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.