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. 79 566 files from 1 758 authors, of which 61 913 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.

61 913

unique skills

out of 79 566 files found on GitHub

17 653

are copies

same content, someone else's repository

1 739

tokens, median

what a typical skill costs you in context

7 886

name collisions

two skills with one name cannot sit side by side

46 261–46 320 of 61 913

page 772 of 1 032

Sort Most copied

Planning And Task Breakdown

Radix UI Design System

Receiving Code Review

Skill Technical Document

by tranhieutt

4k tokens

Source Driven Development

by tranhieutt

2k tokens

Spec Driven Development

Subagent Driven Development

Test Driven Development

Vector Database Engineer

by tranhieutt

701 tokens

Verification Before Completion

Forward Deployed Selling

by vonarmen-wq

Operating doctrine for AI-era enterprise sales. Use when an agent works on accounts, deals, outreach, coaching, or pipeline — any revenue-affecting decision.

550k tokens

Create Kr Patch

by mcpads

>- Use when working on a Korean (Hangul) fan translation of a retro console or PC game — ROM or disc images, text-engine reverse engineering, Hangul fonts and custom encodings, script extraction or reinsertion, code hooks, patch builds, or emulator verification. 레트로 게임 한글화·한글 패치·ROM 번역의 신규 조사와 기존 프로젝트 후속 작업에 사용한다.

75k tokens

Kp Applied Domain

by Tibsfox

Domain knowledge for 10 applied subjects: computer science, data science, world languages, psychology, environmental science, nutrition, economics, creative writing, logic, digital literacy. Use when generating Applied & Practical tier pack content.

881 tokens

Kp Content Authoring

by Tibsfox

Generates knowledge pack content suites: vision documents, modules YAML, activities JSON, assessment frameworks, resource catalogs, and .skillmeta files. Shared by all 3 tier-specific author agents. Use when creating or updating pack content files.

1k tokens

Aminet Browser

by Tibsfox

Aminet search and browse: full-text search, category tree navigation, architecture filtering, package detail, and curated collections. Use when searching, browsing, or managing package collections.

994 tokens

Aminet Installer

by Tibsfox

Aminet package installation: LhA/LZX extraction, Amiga filesystem mapping, dependency detection, install tracking, and scan gate enforcement. Use when installing, extracting, or uninstalling Amiga packages.

1k tokens

Aminet Emulator

by Tibsfox

FS-UAE emulator configuration and launch: hardware profiles, ROM management, WHDLoad integration, config generation, and state snapshots. Use when configuring emulation, managing ROMs, or launching Amiga software.

1k tokens

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: 11 350 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 79 566 files found on GitHub, 61 913 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 into the model's context when it is used, so its size is a running cost on every request that touches it. We measure the whole folder, not just SKILL.md: one official skill is 377 tokens, another drags 83 files of fonts behind it.

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: 7 886 skills here share a name with another skill, and two of them cannot sit side by side.