convez.ai
MCP Server
frankxai

claude-skills-library

frankxai/claude-skills-library

Ver no GitHub
BomPluginScore · de 0 a 100

Professional-grade skills for Claude Code & Claude AI - Transform Claude into a domain expert in seconds

Instalação

$npx convez-ai frankxai/claude-skills-library

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
48
Forks
6
Acompanhando
1
Saúde
57%
Último commit
há 2 dias
Versão
—
Issues abertas
24
Contribuidores
3

README

A tradução para o português deste README ainda está na fila.

🧠 Claude Skills Library

107 production-grade Agent Skills for Claude Code, Claude.ai & every major agentic runtime

Turn your AI agent into a domain expert. Each skill is a self-contained, spec-compliant SKILL.md — engineered with real frameworks, current best practices, and opinionated guidance, not 500 words of filler. Free. MIT-licensed. Installable in one command.

License: MIT Skills Frontmatter validated Runtimes PRs Welcome

⚡ Quick start · 🌐 Browse online · 📚 Full catalog · 🗂️ Categories · ❓ FAQ · 🤝 Contribute


⚡ Quick start

Option A — install as a Claude Code plugin (recommended). One command, auto-updating:

/plugin marketplace add frankxai/claude-skills-library
/plugin install claude-skills-library@claude-skills-library

Skills are now discovered automatically and activate when relevant.

Option B — clone and copy the skills you want:

git clone https://github.com/frankxai/claude-skills-library.git ~/claude-skills-library
mkdir -p ~/.claude/skills

# one skill…
cp -r ~/claude-skills-library/free-skills/mcp-architecture ~/.claude/skills/
# …or all of them
cp -r ~/claude-skills-library/free-skills/* ~/.claude/skills/

Some skills are namespaced (e.g. free-skills/anthropic/pdf). Copy the folder that directly contains the SKILL.md you want. Restart Claude Code and the skills are discovered.

Then just work. Skills trigger on their own, or invoke one explicitly:

"Use the greek-philosopher skill to examine my career decision."
"Design an MCP server with the mcp-architecture skill."
"Review this PR with the github-code-review skill."
"Write a Suno prompt for a cinematic trailer track."

🚀 What is this?

A curated, open-source library of Agent Skills — the portable, model-invoked capability format from Anthropic. Drop a skill into your agent and it gains expert knowledge in a domain: it loads automatically when relevant and stays out of the way when it isn't.

Every skill here:

  • ✅ Is a self-contained folder with a SKILL.md and optional references/, scripts/, assets/.
  • ✅ Has spec-compliant frontmatter (name + description) — enforced by scripts/validate_skills.py.
  • ✅ Is progressive-disclosure friendly: a tight description for routing, deep guidance loaded only on use.
  • ✅ Carries a trigger-rich description so the right skill activates from a library of 100+.

107 skills across AI agents, MCP & SDKs, frontend, Oracle/cloud, content & creative production, engineering workflow, and personal performance. All free. MIT-licensed.


⭐ Featured skills

A small taste — see the full catalog for all 107.

SkillWhy you'd reach for itCategory
nextjs-expertApp Router, server/client boundaries, caching, and the production gotchas that biteWeb & Frontend
mcp-architectureDesign an MCP server's resources, tools, prompts, and security from first principlesMCP & SDKs
oracle-database-expertOracle 23ai, Autonomous DB, AI Vector Search, SQL/PLSQL tuning, HAOracle & Cloud
github-code-reviewTurn a raw diff into a correctness/security/style review with actionable commentsEngineering
suno-ai-masteryPrompt-engineer commercial-quality music with Suno v4.5+Creative
ui-ux-design-expertDesign systems, interaction patterns, and WCAG 2.2 accessibility auditsWeb & Frontend
langgraph-patternsGraph orchestration, state machines, and human-in-the-loop for agent workflowsAI Frameworks
greek-philosopherSocratic questioning and Stoic perspective on a hard decisionMind & Body

🗂️ Skill categories

CategoryCountExamples
🤖 AI Agents & Orchestration15agentic-orchestration, swarm-orchestration, model-routing, reasoningbank-intelligence
🔌 AI Frameworks, MCP & SDKs13mcp-architecture, mcp-builder, openai-agentkit, claude-sdk, langgraph-patterns
☁️ Oracle & Cloud8oracle-ai-architect, oracle-database-expert, oci-services-expert, ai-architecture
🎨 Web, Frontend & Animation14nextjs-expert, ui-ux-design-expert, tailwind, gsap, three, framer-expert
🛠️ Engineering Workflow & GitHub9github-code-review, performance-analysis, verification-quality, hooks-automation
✍️ Content, Writing & Brand14brand-voice, book-publishing, social-media-strategy, creator-productivity
🎬 Creative & Media Production22suno-ai-mastery, video-production-workflow, hyperframes-media, higgsfield-soul-id
🧭 Mind, Body & Philosophy5greek-philosopher, spartan-warrior, gym-training-expert, health-nutrition-expert
📄 Documents & Productivity6pdf, docx, pptx, xlsx, product-management-expert, webapp-testing
🧩 Meta & Library1contribute-catalog

Counts are generated from the repo by scripts/generate_catalog.py. See the full catalog for every skill with its description.


🆚 Skills vs. MCP vs. prompts

They solve different problems and compose well together.

A promptAn MCP serverAn Agent Skill
What it isText you pasteA connection to tools/dataA model-invoked capability
Gives the agentInstructions, onceNew actions (APIs, files, DBs)Expert knowledge + workflow
ActivationManual, every timeAlways on once connectedAuto-loads when relevant
Token costPays every turnTool schemas always present~Free until triggered (progressive disclosure)
PortabilityLocked to one chatServer you runA versioned folder, shared across runtimes

Use a skill to teach the agent how to do something well; use MCP to give it access to a system; use a prompt for a one-off. Many skills here pair naturally with an MCP server.


🌐 Works with every runtime

Agent Skills are a portable format. This library documents import paths for the major agentic runtimes:

RuntimeMaturityGuide
Claude Code✅ Nativeruntimes/claude-code.md
Antigravity (agy)✅ Substrate-compatibleruntimes/antigravity.md
OpenCode✅ Adapter patternruntimes/opencode.md
Codex CLI🟡 Per-skill MCP wrapruntimes/codex.md
Gemini CLI🟡 Per-skill templateruntimes/gemini-cli.md
Cursor🟡 Per-skill convertruntimes/cursor.md

See MULTI_RUNTIME.md for the universal-MCP rationale and the full strategy.


🧱 Anatomy of a skill

free-skills/<skill-name>/
├── SKILL.md          # required — frontmatter + instructions
├── references/       # optional — deep docs loaded on demand
├── scripts/          # optional — executable helpers the agent runs
└── assets/           # optional — templates, fonts, icons used in output

Every SKILL.md opens with two-field frontmatter:

---
name: mcp-architecture          # lowercase, hyphenated, ≤ 64 chars
description: Design and implement MCP servers... Use when architecting an MCP server...
---

The description is the most important line you'll write — it's what the model uses to decide when to load the skill. State what it does and when to use it, with trigger keywords.

📐 Authoring standard: spec/README.md · Start here: template/SKILL.md


✅ Quality & validation

A single zero-dependency validator enforces the standard across every SKILL.md:

python3 scripts/validate_skills.py
# OK: 107 skill file(s) are spec-compliant.

python3 scripts/generate_catalog.py          # regenerate docs/CATALOG.md
python3 scripts/generate_catalog.py --check   # CI-friendly drift check
python3 scripts/check_links.py                # verify no broken internal links

All three run automatically on every push and pull request via GitHub Actions.

It verifies that every skill has well-formed UTF-8 frontmatter, a spec-valid name, a non-empty description (≤ 1024 chars), and the exact filename SKILL.md; it also warns on oversized bodies and reserved-word names. Run it before opening a PR.

The browsable catalog at frankxai.github.io/claude-skills-library is generated by scripts/generate_site.py into docs/index.html and served by GitHub Pages (Settings → Pages → Deploy from branch → main / /docs).


❓ FAQ

Does loading 107 skills bloat my context? No. Only each skill's name + description is preloaded for routing; the full body loads only when a skill triggers, and references/ load only when read. That's the whole point of progressive disclosure.

How do skills get picked from a library this large? By the description. Every skill here states what it does and when to use it with explicit trigger keywords, so the model selects the right one. If a skill mis-triggers, sharpen its description — PRs welcome.

Do I have to install all of them? No. Install the plugin for everything, or copy just the folders you want into ~/.claude/skills/.

Is this affiliated with Anthropic? No. It's an independent, MIT-licensed community library built on Anthropic's open Agent Skills format. Some skills under free-skills/anthropic/ are upstream reference skills that retain their original licenses.

Can I use these outside Claude Code? Yes — see runtimes/ for Antigravity, OpenCode, Codex, Gemini CLI, and Cursor.


🤝 Contributing

New skills, deeper examples, fixes, and better docs are all welcome.

  1. Read CONTRIBUTING.md and the authoring standard.
  2. Copy template/ to free-skills/<skill-name>/ and write your SKILL.md.
  3. Run python3 scripts/validate_skills.py and python3 scripts/generate_catalog.py until both are clean.
  4. Open a pull request.

📜 License

MIT — free to use, modify, and distribute. See LICENSE. Skills under free-skills/anthropic/ retain their original upstream licenses (check the folder for a LICENSE.txt).


🙏 Acknowledgments

Built on Anthropic's open Agent Skills standard and Claude Code best practices, with inspiration from the broader open-source skills community (including obra/superpowers) and current, domain-specific research.

⭐ Star the repo · 📚 Catalog · 🐛 Issues · 💬 Discussions

Made for the agentic era.

Ver o original no GitHub

Bom para

Relacionados