[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-80043":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":12,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":15,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":14,"rankGlobal":10,"rankLanguage":10,"license":16,"archived":17,"fork":17,"defaultBranch":18,"hasWiki":19,"hasPages":19,"topics":20,"createdAt":10,"pushedAt":10,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":15,"starSnapshotCount":15,"syncStatus":34,"lastSyncTime":35,"discoverSource":36},80043,"ai-agent-skills","DevelopersGlobal\u002Fai-agent-skills","DevelopersGlobal","AI agent skills for production grade applications","https:\u002F\u002Fdevelopersglobal.github.io\u002Fai-agent-skills\u002F",null,"Python",64,9,3,0,"MIT License",false,"main",true,[21,22,23,24,25,26,27,28,29,30],"ai","ai-agents","antigravity","artificial-intelligence","claude","claude-code-plugin","claude-skills","codex","cursor","skills","2026-06-12 02:03:57","\u003Cdiv align=\"center\">\n\n# 🤖 AI Agent Skills\n\n### *Production-grade AI agent skills for real-world applications — and everyday use*\n\n[![GitHub Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDevelopersGlobal\u002Fai-agent-skills?style=for-the-badge&logo=github&color=FFD700)](https:\u002F\u002Fgithub.com\u002FDevelopersGlobal\u002Fai-agent-skills\u002Fstargazers)\n[![GitHub Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDevelopersGlobal\u002Fai-agent-skills?style=for-the-badge&logo=github&color=00BFFF)](https:\u002F\u002Fgithub.com\u002FDevelopersGlobal\u002Fai-agent-skills\u002Fnetwork)\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-green?style=for-the-badge)](LICENSE)\n[![PRs Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen?style=for-the-badge)](CONTRIBUTING.md)\n[![GitHub Pages](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocs-GitHub_Pages-blue?style=for-the-badge&logo=github)](https:\u002F\u002Fdevelopersglobal.github.io\u002Fai-agent-skills)\n\n> **Inspired by [addyosmani\u002Fagent-skills](https:\u002F\u002Fgithub.com\u002Faddyosmani\u002Fagent-skills) and [forrestchang\u002Fandrej-karpathy-skills](https:\u002F\u002Fgithub.com\u002Fforrestchang\u002Fandrej-karpathy-skills)**\n\n**🌐 [View the Interactive Skills Browser →](https:\u002F\u002Fdevelopersglobal.github.io\u002Fai-agent-skills)**\n\n\u003C\u002Fdiv>\n\n---\n\n## 🎯 What is this?\n\nAI 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.\n\nUnlike 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.\n\n```\nTHINK → PLAN → BUILD → TEST → REVIEW → HARDEN → SHIP\n  ↓        ↓      ↓       ↓       ↓        ↓        ↓\nClarify  Break  Write  Verify  Quality  Security  Deploy\nGoals    Down   Code   Output  Gates    Gates     Live\n```\n\n---\n\n## 🏆 Why This Repo Goes Beyond the Rest\n\n| Feature | This Repo | agent-skills | karpathy-skills |\n|--------|-----------|--------------|-----------------|\n| Production + Everyday use | ✅ | Production only | General |\n| Multi-agent orchestration | ✅ | ❌ | ❌ |\n| AI safety & hallucination guards | ✅ | ❌ | Partial |\n| RAG \u002F Memory skills | ✅ | ❌ | ❌ |\n| Prompt injection defense | ✅ | ❌ | ❌ |\n| GitHub Pages search UI | ✅ | ❌ | ❌ |\n| 30+ curated skills | ✅ | 20 skills | 4 principles |\n| Everyday productivity skills | ✅ | ❌ | ❌ |\n\n---\n\n## ⚡ Quick Start\n\n### Step 1 — Clone the repo\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FDevelopersGlobal\u002Fai-agent-skills.git\n```\n\n### Step 2 — Pick a skill and copy it into your agent\n\n**Claude \u002F Cursor \u002F Copilot \u002F any agent:**\nCopy the contents of any `SKILL.md` file into your agent's system prompt, instructions file, or context window.\n\n**For Claude Code** — add to your project's `CLAUDE.md`:\n```bash\ncat skills\u002Fthink-before-coding\u002FSKILL.md >> CLAUDE.md\n```\n\n**For Cursor** — copy into `.cursor\u002Frules\u002F`:\n```bash\ncp skills\u002Fsecurity-hardening\u002FSKILL.md .cursor\u002Frules\u002Fsecurity-hardening.mdc\n```\n\n**For Gemini CLI** — add to your project's `GEMINI.md`:\n```bash\ncat skills\u002Fgoal-driven-execution\u002FSKILL.md >> GEMINI.md\n```\n\n**One-liner (any skill, any agent):**\n```bash\n# View raw skill content, then paste into your agent\ncurl https:\u002F\u002Fraw.githubusercontent.com\u002FDevelopersGlobal\u002Fai-agent-skills\u002Fmain\u002Fskills\u002Fproduction-deployment\u002FSKILL.md\n```\n\n> **Browse and copy skills visually →** [developersglobal.github.io\u002Fai-agent-skills](https:\u002F\u002Fdevelopersglobal.github.io\u002Fai-agent-skills)\n\n---\n\n## 📚 All 30 Skills\n\n### 🧠 Think — Before You Code\n| Skill | Description |\n|-------|-------------|\n| [think-before-coding](skills\u002Fthink-before-coding\u002FSKILL.md) | Surface assumptions, manage confusion, prevent hallucination |\n| [goal-driven-execution](skills\u002Fgoal-driven-execution\u002FSKILL.md) | Transform tasks into verifiable goals with success criteria |\n| [idea-to-spec](skills\u002Fidea-to-spec\u002FSKILL.md) | Convert vague ideas into concrete, testable specifications |\n\n### 📐 Plan — Break It Down\n| Skill | Description |\n|-------|-------------|\n| [task-decomposition](skills\u002Ftask-decomposition\u002FSKILL.md) | Break features into atomic, independently verifiable tasks |\n| [context-loading](skills\u002Fcontext-loading\u002FSKILL.md) | Load minimum necessary context; avoid token bloat |\n| [multi-agent-orchestration](skills\u002Fmulti-agent-orchestration\u002FSKILL.md) | Design and coordinate multi-agent pipelines |\n\n### 🏗️ Build — Write Production Code\n| Skill | Description |\n|-------|-------------|\n| [incremental-coding](skills\u002Fincremental-coding\u002FSKILL.md) | Build in verifiable increments; never big-bang rewrites |\n| [simplicity-first](skills\u002Fsimplicity-first\u002FSKILL.md) | Minimum code that solves the problem — nothing speculative |\n| [surgical-changes](skills\u002Fsurgical-changes\u002FSKILL.md) | Touch only what you must; leave the rest untouched |\n| [api-design](skills\u002Fapi-design\u002FSKILL.md) | Design stable, versioned, self-documenting APIs |\n| [frontend-engineering](skills\u002Ffrontend-engineering\u002FSKILL.md) | Accessible, performant, responsive UI patterns |\n| [rag-and-memory](skills\u002Frag-and-memory\u002FSKILL.md) | Retrieval-Augmented Generation and agent memory patterns |\n\n### ✅ Test — Prove It Works\n| Skill | Description |\n|-------|-------------|\n| [test-driven-development](skills\u002Ftest-driven-development\u002FSKILL.md) | Red-green-refactor with meaningful coverage |\n| [debugging-methodology](skills\u002Fdebugging-methodology\u002FSKILL.md) | Systematic root cause analysis; never guess-and-check |\n| [integration-testing](skills\u002Fintegration-testing\u002FSKILL.md) | Test real system boundaries, not mocks of mocks |\n| [ai-output-validation](skills\u002Fai-output-validation\u002FSKILL.md) | Validate, parse, and sanitize AI-generated outputs |\n\n### 🔍 Review — Quality Gates\n| Skill | Description |\n|-------|-------------|\n| [code-review](skills\u002Fcode-review\u002FSKILL.md) | Structured review checklist; correctness over style |\n| [performance-optimization](skills\u002Fperformance-optimization\u002FSKILL.md) | Measure first, optimize second; no premature optimization |\n| [refactoring](skills\u002Frefactoring\u002FSKILL.md) | Safe, behavior-preserving transformation with tests |\n| [documentation](skills\u002Fdocumentation\u002FSKILL.md) | Document decisions, not just implementations |\n\n### 🔒 Harden — Security & Reliability\n| Skill | Description |\n|-------|-------------|\n| [security-hardening](skills\u002Fsecurity-hardening\u002FSKILL.md) | OWASP Top 10, secrets management, least privilege |\n| [prompt-injection-defense](skills\u002Fprompt-injection-defense\u002FSKILL.md) | Guard AI agents against prompt injection attacks |\n| [hallucination-prevention](skills\u002Fhallucination-prevention\u002FSKILL.md) | Detect and mitigate LLM hallucinations in pipelines |\n| [error-handling](skills\u002Ferror-handling\u002FSKILL.md) | Graceful degradation and meaningful error messages |\n| [observability](skills\u002Fobservability\u002FSKILL.md) | Structured logging, tracing, and alerting for AI systems |\n\n### 🚀 Ship — Deploy with Confidence\n| Skill | Description |\n|-------|-------------|\n| [production-deployment](skills\u002Fproduction-deployment\u002FSKILL.md) | Zero-downtime deploys with rollback plans |\n| [ci-cd-pipelines](skills\u002Fci-cd-pipelines\u002FSKILL.md) | Automated quality gates from commit to production |\n| [git-workflow](skills\u002Fgit-workflow\u002FSKILL.md) | Trunk-based development, atomic commits, clean history |\n\n### 🌟 Everyday — Productivity Skills\n| Skill | Description |\n|-------|-------------|\n| [code-explanation](skills\u002Fcode-explanation\u002FSKILL.md) | Get clear, layered explanations of unfamiliar code |\n| [meeting-notes-to-tasks](skills\u002Fmeeting-notes-to-tasks\u002FSKILL.md) | Convert meeting notes into structured action items |\n| [research-and-summarize](skills\u002Fresearch-and-summarize\u002FSKILL.md) | Distill complex topics into actionable summaries |\n\n---\n\n## 🏛️ Skill Anatomy\n\nEvery skill follows the same battle-tested structure:\n\n```\n┌─────────────────────────────────────────────────────┐\n│ SKILL.md                                            │\n│                                                     │\n│  ┌─ Frontmatter ────────────────────────────────┐  │\n│  │  name:        kebab-case-name                │  │\n│  │  description: One-line trigger description   │  │\n│  │  applies-to:  [claude, gemini, cursor, ...]  │  │\n│  │  category:    think|plan|build|test|...      │  │\n│  └──────────────────────────────────────────────┘  │\n│                                                     │\n│  Overview      → What this skill accomplishes       │\n│  When to Use   → Exact triggering conditions        │\n│  Process       → Numbered, verifiable steps         │\n│  Rationalizations → Common excuses + rebuttals      │\n│  Red Flags     → Warning signs the skill is needed  │\n│  Verification  → Non-negotiable evidence required   │\n│  References    → Supporting checklists\u002Fdocs         │\n└─────────────────────────────────────────────────────┘\n```\n\n---\n\n## 🤝 Contributing\n\nWe welcome contributions! The best skills are:\n- **Specific** — Actionable steps, not vague principles\n- **Verifiable** — Clear exit criteria with evidence\n- **Battle-tested** — Based on real production experience\n- **Minimal** — Only what the agent needs; no bloat\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) and [docs\u002Fskill-anatomy.md](docs\u002Fskill-anatomy.md).\n\n---\n\n## 🌐 GitHub Pages\n\nThe full skills library is browsable at **[developersglobal.github.io\u002Fai-agent-skills](https:\u002F\u002Fdevelopersglobal.github.io\u002Fai-agent-skills)** with:\n- 🔍 Full-text search across all skills\n- 🏷️ Filter by category and agent type\n- 📋 One-click copy for any skill\n- 📱 Mobile-friendly responsive design\n\n---\n\n## 📊 Inspiration & Credits\n\nThis project builds on and extends the ideas from:\n- [addyosmani\u002Fagent-skills](https:\u002F\u002Fgithub.com\u002Faddyosmani\u002Fagent-skills) — Production engineering skills for AI agents\n- [forrestchang\u002Fandrej-karpathy-skills](https:\u002F\u002Fgithub.com\u002Fforrestchang\u002Fandrej-karpathy-skills) — Karpathy's observations on LLM coding pitfalls\n- [DevelopersGlobal](https:\u002F\u002Fgithub.com\u002FDevelopersGlobal) — Community-driven developer tools\n\n---\n\n## 📄 License\n\nMIT — Use these skills in your projects, teams, and tools. Attribution appreciated but not required.\n\n---\n\n\u003Cdiv align=\"center\">\n\n**⭐ Star this repo to help developers everywhere build better AI agents ⭐**\n\nMade with ❤️ by [DevelopersGlobal](https:\u002F\u002Fgithub.com\u002FDevelopersGlobal)\n\n\u003C\u002Fdiv>\n","AI Agent Skills 是一个专为生产级应用设计的AI代理技能库，通过提供结构化的Markdown提示文件来提升AI编码代理（如Claude、Gemini、Cursor等）的工作效率和质量。该项目采用Python编写，核心功能包括实际工作流程的编码、多代理协调、AI安全防护以及记忆技能等，旨在将AI代理转变为能够遵循严格工程实践的专业工程师。适用于需要高质量代码产出并重视安全性的软件开发场景，特别是在追求高效与可靠的日常及生产环境中使用。",2,"2026-06-11 03:59:02","CREATED_QUERY"]