SkillKit

The toolkit for creating reusable skills for AI coding agents.

SkillKit helps you build, validate, and share skills that extend how your AI agent works. Works with Claude Code, GitHub Copilot, OpenCode, and Codex.

Previously known as claude-skillkit. All old links redirect here automatically.

What is SkillKit?

SkillKit is a toolkit for creating and validating custom AI agent skills. It ships two core skills:

• skillkit — meta-skill for creating new skills and subagents with dual-mode validation
• skillkit-help — pre-build orientation: understand what skills are, decide skills vs subagents

Looking for community skills & agents? Use: npx @rfxlamia/sm → SkillKit Marketplace

Install

npx @rfxlamia/skillkit

Interactive CLI — pick your tool(s), choose user or project scope. Done.

Core Skills

Create Your First Skill

1. Install: npx @rfxlamia/skillkit
2. Run /skillkit-help — guided path to your first skill in ~10 minutes
3. Submit a PR to SkillKit Marketplace to share it

SkillKit Creator Reference

The skillkit skill drives the creation workflow:

Quality target: 9.0+/10 via 5-layer validation and multi-proposal generation.

Automation Scripts

14 Python scripts in skills/skillkit/scripts/ — all support --format {text|json}.

Screenshots

CLI installer

Guided orientation

A finished skill

Community Skills & Agents

24 community skills and 7 agents are available at SkillKit Marketplace:

npx @rfxlamia/sm

License

Apache 2.0 - Copyright 2025 rfxlamia

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "skillkit-marketplace",
  "description": "Professional skill creation with TDD workflow and behavioral validation. Includes dual-mode (fast/full), pressure testing, and quality gates.",
  "owner": {
    "name": "rfxlamia",
    "email": "rfxlamia@github.com"
  },
  "metadata": {
    "version": "2.1.6",
    "description": "Professional skill and subagent creation toolkit with dual-mode workflow (fast/full), behavioral validation, and quality gates for 9.0/10+ scores."
  },
  "plugins": [
    {
      "name": "skillkit-core",
      "description": "Professional skill and subagent creation with dual-mode workflow: 12-step fast mode and 15-step full mode with behavioral pressure testing and TDD integration.",
      "source": "./skills/skillkit",
      "version": "2.1.6",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "skill-creator",
        "subagent-creator",
        "skillkit",
        "validation",
        "automation",
        "quality-assurance",
        "research-driven",
        "anti-hallucination",
        "testing",
        "security",
        "token-optimization",
        "tdd",
        "behavioral-testing",
        "pressure-testing"
      ],
      "category": "development",
      "strict": false
    },
    {
      "name": "skillkit-essentials",
      "description": "Essential skills for everyday development: beginner-friendly explanations (baby-education), comprehensive README creation (readme-expert), LLM prompt optimization (prompt-engineering), AI-to-human doc transformation (humanize-docs), technical spec creation (quick-spec), pre-deployment QA checklisting (pre-deploy-checklist), and developer progress logging (been-there-done-that).",
      "source": "./bundles/essentials",
      "version": "1.0.0",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "documentation",
        "education",
        "prompting",
        "learning",
        "beginner-friendly",
        "quick-spec",
        "pre-deploy-checklist",
        "been-there-done-that",
        "planning",
        "qa",
        "progress-logging"
      ],
      "category": "productivity",
      "strict": false
    },
    {
      "name": "skillkit-frameworks",
      "description": "Agent capability frameworks: STAR framework for understanding implicit intent (framework-initiative), critical thinking architecture with reasoning selection (framework-critical-thinking), and adversarial review protocol with mandatory bug quota (adversarial-review). Build smarter, self-correcting agents and validate plans before execution.",
      "source": "./bundles/frameworks",
      "version": "1.0.0",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "agent-framework",
        "critical-thinking",
        "reasoning",
        "initiative",
        "STAR",
        "adversarial-review"
      ],
      "category": "development",
      "strict": false
    },
    {
      "name": "skillkit-creative",
      "description": "Content creation powerhouse: viral thread generation (thread-pro), storytelling (storyteller), screenwriting (screenwriter), creative copywriting with databases (creative-copywriting), image prompt optimization (imagine), and high-diversity content generation (diverse-content-gen).",
      "source": "./bundles/creative",
      "version": "1.0.0",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "creative",
        "content-creation",
        "writing",
        "threads",
        "storytelling",
        "copywriting",
        "image-generation"
      ],
      "category": "productivity",
      "strict": false
    },
    {
      "name": "skillkit-social-media",
      "description": "Social media SEO optimization with 2025-proven strategies. Includes comprehensive CSV databases with 100+ caption formulas, thread structures, viral patterns, and platform-specific playbooks for Instagram, X/Twitter, and Threads.",
      "source": "./skills/social-media-seo",
      "version": "1.0.0",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "social-media",
        "seo",
        "marketing",
        "instagram",
        "twitter",
        "threads",
        "viral-content"
      ],
      "category": "productivity",
      "strict": false
    },
    {
      "name": "skillkit-subagents",
      "description": "Specialized subagent collection: Creative copywriter with psychology triggers, SEO manager with proven formulas, decision-making agents (velocity-first Sam Altman, safety-first Dario Amodei), Kotlin expert, doc simplifier, and comprehensive red team security agent.",
      "source": "./bundles/subagents",
      "version": "1.0.0",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "subagents",
        "specialized-agents",
        "decision-making",
        "security",
        "kotlin",
        "documentation"
      ],
      "category": "development",
      "strict": false
    },
    {
      "name": "red-teaming",
      "description": "Comprehensive red teaming methodology for both cybersecurity (MITRE ATT&CK, pentesting) and AI/LLM systems (prompt injection, jailbreaking, OWASP Top 10 LLM). Includes threat modeling, attack simulation, compliance validation (NIST, EU AI Act), and progressive attack technique references.",
      "source": "./skills/red-teaming",
      "version": "1.0.0",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "security",
        "red-team",
        "pentesting",
        "vulnerability-assessment",
        "ai-security",
        "llm-security",
        "prompt-injection",
        "compliance"
      ],
      "category": "security",
      "strict": false
    },
    {
      "name": "releasing",
      "description": "Automate the full release workflow: version bumping (major/minor/patch), changelog generation, git tagging, pushing, and GitHub release creation. Handles semver across Node.js, Python, Rust, Go, and generic projects. Enforces mandatory confirmations before irreversible actions (push, release).",
      "source": "./skills/releasing",
      "version": "1.0.0",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "release",
        "version",
        "semver",
        "changelog",
        "git-tag",
        "github-release",
        "deployment"
      ],
      "category": "development",
      "strict": false
    },
    {
      "name": "validate-plan",
      "description": "Validate implementation plans against DRY, YAGNI, TDD principles and best practices. Identifies gaps, anti-patterns, and improvement opportunities before execution. Prevents over-engineering and ensures test-first approach.",
      "source": "./skills/validate-plan",
      "version": "1.0.0",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "planning",
        "validation",
        "dry",
        "yagni",
        "tdd",
        "code-review",
        "best-practices"
      ],
      "category": "development",
      "strict": false
    },
    {
      "name": "verify-before-ship",
      "description": "Enforce completion of all 7 production safety gates with evidence before any deployment. Blocks rationalized shortcuts under time, authority, sunk-cost, or exhaustion pressure. Gates: tests, security scan, breaking changes, config validation, staging verification, rollback plan, code review.",
      "source": "./skills/verify-before-ship",
      "version": "1.0.0",
      "author": {
        "name": "rfxlamia"
      },
      "homepage": "https://github.com/rfxlamia/skillkit",
      "repository": "https://github.com/rfxlamia/skillkit",
      "license": "Apache-2.0",
      "keywords": [
        "deployment",
        "production",
        "safety",
        "verification",
        "gates",
        "devops",
        "release"
      ],
      "category": "development",
      "strict": false
    }
  ]
}