Skip to content
Back to search

ai-agent-skills

AI agent skills for production grade applications

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/developersglobal--ai-agent-skills/badge.svg)](/listings/developersglobal--ai-agent-skills)

HTML

<a href="/listings/developersglobal--ai-agent-skills"><img src="/api/listings/developersglobal--ai-agent-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Step 1 — Clone the repo

git clone https://github.com/DevelopersGlobal/ai-agent-skills.git

Step 2 — Pick a skill and copy it into your agent

**Claude / Cursor / Copilot / any agent:** Copy the contents of any `SKILL.md` file into your agent's system prompt, instructions file, or context window.

**For Claude Code** — add to your project's `CLAUDE.md`:

cat skills/think-before-coding/SKILL.md >> CLAUDE.md

**For Cursor** — copy into `.cursor/rules/`:

cp skills/security-hardening/SKILL.md .cursor/rules/security-hardening.mdc

**For Gemini CLI** — add to your project's `GEMINI.md`:

cat skills/goal-driven-execution/SKILL.md >> GEMINI.md

**One-liner (any skill, any agent):**

# View raw skill content, then paste into your agent
curl https://raw.githubusercontent.com/DevelopersGlobal/ai-agent-skills/main/skills/production-deployment/SKILL.md

> **Browse and copy skills visually →** [developersglobal.github.io/ai-agent-skills](https://developersglobal.github.io/ai-agent-skills)

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 226 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. # 🤖 AI Agent Skills
  3. ### *Production-grade AI agent skills for real-world applications — and everyday use*
  4. [![GitHub Stars](https://img.shields.io/github/stars/DevelopersGlobal/ai-agent-skills?style=for-the-badge&logo=github&color=FFD700)](https://github.com/DevelopersGlobal/ai-agent-skills/stargazers)
  5. [![GitHub Forks](https://img.shields.io/github/forks/DevelopersGlobal/ai-agent-skills?style=for-the-badge&logo=github&color=00BFFF)](https://github.com/DevelopersGlobal/ai-agent-skills/network)
  6. [![License: MIT](https://img.shields.io/badge/License-MIT-green?style=for-the-badge)](LICENSE)
  7. [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen?style=for-the-badge)](CONTRIBUTING.md)
  8. [![GitHub Pages](https://img.shields.io/badge/Docs-GitHub_Pages-blue?style=for-the-badge&logo=github)](https://developersglobal.github.io/ai-agent-skills)
  9. > **Inspired by [addyosmani/agent-skills](https://github.com/addyosmani/agent-skills) and [forrestchang/andrej-karpathy-skills](https://github.com/forrestchang/andrej-karpathy-skills)**
  10. **🌐 [View the Interactive Skills Browser →](https://developersglobal.github.io/ai-agent-skills)**
  11. </div>
  12. ---
  13. ## 🎯 What is this?
  14. AI agents are only as good as the instructions they follow. **AI Agent Skills** is a curated, battle-tested library of skill files — structured markdown prompts — that transform AI coding agents (Claude, Gemini, Cursor, Copilot, etc.) into disciplined, production-ready engineers.
  15. Unlike generic prompts, these skills encode **actual workflows** with steps, checkpoints, verification gates, and anti-pattern guards — the same discipline senior engineers bring to every production deployment.
  16. ```
  17. THINK → PLAN → BUILD → TEST → REVIEW → HARDEN → SHIP
  18. ↓ ↓ ↓ ↓ ↓ ↓ ↓
  19. Clarify Break Write Verify Quality Security Deploy
  20. Goals Down Code Output Gates Gates Live
  21. ```
  22. ---
  23. ## 🏆 Why This Repo Goes Beyond the Rest
  24. | Feature | This Repo | agent-skills | karpathy-skills |
  25. |--------|-----------|--------------|-----------------|
  26. | Production + Everyday use | ✅ | Production only | General |
  27. | Multi-agent orchestration | ✅ | ❌ | ❌ |
  28. | AI safety & hallucination guards | ✅ | ❌ | Partial |
  29. | RAG / Memory skills | ✅ | ❌ | ❌ |
  30. | Prompt injection defense | ✅ | ❌ | ❌ |
  31. | GitHub Pages search UI | ✅ | ❌ | ❌ |
  32. | 30+ curated skills | ✅ | 20 skills | 4 principles |
  33. | Everyday productivity skills | ✅ | ❌ | ❌ |
  34. ---
  35. ## ⚡ Quick Start
  36. ### Step 1 — Clone the repo
  37. ```bash
  38. git clone https://github.com/DevelopersGlobal/ai-agent-skills.git
  39. ```
  40. ### Step 2 — Pick a skill and copy it into your agent
  41. **Claude / Cursor / Copilot / any agent:**
  42. Copy the contents of any `SKILL.md` file into your agent's system prompt, instructions file, or context window.
  43. **For Claude Code** — add to your project's `CLAUDE.md`:
  44. ```bash
  45. cat skills/think-before-coding/SKILL.md >> CLAUDE.md
  46. ```
  47. **For Cursor** — copy into `.cursor/rules/`:
  48. ```bash
  49. cp skills/security-hardening/SKILL.md .cursor/rules/security-hardening.mdc
  50. ```
  51. **For Gemini CLI** — add to your project's `GEMINI.md`:
  52. ```bash
  53. cat skills/goal-driven-execution/SKILL.md >> GEMINI.md
  54. ```
  55. **One-liner (any skill, any agent):**
  56. ```bash
  57. # View raw skill content, then paste into your agent
  58. curl https://raw.githubusercontent.com/DevelopersGlobal/ai-agent-skills/main/skills/production-deployment/SKILL.md
  59. ```
  60. > **Browse and copy skills visually →** [developersglobal.github.io/ai-agent-skills](https://developersglobal.github.io/ai-agent-skills)
  61. ---
  62. ## 📚 All Skills
  63. ### 🧠 Think — Before You Code
  64. | Skill | Description |
  65. |-------|-------------|
  66. | [think-before-coding](skills/think-before-coding/SKILL.md) | Surface assumptions, manage confusion, prevent hallucination |
  67. | [goal-driven-execution](skills/goal-driven-execution/SKILL.md) | Transform tasks into verifiable goals with success criteria |
  68. | [idea-to-spec](skills/idea-to-spec/SKILL.md) | Convert vague ideas into concrete, testable specifications |
  69. ### 📐 Plan — Break It Down
  70. | Skill | Description |
  71. |-------|-------------|
  72. | [task-decomposition](skills/task-decomposition/SKILL.md) | Break features into atomic, independently verifiable tasks |
  73. | [context-loading](skills/context-loading/SKILL.md) | Load minimum necessary context; avoid token bloat |
  74. | [multi-agent-orchestration](skills/multi-agent-orchestration/SKILL.md) | Design and coordinate multi-agent pipelines |
  75. ### 🏗️ Build — Write Production Code
  76. | Skill | Description |
  77. |-------|-------------|
  78. | [incremental-coding](skills/incremental-coding/SKILL.md) | Build in verifiable increments; never big-bang rewrites |
  79. | [simplicity-first](skills/simplicity-first/SKILL.md) | Minimum code that solves the problem — nothing speculative |
  80. | [surgical-changes](skills/surgical-changes/SKILL.md) | Touch only what you must; leave the rest untouched |
  81. | [api-design](skills/api-design/SKILL.md) | Design stable, versioned, self-documenting APIs |
  82. | [frontend-engineering](skills/frontend-engineering/SKILL.md) | Accessible, performant, responsive UI patterns |
  83. | [rag-and-memory](skills/rag-and-memory/SKILL.md) | Retrieval-Augmented Generation and agent memory patterns |
  84. ### ✅ Test — Prove It Works
  85. | Skill | Description |
  86. |-------|-------------|
  87. | [test-driven-development](skills/test-driven-development/SKILL.md) | Red-green-refactor with meaningful coverage |
  88. | [debugging-methodology](skills/debugging-methodology/SKILL.md) | Systematic root cause analysis; never guess-and-check |
  89. | [integration-testing](skills/integration-testing/SKILL.md) | Test real system boundaries, not mocks of mocks |
  90. | [ai-output-validation](skills/ai-output-validation/SKILL.md) | Validate, parse, and sanitize AI-generated outputs |
  91. | [agent-qa-run-review](skills/agent-qa-run-review/SKILL.md) | Review agent-qa evidence and memidex memory provenance before explaining a QA verdict |
  92. ### 🔍 Review — Quality Gates
  93. | Skill | Description |
  94. |-------|-------------|
  95. | [code-review](skills/code-review/SKILL.md) | Structured review checklist; correctness over style |
  96. | [performance-optimization](skills/performance-optimization/SKILL.md) | Measure first, optimize second; no premature optimization |
  97. | [refactoring](skills/refactoring/SKILL.md) | Safe, behavior-preserving transformation with tests |
  98. | [documentation](skills/documentation/SKILL.md) | Document decisions, not just implementations |
  99. ### 🔒 Harden — Security & Reliability
  100. | Skill | Description |
  101. |-------|-------------|
  102. | [security-hardening](skills/security-hardening/SKILL.md) | OWASP Top 10, secrets management, least privilege |
  103. | [prompt-injection-defense](skills/prompt-injection-defense/SKILL.md) | Guard AI agents against prompt injection attacks |
  104. | [hallucination-prevention](skills/hallucination-prevention/SKILL.md) | Detect and mitigate LLM hallucinations in pipelines |
  105. | [error-handling](skills/error-handling/SKILL.md) | Graceful degradation and meaningful error messages |
  106. | [observability](skills/observability/SKILL.md) | Structured logging, tracing, and alerting for AI systems |
  107. ### 🚀 Ship — Deploy with Confidence
  108. | Skill | Description |
  109. |-------|-------------|
  110. | [production-deployment](skills/production-deployment/SKILL.md) | Zero-downtime deploys with rollback plans |
  111. | [ci-cd-pipelines](skills/ci-cd-pipelines/SKILL.md) | Automated quality gates from commit to production |
  112. | [git-workflow](skills/git-workflow/SKILL.md) | Trunk-based development, atomic commits, clean history |
  113. ### 🌟 Everyday — Productivity Skills
  114. | Skill | Description |
  115. |-------|-------------|
  116. | [code-explanation](skills/code-explanation/SKILL.md) | Get clear, layered explanations of unfamiliar code |
  117. | [meeting-notes-to-tasks](skills/meeting-notes-to-tasks/SKILL.md) | Convert meeting notes into structured action items |
  118. | [research-and-summarize](skills/research-and-summarize/SKILL.md) | Distill complex topics into actionable summaries |
  119. ---
  120. ## 🏛️ Skill Anatomy
  121. Every skill follows the same battle-tested structure:
  122. ```
  123. ┌─────────────────────────────────────────────────────┐
  124. │ SKILL.md │
  125. │ │
  126. │ ┌─ Frontmatter ────────────────────────────────┐ │
  127. │ │ name: kebab-case-name │ │
  128. │ │ description: One-line trigger description │ │
  129. │ │ applies-to: [claude, gemini, cursor, ...] │ │
  130. │ │ category: think|plan|build|test|... │ │
  131. │ └──────────────────────────────────────────────┘ │
  132. │ │
  133. │ Overview → What this skill accomplishes │
  134. │ When to Use → Exact triggering conditions │
  135. │ Process → Numbered, verifiable steps │
  136. │ Rationalizations → Common excuses + rebuttals │
  137. │ Red Flags → Warning signs the skill is needed │
  138. │ Verification → Non-negotiable evidence required │
  139. │ References → Supporting checklists/docs │
  140. └─────────────────────────────────────────────────────┘
  141. ```
  142. ---
  143. ## 🤝 Contributing
  144. We welcome contributions! The best skills are:
  145. - **Specific** — Actionable steps, not vague principles
  146. - **Verifiable** — Clear exit criteria with evidence
  147. - **Battle-tested** — Based on real production experience
  148. - **Minimal** — Only what the agent needs; no bloat
  149. See [CONTRIBUTING.md](CONTRIBUTING.md) and [docs/skill-anatomy.md](docs/skill-anatomy.md).
  150. ---
  151. ## 🌐 GitHub Pages
  152. The full skills library is browsable at **[developersglobal.github.io/ai-agent-skills](https://developersglobal.github.io/ai-agent-skills)** with:
  153. - 🔍 Full-text search across all skills
  154. - 🏷️ Filter by category and agent type
  155. - 📋 One-click copy for any skill
  156. - 📱 Mobile-friendly responsive design
  157. ---
  158. ## 📊 Inspiration & Credits
  159. This project builds on and extends the ideas from:
  160. - [addyosmani/agent-skills](https://github.com/addyosmani/agent-skills) — Production engineering skills for AI agents
  161. - [forrestchang/andrej-karpathy-skills](https://github.com/forrestchang/andrej-karpathy-skills) — Karpathy's observations on LLM coding pitfalls
  162. - [DevelopersGlobal](https://github.com/DevelopersGlobal) — Community-driven developer tools
  163. ---
  164. ## 📄 License
  165. MIT — Use these skills in your projects, teams, and tools. Attribution appreciated but not required.
  166. ---
  167. <div align="center">
  168. **⭐ Star this repo to help developers everywhere build better AI agents ⭐**
  169. Made with ❤️ by [DevelopersGlobal](https://github.com/DevelopersGlobal)
  170. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.