ClaudeCodeMod

All shelves / Marketplaces

AsiaOstrich/universal-dev-standards

AsiaOstrich/universal-dev-standards · 1 plugin

Marketplace Universal, language-agnostic development standards for software projects. Includes coding standards, git workflows, testing guidelines, documentation structure, and AI collaboration rules.

Install

The repo has no one-line install. Follow its README.

Open the repo

Plugins 1

After adding the marketplace, install one with /plugin install <name>@asia-ostrich.

  1. 1universal-dev-standardsSkills for development standards: commit messages, code review, testing, documentation, git workflow, release management, and more. Language-agnostic and framework-agnostic./plugin install universal-dev-standards@asia-ostrichv6.13.1

Files

README.md

Universal Development Standards



Language: English | 繁體中文 | 简体中文

Version: 6.14.0-beta.8 (Pre-release) | Released: 2026-10-07 | License: Dual License (CC BY 4.0 + MIT)

Language-agnostic, framework-agnostic development standards for software projects. Ensure consistency, quality, and maintainability across diverse technology stacks with AI-native workflows.


🚀 Quick Start

Install via npm (Recommended)

# Install globally (stable)
npm install -g universal-dev-standards

# Initialize your project
uds init

Looking for beta or RC versions? See Pre-release Versions.

Or use npx (No installation required)

npx universal-dev-standards init

Note: Copying standards alone won't enable AI assistance. Use uds init to automatically configure your AI tool or manually reference standards in your tool's configuration file.

🗺️ What's Next?

I want to... Command
Understand an existing codebase /discover
Build a new feature with specs /sdd
Work with legacy code /reverse
Choose a development methodology /methodology
Make a clean commit /commit

Tip: Type /dev-workflow for a complete guide to all development phases and available commands.

See also: Daily Workflow Guide

📚 Documentation

I want to... Document
New to UDS? Set up in 5 minutes docs/user/GETTING-STARTED.md
Browse all 55 skills by Tier & Category docs/user/SKILLS-INDEX.md
See all slash commands docs/user/COMMANDS-INDEX.md
Quick reference card docs/user/CHEATSHEET.md
Common questions docs/user/FAQ.md
Troubleshoot problems docs/user/TROUBLESHOOTING.md
Understand UDS terminology docs/user/GLOSSARY.md

✨ Features

Category Count Description
Core Standards 153 Universal development guidelines
AI Skills 56 Interactive skills
Slash Commands 51 Quick actions
CLI Commands 24 Project setup & maintenance

What's New in 5.0? See Pre-release Notes for details on new features.


🏗️ Architecture

UDS content is organised along two independent axes. They answer different questions, and
conflating them is the most common way to misread the layout — so they are stated separately.

Axis 1 — Depth: how much must always be loaded

This axis is a behavioural contract: it tells an AI agent what to read up front and what to
leave until asked. It is the axis that matters for context cost.

graph TD
    A[AI Agent / Developer] --> R["<b>Rules</b><br/>core/*.md<br/><b>Always Read</b>"]
    R -- "needs explanation or a worked example" --> G["<b>Guides</b><br/>core/guides/*.md<br/>Read on Demand Only"]
    R -- "needs a full methodology (TDD, BDD, …)" --> M["<b>Methodologies</b><br/>methodologies/guides/*.md<br/>Read on Demand Only"]
Loading
Layer Location Contains AI behaviour
Rules core/*.md Actionable rules, checklists, thresholds Always Read
Guides core/guides/*.md Explanations, tutorials, examples Read on Demand Only
Methodologies methodologies/guides/*.md Full methodology guides Read on Demand Only

Axis 2 — Format: how the same standard is encoded

This axis carries no depth claim. A standard's .ai.yaml and .md forms are two encodings
of the same material, chosen by who is reading.

Aspect ai/standards/*.ai.yaml core/*.md
Encoding Structured YAML Prose Markdown
Best for Deterministic machine lookup Human reading and review
Relative size ~69% of the Markdown form — a reformat, not a compaction tier† baseline

† Measured 2026-07-23 across the 135 standards that have both forms: 872,380 bytes of
YAML against 1,271,471 bytes of Markdown. Reproduce with the commands in
Content Architecture §7.

📐 The depth contract, where it is enforced across integrations, and the measured gap between
the contract and the current tree are documented in
docs/reference/CONTENT-ARCHITECTURE.md.


🤖 AI Tool Support

UDS ships integrations for 11 live tools. 1 of them is behaviourally verified.

Those are two different numbers on purpose. Status says how complete the integration
we wrote is. Verified says whether anyone has confirmed the tool actually reads it and
behaves accordingly — by running probes and recording the output. Until today the second
question had never been asked, so no answer to it can be assumed. See
XSPEC-357 for the probe design and the
verification queue (Antigravity → Codex → Claude Code → the rest).

AI Tool Status Verified Skills Slash Commands Configuration
Claude Code ✅ Complete 🔬 —◆ 55 51 CLAUDE.md
OpenCode ✅ Complete 🔬 — 55 51 AGENTS.md
Cursor ✅ Complete 🔬 — Core Simulated .cursorrules
Roo Code ✅ Complete 🔬 — Core Workflow .roo/rules/
Cline 🔶 Partial 🔬 — Core Workflow .clinerules
Windsurf 🔶 Partial 🔬 — Core Rulebook .windsurfrules
GitHub Copilot 🔶 Partial 🔬 — Core Prompts .github/copilot-instructions.md
OpenAI Codex 🔶 Partial ✅ 2026-07-23 Core — AGENTS.md
Aider 🔶 Partial 🔬 — — — AGENTS.md
Continue.dev 🔶 Partial 🔬 — — — .continue/config.json
Google Antigravity ⚠️ Minimal 🔬 — —‡ — .antigravity/rules.md
Gemini CLI ⛔ Discontinued† — — — GEMINI.md (frozen)

Status Legend (how complete the integration we wrote is):
✅ Complete | 🔶 Partial | ⚠️ Minimal | ⏳ Planned | ⛔ Discontinued

Verified Legend (whether a probe run confirmed the tool behaves accordingly):
✅ date verified | 🔬 — not yet verified | ⌛ expired | ❌ failed

◆ Claude Code is in daily production use by the maintainer, which is why the
integration is the most complete — but daily use is not a recorded verification, and a
tool cannot be the judge of itself. It sits in the queue like everything else.

† Google sunset Gemini CLI on 2026-06-18 (announced at I/O 2026-05-19, 30-day
migration window), succeeded by Antigravity CLI. The integrations/gemini-cli/ and .gemini/
trees are frozen — kept for reference, excluded from sync checks, and no longer maintained.
See .gemini/DEPRECATED.md.

‡ Antigravity supports skills, but the correct install path is not yet verified
against a real Antigravity CLI. Two candidates conflict: ~/.gemini/antigravity-cli/plugins/<name>/skills/
(official plugin docs) and .agent/skills/ (UDS's own 2026-02 spec, written in the Gemini CLI era).
uds init therefore does not install skills for this target until one is confirmed — an
unverified path fails silently, which is worse than not installing.


📦 Installation Methods

CLI Tool (Primary)

npm (Recommended)

npm install -g universal-dev-standards
uds init        # Interactive initialization
uds check       # Check adoption status
uds update      # Update to latest version
uds config      # Manage preferences (language, mode)
uds uninstall   # Remove standards from project

⚙️ Configuration

Use uds config to manage your preferences:

Parameter Command Description
Commit Language uds config set output_language traditional-chinese Set preferred language for AI commits
Standards uds init Install all available standards
Tool Mode uds config --type content_mode Choose between Skills, Standards, or Both

👥 Contributing

  1. Suggest Improvements: Open an issue with problem and solution.
  2. Add Examples: Submit real-world usage examples.
  3. Extend Standards: Contribute language/framework extensions.

See CONTRIBUTING.md for detailed guidelines.


📄 License

Component License
Documentation CC BY 4.0
CLI Tool MIT

Acknowledgments

UDS draws architectural inspiration from these outstanding open-source projects:

Project Inspiration License
Superpowers Systematic debugging, agent dispatch, verification evidence MIT
GSD Structured task definition, traceability matrix, verification loop cap MIT
PAUL Plan-Apply-Unify loop, acceptance-driven development MIT
CARL Context-aware loading, dynamic rule injection MIT
CrewAI Multi-agent communication protocol, context budget tracking MIT
LangGraph Workflow state protocol, HITL interrupt checkpoints MIT
OpenHands Event sourcing, action-observation stream patterns MIT
DSPy Agent signatures, structured I/O contracts MIT

Note: UDS adopts concepts and methodologies only — no source code from these projects is included.


Maintained with ❤️ by the open-source community

Facts

Kind
Marketplace
Repo
AsiaOstrich/universal-dev-standards
Group
Uncategorized
Marketplace name
asia-ostrich
Owner
AsiaOstrich
Language
JavaScript
Created
2025-12-24
Forks
13
Topics
ai-collaboration, best-practices, claude-code, code-review, coding-standards, commit-conventions, conventional-commits, developer-tools, development-standards, devops, documentation, git-workflow, quality-assurance, semantic-versioning, skills, software-engineering, spec-driven-development, testing-standards
Plugins
1

More on this shelf

  1. 1f/prompts.chatf/prompts.chatf.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
  2. 2affaan-m/everything-claude-codeaffaan-m/everything-claude-codeThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
  3. 3obra/superpowersobra/superpowersAn agentic skills framework & software development methodology that works.
  4. 4anthropics/skillsanthropics/skillsPublic repository for Agent Skills
  5. 5anthropics/claude-codeanthropics/claude-codeClaude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
  6. 6nextlevelbuilder/ui-ux-pro-max-skillnextlevelbuilder/ui-ux-pro-max-skillAn AI skill that provides design intelligence for building professional UI/UX across multiple platforms.