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
Electron To Electrobun
by ComeOnOliver
Organize
by ComeOnOliver
Utg
by ComeOnOliver
Redis Development
by ComeOnOliver
Remotion
by ComeOnOliver
Laravel Collections
by ComeOnOliver
Laravel Validation
by ComeOnOliver
Accessibility Compliance Accessibility Audit
by ComeOnOliver
Agent Orchestration Improve Agent
by ComeOnOliver
Agent Orchestration Multi Agent Optimize
by ComeOnOliver
Airflow Dag Patterns
by ComeOnOliver
API Testing Observability API Mock
by ComeOnOliver
Application Performance Performance Optimization
by ComeOnOliver
Attack Tree Construction
by ComeOnOliver
Auth Implementation Patterns
by ComeOnOliver
Backend Architect
by ComeOnOliver
Backend Development Feature Development
by ComeOnOliver
Backend Security Coder
by ComeOnOliver
Backtesting Frameworks
by ComeOnOliver
Bash Defensive Patterns
by ComeOnOliver
Bash Pro
by ComeOnOliver
Bats Testing Patterns
by ComeOnOliver
Bazel Build Optimization
by ComeOnOliver
Binary Analysis Patterns
by ComeOnOliver
Blockchain Developer
by ComeOnOliver
Business Analyst
by ComeOnOliver
C Pro
by ComeOnOliver
C4 Architecture C4 Architecture
by ComeOnOliver
C4 Code
by ComeOnOliver
C4 Component
by ComeOnOliver
C4 Container
by ComeOnOliver
C4 Context
by ComeOnOliver
Changelog Automation
by ComeOnOliver
Cicd Automation Workflow Automate
by ComeOnOliver
Cloud Architect
by ComeOnOliver
Code Documentation Code Explain
by ComeOnOliver
Code Documentation Doc Generate
by ComeOnOliver
Code Refactoring Context Restore
by ComeOnOliver
Code Refactoring Refactor Clean
by ComeOnOliver
Code Refactoring Tech Debt
by ComeOnOliver
Code Review AI AI Review
by ComeOnOliver
Code Review Excellence
by ComeOnOliver
Codebase Cleanup Deps Audit
by ComeOnOliver
Codebase Cleanup Refactor Clean
by ComeOnOliver
Competitive Landscape
by ComeOnOliver
Comprehensive Review Full Review
by ComeOnOliver
Comprehensive Review Pr Enhance
by ComeOnOliver
Conductor Implement
by ComeOnOliver
Conductor Manage
by ComeOnOliver
Conductor New Track
by ComeOnOliver
Conductor Revert
by ComeOnOliver
Conductor Setup
by ComeOnOliver
Conductor Status
by ComeOnOliver
Conductor Validator
by ComeOnOliver
Content Marketer
by ComeOnOliver
Context Driven Development
by ComeOnOliver
Context Management Context Save
by ComeOnOliver
Context Manager
by ComeOnOliver
Cost Optimization
by ComeOnOliver
Cpp Pro
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.