Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 961 files from 2 125 authors, of which 68 678 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
68 678
unique skills
out of 86 961 files found on GitHub
18 283
are copies
same content, someone else's repository
1 749
tokens, median
what a typical skill costs you in context
8 467
name collisions
two skills with one name cannot sit side by side
Cqrs Implementation
by ComeOnOliver
Csharp Pro
by ComeOnOliver
Customer Support
by ComeOnOliver
Data Engineer
by ComeOnOliver
Data Engineering Data Driven Feature
by ComeOnOliver
Data Engineering Data Pipeline
by ComeOnOliver
Data Quality Frameworks
by ComeOnOliver
Data Scientist
by ComeOnOliver
Data Storytelling
by ComeOnOliver
Database Admin
by ComeOnOliver
Database Architect
by ComeOnOliver
Database Cloud Optimization Cost Optimize
by ComeOnOliver
Database Migration
by ComeOnOliver
Database Migrations Migration Observability
by ComeOnOliver
Database Migrations SQL Migrations
by ComeOnOliver
Database Optimizer
by ComeOnOliver
Dbt Transformation Patterns
by ComeOnOliver
Debugger
by ComeOnOliver
Debugging Strategies
by ComeOnOliver
Debugging Toolkit Smart Debug
by ComeOnOliver
Dependency Management Deps Audit
by ComeOnOliver
Dependency Upgrade
by ComeOnOliver
Deployment Engineer
by ComeOnOliver
Deployment Pipeline Design
by ComeOnOliver
Deployment Validation Config Validate
by ComeOnOliver
Devops Troubleshooter
by ComeOnOliver
Distributed Debugging Debug Trace
by ComeOnOliver
Distributed Tracing
by ComeOnOliver
Django Pro
by ComeOnOliver
Docs Architect
by ComeOnOliver
Dotnet Architect
by ComeOnOliver
Dotnet Backend Patterns
by ComeOnOliver
Dx Optimizer
by ComeOnOliver
E2e Testing Patterns
by ComeOnOliver
Elixir Pro
by ComeOnOliver
Embedding Strategies
by ComeOnOliver
Error Debugging Error Analysis
by ComeOnOliver
Error Debugging Error Trace
by ComeOnOliver
Error Debugging Multi Agent Review
by ComeOnOliver
Error Detective
by ComeOnOliver
Error Diagnostics Error Trace
by ComeOnOliver
Error Diagnostics Smart Debug
by ComeOnOliver
Error Handling Patterns
by ComeOnOliver
Event Sourcing Architect
by ComeOnOliver
Event Store Design
by ComeOnOliver
Fastapi Pro
by ComeOnOliver
Firmware Analyst
by ComeOnOliver
Flutter Expert
by ComeOnOliver
Framework Migration Code Migrate
by ComeOnOliver
Framework Migration Deps Upgrade
by ComeOnOliver
Framework Migration Legacy Modernize
by ComeOnOliver
Frontend Developer
by ComeOnOliver
Frontend Mobile Development Component Scaffold
by ComeOnOliver
Frontend Mobile Security Xss Scan
by ComeOnOliver
Frontend Security Coder
by ComeOnOliver
Full Stack Orchestration Full Stack Feature
by ComeOnOliver
Gdpr Data Handling
by ComeOnOliver
Git Advanced Workflows
by ComeOnOliver
Git Pr Workflows Git Workflow
by ComeOnOliver
Git Pr Workflows Onboard
by ComeOnOliver
Claude Skills — questions
Answers built from the skills we actually parsed.
What is a Claude Skill?
A folder with a SKILL.md file: instructions that teach an agent to do one thing well, optionally with scripts and reference files alongside. The format is open and called Agent Skills — Claude Code, Codex and other agents read the same files. It is not a program you run; it is knowledge the agent loads when the task calls for it.
How is a skill different from an MCP server?
A server gives the agent new abilities — it connects to something and exposes tools. A skill gives the agent knowledge: how to use what it already has. They combine, and often literally: 13 478 of the skills here declare which MCP servers they need to work.
Why are there fewer skills here than in other catalogues?
Because we deduplicate by content. Of 86 961 files found on GitHub, 68 678 are unique — the rest is the same skill copied into someone else's repository, word for word. Catalogues that count files rather than skills show every copy as a separate entry.
What does the token count mean?
A skill is loaded in stages. Its name and description stay in the model's context all the time; the body of SKILL.md is read when the skill is used; other files in the folder, such as references, scripts and fonts, are opened only when the skill asks for them. The number we show is SKILL.md, the part every use pays for. A big folder is not a big cost: one official skill ships 83 font files, and none of them ever enters the context.
How do I install a skill?
Copy the skill folder into ~/.claude/skills for personal use, or into .claude/skills inside a project. The agent picks it up by the name in the SKILL.md header — which is worth checking: 8 467 skills here share a name with another skill, and two of them cannot sit side by side.