troubleshooting",
        "./claude-md-progressive-disclosurer",
        "./statusline-generator",
        "./claude-export-txt-better",
        "./marketplace-dev",
        "./terminal-screenshot",
        "./claude-usage-analyst",
        "./claude-switch-models-setup",
        "./read-claude-web-conversation",
        "./claude-migrate-memory-to-doc",
        "./claude-code-hooks",
        "./prior-work-retrieval",
        "./lark-cli-router",
        "./claude-code-ping-start-5h-quota",
        "./agent-web-search-setup",
        "./tech-selection"
      ]
    },
    {
      "name": "daymade-codex",
      "description": "OpenAI Codex operations and design exploration suite bundling model-aware long-context workstation setup, local Codex delegation, generated-image review, static visual-direction selection, and runnable HTML interaction Design Boards under one shared namespace.",
      "source": "./daymade-codex",
      "strict": false,
      "version": "1.4.1",
      "category": "suite",
      "keywords": [
        "suite",
        "codex",
        "openai",
        "context-window",
        "codex-desktop",
        "workstation-setup",
        "code-review",
        "image-gallery",
        "design",
        "visual-direction",
        "interaction-design",
        "html-prototype",
        "design-board"
      ],
      "skills": [
        "./codex-image-gallery",
        "./local-codex",
        "./design-style-picker",
        "./interaction-design-board",
        "./codex-1m-context-window-setup"
      ]
    },
    {
      "name": "daymade-docs",
      "description": "Routes docs: Word/PDF/PPTX/saved HTML→Markdown; MD/Word→PDF; create Word; PDF HTML/translate; Excel/xlsm/macOS; photo/signed scans; Mermaid; DOCX review; post-change docs. Reads one bundled Daymade specialist. New slide decks use deck-creator when installed; generic PDF reading/editing and spreadsheet analysis stay with their own Skills. Retired ppt-creator stays manual-only.",
      "source": "./daymade-docs",
      "strict": false,
      "version": "1.24.1",
      "category": "suite",
      "keywords": [
        "suite",
        "documentation",
        "markdown",
        "mermaid",
        "pdf",
        "pptx",
        "docx",
        "word",
        "excel",
        "xlsx",
        "xlsm",
        "meeting-minutes",
        "scan",
        "photo-to-pdf",
        "comments",
        "track-changes",
        "review"
      ],
      "skills": [
        "./docs-router",
        "./doc-to-markdown",
        "./mermaid-tools",
        "./pdf-creator",
        "./ppt-creator",
        "./docx-creator",
        "./docs-cleaner",
        "./pdf-to-html",
        "./photo-to-scanned-pdf",
        "./excel-automation",
        "./read-docx-review"
      ]
    },
    {
      "name": "daymade-financial",
      "description": "Financial data and investment-research suite covering the full China A-share and global equity data pipeline: Bigdata.com (RavenPack) structured financials and news sentiment, US equity fundamentals via yfinance, Gangtise (岗底斯) OpenAPI research suite installation and orchestration, A-share news and policy aggregation, A-share pharmaceutical sector daily reporting, structured devil's-advocate pressure-testing of investment theses, and adversarial due diligence on inflated benchmark claims with replicability mapping. Install once for the complete financial research workflow.",
      "source": "./daymade-financial",
      "strict": false,
      "version": "1.5.2",
      "category": "suite",
      "keywords": [
        "suite",
        "financial-data",
        "investment-research",
        "a-share",
        "bigdata",
        "ravenpack",
        "gangtise",
        "pharma",
        "news",
        "yfinance",
        "devils-advocate",
        "thesis-pressure-test",
        "benchmark",
        "due-diligence"
      ],
      "skills": [
        "./financial-router",
        "./bigdata-skill",
        "./financial-data-collector",
        "./gangtise-copilot",
        "./ashare-news-fetcher",
        "./daymade-sector-research",
        "./pharma-daily-report",
        "./devils-advocate",
        "./benchmark-due-diligence"
      ]
    },
    {
      "name": "daymade-macos",
      "description": "Apple-platform development and operations suite for macOS window capture, TCC permission diagnosis and Full Disk Access repair, iOS/macOS app development, disk cleanup, and launchd watchdogs.",
      "source": "./daymade-macos",
      "strict": false,
      "version": "1.22.4",
      "category": "suite",
      "keywords": [
        "suite",
        "macos",
        "ios",
        "xcodegen",
        "swiftui",
        "screenshot",
        "disk-space",
        "launchd",
        "watchdog"
      ],
      "skills": [
        "./capture-screen",
        "./developing-ios-apps",
        "./macos-cleaner",
        "./macos-permissions",
        "./macos-watchdog",
        "./macos-load-doctor"
      ]
    },
    {
      "name": "daymade-audio",
      "description": "Audio processing suite covering the full speech pipeline: ASR transcription (Qwen3, StepFun) with batch-mode guards against music-only repetition-loop hallucinations, speaker diarization and CAM++ voiceprint identification for multi-speaker recordings, transcript error correction, structured meeting minutes generation, and TTS voice synthesis (StepFun). Install once for the complete audio workflow.",
      "source": "./daymade-audio",
      "strict": false,
      "version": "1.46.2",
      "category": "suite",
      "keywords": [
        "suite",
        "audio",
        "asr",
        "tts",
        "transcription",
        "speech-to-text",
        "text-to-speech",
        "meeting-minutes",
        "voice"
      ],
      "skills": [
        "./audio-router",
        "./asr-transcribe-to-text",
        "./stepfun-asr",
        "./transcript-fixer",
        "./meeting-minutes-taker",
        "./stepfun-tts"
      ]
    },
    {
      "name": "daymade-skill",
      "description": "Daymade skills core suite. Bundles skill creation, quality review, real Claude/Codex Skill-surface governance, suite-migration reconciliation, and marketplace development tooling under one shared namespace. Skill governance separates canonical source, installed inventory, discovery policy, the fresh model-visible catalog, and router-resolved cold resources instead of optimizing cache counts; it preserves Claude's official versioned-cache lifecycle and verifies selected entries in the real host prompt. Skill verification separates risk classification from evaluation spend: bounded fixes use targeted checks, narrow behavior changes use sampled replays, and paired baselines, graders, benchmarks, or a viewer run only after explicit user authorization or a decision-bearing evidence plan plus opt-in; that authorization does not change the risk tier. Existing-skill edits retain an old-vs-new capability audit and content-bound packaging attestation so prompt compression cannot silently delete runtime contracts. When the official skill-creator plugin is also installed, skill-creator detects the coexistence and offers a consent-based, reversible SessionStart routing hook so the daymade edition wins deterministically; on machines without the official plugin nothing is ever installed.",
      "source": "./daymade-skill",
      "strict": false,
      "version": "1.67.6",
      "category": "suite",
      "keywords": [
        "suite",
        "skill-creation",
        "skill-review",
        "skill-governance",
        "marketplace-dev",
        "development",
        "tooling"
      ],
      "skills": [
        "./skill-creator",
        "./skill-reviewer",
        "./skills-search",
        "./skill-governance"
      ]
    },
    {
      "name": "deep-research",
      "description": "Generate evidence-tracked research reports with reusable source and claim records, original-source verification, and evidence-family tracking. Coordinate provider-specific Skills across selected modes, retain original artifacts, and synthesize by decision; select depth and routes by the question.",
      "source": "./deep-research",
      "strict": false,
      "version": "2.12.0",
      "category": "documentation",
      "keywords": [
        "research",
        "report",
        "analysis",
        "literature-review",
        "market-research",
        "citations",
        "evidence",
        "deepresearch",
        "enterprise",
        "company-research",
        "due-diligence"
      ]
    },
    {
      "name": "douban-skill",
      "description": "Export and sync Douban (豆瓣) book/movie/music/game collections to local CSV files via Frodo API. Supports full export (all history) and RSS incremental sync (recent items). Use when the user wants to export Douban reading/watching/listening/gaming history, back up their Douban data, set up incremental sync, or mentions 豆瓣/douban collections. Triggers on: 豆瓣, douban, 读书记录, 观影记录, 书影音, 导出豆瓣, export, backup, sync, collection.",
      "source": "./douban-skill",
      "strict": false,
      "version": "1.1.0",
      "category": "productivity",
      "keywords": [
        "douban",
        "豆瓣",
        "csv",
        "export",
        "backup",
        "rss",
        "frodo"
      ]
    },
    {
      "name": "fact-checker",
      "description": "Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements",
      "source": "./fact-checker",
      "strict": false,
      "version": "1.0.0",
      "category": "productivity",
      "keywords": [
        "fact-checking",
        "verification",
        "accuracy",
        "sources",
        "validation",
        "corrections",
        "web-search"
      ]
    },
    {
      "name": "feishu-doc-scraper",
      "description": "Extracts Feishu/Lark Docs, Wiki, Sheets, and Minutes (妙记) transcripts into faithful local Markdown via the lark-cli API — no LLM paraphrasing, browser-DOM fallback when lark-cli can't reach content. Use whenever the source is a Feishu/Lark URL and fidelity matters — 导出飞书文档/合集/妙记转写, 把飞书 wiki 转 markdown, or archiving a collection — even if the user just says \"save this\". Also covers owner-exported .docx → Markdown.",
      "source": "./feishu-doc-scraper",
      "strict": false,
      "version": "1.8.1",
      "category": "productivity",
      "keywords": [
        "feishu",
        "lark",
        "lark-cli",
        "markdown",
        "wiki",
        "minutes",
        "transcript",
        "collection",
        "api",
        "docx",
        "scraping",
        "browser",
        "archival",
        "comments",
        "replies",
        "feedback"
      ]
    },
    {
      "name": "github-contributor",
      "description": "Ships pull requests to open-source projects you don't maintain — CONTRIBUTING compliance, PR-size/scope checks, minimal-diff implementation, AI-disclosure PR descriptions, and rebase or bot-review replies. Use for 提 PR / 上游 PR / 贡献代码, \"open a PR\", \"fix this upstream\", \"rebase against main\", \"respond to the bot review\". Not for reviewing PRs as maintainer (use github-review-pr) or general GitHub CRUD (use github-ops).",
      "source": "./github-contributor",
      "strict": false,
      "version": "1.3.3",
      "category": "developer-tools",
      "keywords": [
        "github",
        "open-source",
        "contribution",
        "pull-request",
        "reputation",
        "contributor",
        "oss",
        "rebase",
        "conflict-resolution",
        "pr-description",
        "ai-assisted-disclosure",
        "bot-review"
      ]
    },
    {
      "name": "github-ops",
      "description": "Operates GitHub via gh CLI and REST/GraphQL — PRs, issues, Actions, repos, collaborators, org permissions, 2FA — with explicit target, authorization, and independent readback. Use when a write reports success but state didn't change, or choosing gh/REST/GraphQL/UI-only. Not for local Git recovery (use git-safety-net), maintainer PR review (use github-review-pr), or upstream contribution (use github-contributor).",
      "source": "./github-ops",
      "strict": false,
      "version": "1.14.7",
      "category": "developer-tools",
      "keywords": [
        "github",
        "gh-cli",
        "pull-request",
        "issues",
        "workflows",
        "organizations",
        "permissions",
        "2fa",
        "api"
      ]
    },
    {
      "name": "github-review-pr",
      "description": "Reviews PRs against the live base with immutable objects and three-way merges. Use for PR review/merge readiness, main changed, closed-PR reconsideration, open-PR sweeps, review-led repair, or explicitly requested independent review of your own contribution. Not for GitHub CRUD (use github-ops), authoring/maintaining your PR (use github-contributor), or merging without fresh review.",
      "source": "./github-review-pr",
      "strict": false,
      "version": "1.4.4",
      "category": "developer-tools",
      "keywords": [
        "github",
        "pull-request",
        "code-review",
        "maintainer",
        "base-drift",
        "merge-readiness",
        "three-way-merge",
        "contributor",
        "open-pr-sweep",
        "curation"
      ]
    },
    {
      "name": "git-safety-net",
      "description": "Audits, preserves and recovers local Git state before cleanup: unpushed or wrong-branch commits, dirty worktrees, duplicate clones, stashes, dangling commits, squash-merge uncertainty. Use when the user fears lost work, wants to recover a commit, asks if a branch is actually merged, asks whether a branch, worktree or clone is safe to delete, or wants one clean main (误删分支 / 还有没有丢的东西). Not for GitHub PR operations.",
      "source": "./git-safety-net",
      "strict": false,
      "version": "1.22.5",
      "category": "developer-tools",
      "keywords": [
        "git",
        "reflog",
        "dangling-commits",
        "lost-commits",
        "branch-recovery",
        "merge-verification",
        "squash-merge",
        "disaster-recovery",
        "worktree",
        "claude-code",
        "clone-discovery",
        "untracked-backup",
        "stale-remote-cache",
        "checkout-alignment"
      ]
    },
    {
      "name": "i18n-expert",
      "description": "Complete internationalization/localization setup and auditing for UI codebases. Configure i18n frameworks, replace hard-coded strings with translation keys, ensure locale parity between en-US and zh-CN, and validate pluralization and formatting. Use when setting up i18n for React/Next.js/Vue apps, auditing existing implementations, replacing hard-coded strings, ensuring proper error code mapping, or validating pluralization and date/time/number formatting across locales",
      "source": "./i18n-expert",
      "strict": false,
      "version": "1.0.0",
      "category": "developer-tools",
      "keywords": [
        "i18n",
        "internationalization",
        "localization",
        "translation",
        "react-i18next",
        "next-intl",
        "vue-i18n",
        "locale",
        "multilingual",
        "globalization"
      ]
    },
    {
      "name": "ima-copilot",
      "description": "One-stop companion and installer for the official Tencent IMA skill (ima.qq.com). Installs upstream ima-skill to Claude Code/Codex/OpenClaw via npx skills add, guides API key setup, detects and fixes known issues (including the missing-YAML-frontmatter bug in submodule SKILL.md files) with user consent, and implements a personalized fan-out search strategy with priority-based knowledge base boosting and silent truncation detection",
      "source": "./ima-copilot",
      "strict": false,
      "version": "1.2.1",
      "category": "developer-tools",
      "keywords": [
        "ima",
        "tencent-ima",
        "knowledge-base",
        "note-search",
        "fan-out-search",
        "installer",
        "wrapper",
        "upstream-fix",
        "claude-code",
        "codex",
        "openclaw"
      ]
    },
    {
      "name": "llm-eval-harness",
      "description": "Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression. Use before hand-rolling a curl loop, when onboarding a provider, or debugging \"system prompt 不生效\" / a tok/s claim — 测评/压测一个模型或渠道. Not for TTS/voice-clone supplier eval (use the audio skill).",
      "source": "./llm-eval-harness",
      "strict": false,
      "version": "1.5.0",
      "category": "developer-tools",
      "keywords": [
        "llm",
        "eval",
        "benchmark",
        "model-comparison",
        "speed-test",
        "concurrency",
        "protocol-compliance",
        "tokens-per-second",
        "ttft",
        "thinking-aware",
        "availability",
        "fidelity",
        "system-prompt",
        "gateway-testing",
        "vendor-bug-report"
      ]
    },
    {
      "name": "llm-icon-finder",
      "description": "Find and access AI/LLM model brand icons from lobe-icons library in SVG/PNG/WEBP formats",
      "source": "./llm-icon-finder",
      "strict": false,
      "version": "1.0.0",
      "category": "assets",
      "keywords": [
        "icons",
        "ai-models",
        "llm",
        "branding",
        "lobe-icons"
      ]
    },
    {
      "name": "product-analysis",
      "description": "Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code + Codex CLI) for multi-perspective exploration, then synthesizes findings into actionable optimization plans. Supports self-audit, UX audit, API audit, architecture review, and competitive benchmarking via competitors-analysis skill",
      "source": "./product-analysis",
      "strict": false,
      "version": "1.0.2",
      "category": "productivity",
      "keywords": [
        "product-analysis",
        "self-review",
        "ux-audit",
        "parallel-agents",
        "cross-model",
        "test-time-compute",
        "codex",
        "synthesis",
        "product-audit",
        "information-architecture"
      ]
    },
    {
      "name": "prompt-optimizer",
      "description": "Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology. Use when users provide loose requirements, ambiguous feature descriptions, need to enhance prompts for AI-generated code/products/documents, request prompt optimization, or want to improve requirements engineering. Applies domain theories (GTD, BJ Fogg, Gestalt, AIDA, Zero Trust) and structured Role/Skills/Workflows/Examples/Formats framework",
      "source": "./prompt-optimizer",
      "strict": false,
      "version": "1.2.0",
      "category": "productivity",
      "keywords": [
        "prompt-engineering",
        "ears",
        "requirements",
        "specifications",
        "optimization",
        "domain-theory",
        "prompt-enhancement",
        "ai-prompting"
      ]
    },
    {
      "name": "promptfoo-evaluation",
      "description": "Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like promptfoo, eval, LLM evaluation, prompt testing, or model comparison",
      "source": "./promptfoo-evaluation",
      "strict": false,
      "version": "1.1.0",
      "category": "developer-tools",
      "keywords": [
        "promptfoo",
        "evaluation",
        "llm-testing",
        "prompt-testing",
        "assertions",
        "llm-rubric",
        "few-shot",
        "model-comparison"
      ]
    },
    {
      "name": "qa-expert",
      "description": "Comprehensive QA testing infrastructure with autonomous LLM execution, Google Testing Standards (AAA pattern), and OWASP security testing. Use when establishing QA processes, writing test cases, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, enforcing quality gates, or preparing third-party QA handoffs. Enables 100x faster test execution via master prompts",
      "source": "./qa-expert",
      "strict": false,
      "version": "1.1.0",
      "category": "developer-tools",
      "keywords": [
        "qa",
        "testing",
        "test-cases",
        "bug-tracking",
        "google-standards",
        "owasp",
        "security",
        "automation",
        "quality-gates",
        "metrics"
      ]
    },
    {
      "name": "repomix-safe-mixer",
      "description": "Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing. Use when packaging code for distribution, creating reference packages, or when the user mentions security concerns about sharing code with repomix",
      "source": "./repomix-safe-mixer",
      "strict": false,
      "version": "1.0.2",
      "category": "security",
      "keywords": [
        "repomix",
        "security",
        "credentials",
        "secrets-scanning",
        "safe-packaging",
        "secret-detection",
        "code-security"
      ]
    },
    {
      "name": "repomix-unmixer",
      "description": "Extract files from repomix packaged formats (XML, Markdown, JSON) with automatic format detection and validation",
      "source": "./repomix-unmixer",
      "strict": false,
      "version": "1.0.0",
      "category": "utilities",
      "keywords": [
        "repomix",
        "unmix",
        "extract",
        "xml",
        "conversion"
      ]
    },
    {
      "name": "scrapling-skill",
      "description": "Install, troubleshoot, and use Scrapling CLI for extracting HTML, Markdown, or text from webpages. Diagnoses missing extras, Playwright browser runtime issues, TLS verification failures, and WeChat public article extraction patterns. Use when users mention Scrapling, `scrapling extract`, `uv tool install scrapling`, or need to decide between static and browser-backed fetching",
      "source": "./scrapling-skill",
      "strict": false,
      "version": "1.0.0",
      "category": "developer-tools",
      "keywords": [
        "scrapling",
        "web-scraping",
        "html",
        "markdown",
        "playwright",
        "wechat",
        "extraction",
        "cli"
      ]
    },
    {
      "name": "slides-creator",
      "description": "【DEPRECATED · 已废弃】叙事优先的幻灯片创建方法论已于 2026-08-07 并入 deck-creator（作者私有仓 Route A）。本条目仅为退役通告保留，请勿调用。",
      "source": "./slides-creator",
      "strict": false,
      "version": "2.1.0",
      "category": "content-creation",
      "keywords": [
        "slides",
        "presentation",
        "ppt",
        "deck",
        "narrative",
        "storytelling",
        "ABCDEFG"
      ]
    },
    {
      "name": "teams-channel-post-writer",
      "description": "Create professional Microsoft Teams channel posts with Adaptive Cards, formatted announcements, and corporate communication standards",
      "source": "./teams-channel-post-writer",
      "strict": false,
      "version": "1.1.0",
      "category": "communication",
      "keywords": [
        "teams",
        "microsoft",
        "adaptive-cards",
        "communication",
        "announcements"
      ]
    },
    {
      "name": "terraform-skill",
      "description": "Diagnoses and designs safe Terraform releases, provisioners (remote-exec/local-exec/file, cloud-init, Compose, Caddy), multi-environment isolation, and fresh-host bootstrap. Use when writing or reviewing plan/apply wrappers or provisioners; when staging/production config may differ; when a rollout can mutate a shared gateway; or debugging drift, TLS, container restarts, DNS duplication, or snapshot contamination.",
      "source": "./terraform-skill",
      "strict": false,
      "version": "1.5.6",
      "category": "developer-tools",
      "keywords": [
        "terraform",
        "iac",
        "provisioner",
        "devops",
        "infrastructure",
        "cloud-init",
        "cloudflare",
        "release-safety"
      ]
    },
    {
      "name": "tunnel-doctor",
      "description": "MUST be used first for tunnel / proxy-path connectivity failures or slow throughput (网络故障 / 连不上 / 代理或隧道下超时). Diagnoses Tailscale, proxy, TUN, DNS and SSH-tunnel problems on macOS and Windows/WSL, e.g. Tailscale ping works but SSH fails, curl works but browser gets 503, Git/Docker fails behind the proxy, or downloads crawl despite a reachable proxy. Not for application-layer bugs (use debugging-network-issues).",
      "source": "./tunnel-doctor",
      "strict": false,
      "version": "1.17.1",
      "category": "developer-tools",
      "keywords": [
        "tailscale",
        "vpn",
        "shadowrocket",
        "clash",
        "surge",
        "route-conflict",
        "wsl",
        "ssh",
        "ssh-tunnel",
        "autossh",
        "proxy",
        "proxycommand",
        "git-push",
        "networking",
        "macos",
        "makefile",
        "remote-development",
        "local-domain"
      ]
    },
    {
      "name": "twitter-reader",
      "description": "Fetch Twitter/X post content including long-form Articles with full images and metadata. Use when Claude needs to retrieve tweet/article content, author info, engagement metrics (likes, retweets, bookmarks), and embedded media. Supports individual posts and X Articles (long-form content). Automatically downloads all images to local attachments folder and generates complete Markdown with proper image references. Preferred over Jina for X Articles with images.",
      "source": "./twitter-reader",
      "strict": false,
      "version": "1.4.0",
      "category": "utilities",
      "keywords": [
        "twitter",
        "x",
        "social-media",
        "jina",
        "content-fetching",
        "api",
        "scraping",
        "threads",
        "images",
        "attachments",
        "markdown"
      ]
    },
    {
      "name": "ui-designer",
      "description": "Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs",
      "source": "./ui-designer",
      "strict": false,
      "version": "1.0.0",
      "category": "design",
      "keywords": [
        "ui",
        "design-system",
        "mockup",
        "screenshot",
        "design-extraction",
        "mvp"
      ]
    },
    {
      "name": "video-comparer",
      "description": "Compare two videos and generate interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Use when analyzing compression results, evaluating codec performance, or assessing video quality differences",
      "source": "./video-comparer",
      "strict": false,
      "version": "1.0.0",
      "category": "media",
      "keywords": [
        "video",
        "comparison",
        "quality-analysis",
        "psnr",
        "ssim",
        "compression",
        "ffmpeg",
        "codec"
      ]
    },
    {
      "name": "windows-remote-desktop-connection-doctor",
      "description": "Diagnoses Windows App (Remote Desktop / AVD / W365 / direct PC) connection problems on macOS: transport selection (UDP Shortpath vs WebSocket), VPN/proxy interference, and stuck \"Configuring remote PC...\" dialogs. Use when a VDI connection is slow/stuck, transport shows WebSocket not UDP, or Windows App freezes at a progress dialog. Not for general network diagnosis (use debugging-network-issues or tunnel-doctor).",
      "source": "./windows-remote-desktop-connection-doctor",
      "strict": false,
      "version": "1.2.0",
      "category": "developer-tools",
      "keywords": [
        "rdp",
        "avd",
        "wvd",
        "w365",
        "windows-app",
        "remote-desktop",
        "shortpath",
        "udp",
        "websocket",
        "stun",
        "turn",
        "vpn",
        "macos",
        "networking"
      ]
    },
    {
      "name": "youtube-downloader",
      "description": "Download YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use when users request downloading videos, extracting audio, handling protected streams with authentication headers, or troubleshooting download issues like nsig extraction failures, 403 errors, or cookie extraction problems",
      "source": "./youtube-downloader",
      "strict": false,
      "version": "1.1.1",
      "category": "utilities",
      "keywords": [
        "youtube",
        "yt-dlp",
        "video-download",
        "audio-extraction",
        "mp3",
        "download",
        "hls",
        "m3u8",
        "ffmpeg",
        "streaming",
        "mux",
        "vimeo"
      ]
    },
    {
      "name": "debugging-network-issues",
      "description": "Investigates network, streaming and protocol failures with falsification-first layered experiments, the general fallback for unknown root causes. Use for ECONNRESET / RST_STREAM / SSE stalls, CDN/CGNAT timeouts or certificate errors, throughput collapse where everything returns 200 but transfers crawl, or LAN identity/topology mysteries. Not for known Tailscale/TUN/DNS/proxy-path conflicts (use tunnel-doctor).",
      "source": "./debugging-network-issues",
      "strict": false,
      "version": "1.11.1",
      "category": "developer-tools",
      "keywords": [
        "debugging",
        "network",
        "sse",
        "http2",
        "rst",
        "econnreset",
        "cloudflare",
        "streaming",
        "troubleshooting",
        "methodology",
        "proxy",
        "tun",
        "vpn",
        "cname",
        "dns",
        "lan",
        "mdns",
        "throughput",
        "bandwidth",
        "performance"
      ]
    },
    {
      "name": "auto-repo-setup",
      "description": "Evidence-driven repository setup, repair, handoff, and safe Git workflow for Claude Code or Codex. Detects the actual stack from project instructions and manifests instead of assuming Python, ffmpeg, uv, or .env; preserves local work during sync/conflict handling; diagnoses repeated SessionStart output before editing config; and defaults routine startup behavior to AGENTS.md/CLAUDE.md or a normal Agent request. Lifecycle hooks are an explicit pre-prompt exception with guarded, idempotent Claude Code setup and runtime-specific Codex verification.",
      "source": "./auto-repo-setup",
      "strict": false,
      "version": "2.1.6",
      "category": "developer-tools",
      "keywords": [
        "repo-setup",
        "environment",
        "onboarding",
        "git",
        "configuration",
        "claude-code",
        "project-instructions",
        "session-start-diagnosis",
        "pii-guard",
        "codex",
        "git-sync"
      ]
    },
    {
      "name": "llm-wiki-setup",
      "description": "Co-creates a personal investment-research LLM Wiki (Karpathy's pattern) by interviewing the user for THEIR OWN analysis framework, not a template — a living CLAUDE.md of pure markdown + wikilinks, no RAG in place of compilation. Use to build a compounding 投研第二大脑 / 投研知识库 / 个人投研 wiki, ingest research reports / earnings calls into an existing wiki, or run post-earnings prediction→fulfillment reviews.",
      "source": "./llm-wiki-setup",
      "strict": false,
      "version": "1.2.0",
      "category": "documentation",
      "keywords": [
        "llm-wiki",
        "karpathy",
        "investment-research",
        "投研第二大脑",
        "knowledge-base",
        "markdown-wiki",
        "compounding-notes",
        "analyst-tracking",
        "second-brain",
        "投研知识库"
      ]
    },
    {
      "name": "marketplace-health-check",
      "description": "Run a full 6-dimension health check of this Claude Code skills marketplace repo — code/script safety, documentation/SSOT consistency, security/PII leaks, open-PR triage, open-issue triage, and marketplace-manifest integrity — via a parallel fan-out Dynamic Workflow, then verify the serious findings and report by priority. Use this whenever the user asks to check the repo, run a health check, do a full sweep/audit before a release, 全面体检, 检查仓库状态, 看看仓库健康吗, 审计一下仓库, or asks whether the PRs / issues / docs / versions / PII are in good shape across the board — even if they never say workflow. Reach for it for any broad is-this-whole-repo-OK request, not just one-file checks.",
      "source": "./marketplace-health-check",
      "strict": false,
      "version": "1.1.0",
      "category": "developer-tools",
      "keywords": [
        "health-check",
        "audit",
        "marketplace",
        "workflow",
        "pii",
        "code-review",
        "repo-audit"
      ]
    },
    {
      "name": "setup-notifications-via-wecom",
      "description": "Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks. Use this skill whenever the user needs to send notifications, alerts, backup completion reports, or status updates via WeCom; when they mention 企业微信, 企微机器人, webhook, or alerting; or when a message needs to be clear, unambiguous, and technically precise rather than vague or condescending.",
      "source": "./setup-notifications-via-wecom",
      "strict": false,
      "version": "1.3.0",
      "category": "developer-tools",
      "keywords": [
        "wecom",
        "enterprise-wechat",
        "notifications",
        "webhook",
        "alerts",
        "企业微信",
        "企微机器人",
        "status-updates",
        "claude-code"
      ]
    },
    {
      "name": "notify-wecom",
      "description": "Send a single one-off message to a WeCom (Enterprise WeChat) group bot. Use this skill whenever the user says \"/notify-wecom\", \"send a quick WeCom message\", \"企微通知一下\", \"临时发一条企业微信\", or any one-shot notification that does not need a reusable template or setup workflow.",
      "source": "./notify-wecom",
      "strict": false,
      "version": "1.1.1",
      "category": "developer-tools",
      "keywords": [
        "wecom",
        "enterprise-wechat",
        "notify",
        "one-shot",
        "企业微信",
        "企微机器人",
        "claude-code"
      ]
    },
    {
      "name": "github-sensitive-data-cleanup",
      "description": "Scan and remove sensitive data (secrets, API keys, private domains/IPs, PII) from GitHub repository history. Use this skill whenever the user says scan sensitive data, clean git history, remove secrets from repo, sanitize GitHub history, 清理敏感数据, 历史重写, force push, 泄露, or needs to repair a public repo after accidental secret/private context leakage. Also use before any force push to a public repository to verify visibility, backup, and scan results.",
      "source": "./github-sensitive-data-cleanup",
      "strict": false,
      "version": "2.1.0",
      "category": "security",
      "keywords": [
        "github",
        "sensitive-data",
        "secrets",
        "history-rewrite",
        "git-filter-repo",
        "gitleaks",
        "pii",
        "force-push",
        "cleanup",
        "claude-code"
      ]
    },
    {
      "name": "frontend-visual-qa",
      "description": "Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI implementation to find typography, overflow, responsive, routing, data-viz, browser-output, or native-shell defects, or to compare a render against a reference. Not for greenfield UI design (use ui-designer) or QA-program setup (use qa-expert).",
      "source": "./frontend-visual-qa",
      "strict": false,
      "version": "1.20.7",
      "category": "design",
      "keywords": [
        "frontend",
        "visual-qa",
        "layout",
        "line-breaks",
        "responsive",
        "chrome",
        "playwright",
        "ai-slop",
        "design-review",
        "Markdown",
        "Obsidian",
        "image-sizing"
      ]
    },
    {
      "name": "openclaw",
      "description": "Manage OpenClaw (龙虾 / lobster) instance configurations, gateway health, and plugin lifecycle — audit, diff, copy, add-model, list, and switch models across openclaw.json files; diagnose a parked or down gateway, plugin register failures, and hooks blocked after an upgrade; confirm whether an install is out of date. Use when juggling multiple OpenClaw / Claude Code wrapper instances, applying DeepSeek model patches, managing default models and aliases, or validating config.",
      "source": "./openclaw",
      "strict": false,
      "version": "1.3.0",
      "category": "claude-code",
      "keywords": [
        "openclaw",
        "lobster",
        "config",
        "model-management",
        "deepseek",
        "claude-code",
        "config-validation"
      ]
    },
    {
      "name": "download-gemini-images",
      "description": "Download, export, save, or package images from a Google Gemini conversation page — uploaded images or generated image previews. Use when the task needs logged-in Chrome/Gemini state, opening Gemini image lightboxes, downloading the larger displayed files, renaming them in order, and producing a ZIP archive.",
      "source": "./download-gemini-images",
      "strict": false,
      "version": "1.0.0",
      "category": "media",
      "keywords": [
        "gemini",
        "images",
        "download",
        "chrome",
        "lightbox",
        "zip",
        "export"
      ]
    },
    {
      "name": "gemini-history-analyzer",
      "description": "Analyze Google Takeout exports of Gemini conversation history — extract, categorize, and mine transcripts and attachments for insights, then optionally distill them into a personal knowledge base. Use when the user mentions Gemini Takeout, Gemini export, Gemini history, analyzing Gemini conversation data, or drags a takeout zip into the project.",
      "source": "./gemini-history-analyzer",
      "strict": false,
      "version": "1.0.1",
      "category": "productivity",
      "keywords": [
        "gemini",
        "takeout",
        "history",
        "analysis",
        "conversation",
        "export",
        "transcript",
        "knowledge-base"
      ]
    },
    {
      "name": "wps-doc-scraper",
      "description": "Faithfully archive public WPS / KDocs / 金山文档 links — especially embedded ProcessOn .pof mind maps and canvases — as raw source data, original SVG/PNG, and Markdown. Use when a user gives a kdocs.cn or wps.processon.com link and asks to scrape, save, download, 扒下来, 归档, or 转 Markdown without logging in.",
      "source": "./wps-doc-scraper",
      "strict": false,
      "version": "1.0.0",
      "category": "productivity",
      "keywords": [
        "wps",
        "kdocs",
        "processon",
        "mindmap",
        "scraper",
        "markdown",
        "archive"
      ]
    },
    {
      "name": "openclaw-model-switch",
      "description": "Switch or repair the model configuration of an OpenClaw instance (e.g., Kimi k2p6 → k3): change the default model, add model definitions, and fix model-config failures — 401 \"Invalid token\", \"No available channel / model not found\", thinking-level rejections, and config edits that don't take effect. Ships a config-discovering switch script with backup + mirror sync, an endpoint probe protocol, and a field-tested trap catalog (env-var key hijack, provider-plugin thinking restrictions, relay availability).",
      "source": "./openclaw-model-switch",
      "strict": false,
      "version": "1.2.0",
      "category": "claude-code",
      "keywords": [
        "claude-code",
        "config",
        "deepseek",
        "gateway",
        "k2.7",
        "k3",
        "kimi",
        "lobster",
        "model-management",
        "model-repair",
        "model-switch",
        "openclaw",
        "relay",
        "thinking-levels"
      ]
    },
    {
      "name": "tibo-reset-codex",
      "description": "查询 ChatGPT/Codex 重置公告及多个 Pro 账号的剩余额度、备用 Full reset；复用 Google 登录逐个核实并恢复网页账号，换算北京时间。区分 Tibo 官宣、未官宣的平台静默重置、banked reset 与账户级周期重置。Use when 用户问「什么时候重置」「额度什么时候恢复」「下次全员重置几点」 「banked reset 到了吗」「Tibo 说了什么」「usage limit when reset」，或说「额度突然回到 100%」「好像/肯定又重置了」，或问「几个账号都用完了吗」「哪个还满额」。必须用实时产品状态、独立用户实测与公告交叉核验；禁止因 Tibo Radar 没有新条目就否定已经发生的重置，并须把太平洋时间当场换算为北京时间。",
      "source": "./tibo-reset-codex",
      "strict": false,
      "version": "1.22.1",
      "category": "utilities",
      "keywords": [
        "chatgpt",
        "codex",
        "openai",
        "usage-limit",
        "reset",
        "tibo",
        "quota",
        "额度重置",
        "timezone"
      ]
    },
    {
      "name": "excalidraw-use",
      "description": "Places existing images onto an Excalidraw whiteboard, turns a slide deck into clean per-slide images, and inspects a .excalidraw file. Use whenever someone mentions Excalidraw, a whiteboard/canvas, .excalidraw, 白板 or 画板 — e.g. \"put these screenshots on my board\" — or a workshop delivered by hand-drawing over screenshots on a shared canvas. Not for generating a diagram from a text description.",
      "source": "./excalidraw-use",
      "strict": false,
      "version": "1.1.0",
      "category": "developer-tools",
      "keywords": [
        "excalidraw",
        "whiteboard",
        "canvas",
        "screenshot",
        "slide-deck",
        "image-layout",
        "puppeteer",
        "白板"
      ]
    },
    {
      "name": "meme-creator",
      "description": "Creates video/GIF memes by overlaying images (logos, avatars, stickers) onto moving objects in a clip with frame-accurate tracking, then exports MP4 + GIF. Use whenever the user wants a meme, 梗图, 表情包, or reaction GIF from footage; to cover faces in a video; or asks to 把 logo/头像贴到视频里跟着动. Not for transcript-driven editing, programmatic scene generation, or subtitle work.",
      "source": "./meme-creator",
      "strict": false,
      "version": "1.1.1",
      "category": "media",
      "keywords": [
        "meme",
        "梗图",
        "表情包",
        "gif",
        "video-overlay",
        "object-tracking",
        "csrt",
        "sticker",
        "avatar",
        "logo"
      ]
    },
    {
      "name": "data-visualization-discipline",
      "description": "数据可视化的判断层 SSOT——画任何图表、dashboard、看板之前先加载它，不是画完之后。管\"该不该这么画\"：这张图想让读者得出什么结论、用均值还是中位数、能不能聚合、堆叠还是折线、能不能上双轴、配色与颜色数量、同一实体跨图是否同色同位、表格该留几列。介质无关：HTML 报告页、React/Vue dashboard、PPT 原生图表、matplotlib/plotly/ECharts/D3、渲染成 PNG 的图，一律适用。Use when 动手画图之前，或评审既有图表（\"这几张图有什么问题\"、\"图例为什么不一致\"）。Not for 报告页的排版/组件/交互（用 report-with-html:report-with-html）或 PPT 原生图表的实现与渲染陷阱（用 deck-creator:deck-creator）。",
      "source": "./data-visualization-discipline",
      "strict": false,
      "version": "1.1.2",
      "category": "documentation",
      "keywords": [
        "数据可视化",
        "图表",
        "chart",
        "dashboard",
        "看板",
        "可视化纪律",
        "图型选择",
        "统计量",
        "中位数",
        "堆叠图",
        "双轴",
        "配色",
        "图例",
        "Cleveland",
        "Tufte",
        "Bertin",
        "data visualization",
        "chart critique",
        "图表评审"
      ]
    },
    {
      "name": "report-with-html",
      "description": "Produces the reader-facing HTML artifact — report, dashboard, architecture view, data browser, or review workbench — evidence-backed, browser-verified. Use when the deliverable IS a visual HTML report, or the user asks for an HTML/web presentation. Load data-visualization-discipline for chart judgment. Not for chat status or Markdown prose unless asked to become a report; not for PowerPoint (deck-creator Route C).",
      "source": "./report-with-html",
      "strict": false,
      "version": "1.4.1",
      "category": "documentation",
      "keywords": [
        "HTML报告",
        "可视化报告",
        "一页纸",
        "数据报告",
        "半年报",
        "系统可视化",
        "差距地图",
        "架构可视化",
        "用户旅程",
        "决策看板",
        "事故时间线",
        "对比看板",
        "dashboard",
        "html",
        "html one-pager",
        "数据浏览器",
        "归档浏览器",
        "审核工作台",
        "review workbench"
      ]
    },
    {
      "name": "ghostty-use",
      "description": "Snapshots, restores and reconciles Claude Code / Codex sessions inside Ghostty tabs across reboots. Use when quitting the Mac for an update (保存终端会话 / 重启前备份终端), after restart to reopen tabs with their original session IDs (恢复之前的窗口 / restore my ghostty tabs), or to audit which sessions survived. Not for resuming one conversation via its own --resume, terminal screenshots, or tmux state. Also use for periodic change-only snapshots (定期增量快照 / 没变化不记录). Also use before or after a manual Codex account switch (额度耗尽换号 / 换号后恢复全部 Codex).",
      "source": "./ghostty-use",
      "strict": false,
      "version": "1.6.1",
      "category": "developer-tools",
      "keywords": [
        "ghostty",
        "terminal",
        "session-restore",
        "reboot",
        "snapshot",
        "claude-code",
        "codex",
        "终端会话",
        "会话恢复",
        "重启恢复"
      ]
    }
  ]
}