About
About Claude Skills
An independent library of Claude Code skills written to one standard: specific enough that the agent behaves like a careful senior engineer, and transparent enough that you can read every line before installing.
Why this exists
Agent Skills are the most efficient way to give Claude Code durable expertise: a short description sits in context, and the full procedure loads only when a task needs it. Most skills published so far are either very narrow or a few paragraphs of generic advice that Claude would follow anyway. This directory collects 504 skills that try to encode what an experienced practitioner actually does — the order of operations, the thresholds, the traps and the check at the end.
Editorial standards
Every skill is held to the same written specification before it is published:
- Selective description. The frontmatter says what the skill does and lists the concrete situations that should trigger it, so it loads for the right requests and stays out of the way otherwise.
- Procedure over prose. A numbered workflow, decision tables for real forks, and exact commands or configuration for current stable tool versions.
- Pitfalls and verification. Each skill names the mistakes that cause production incidents and ends with how to prove the work is correct.
- Safety. Destructive operations require explicit confirmation inside the workflow. Security skills cover defensive work and explicitly authorized testing only.
- Portability. Only standard frontmatter fields (
name,description,license) are used, so a skill works in Claude Code, on Claude.ai and through the Skills API. See the Agent Skills specification. - Full transparency. Each page renders the complete
SKILL.mdand every bundled script or reference file. The downloadable zip contains exactly those files.
Skills are drafted with AI assistance and edited against this specification. Tools and APIs change; if a command or version in a skill is out of date, please report it and it will be corrected.
Licensing
All skills are released under the MIT license. You may use, modify and redistribute them, including inside commercial products and private plugin marketplaces, provided the license notice is kept.
Corrections and contact
Found an error, a broken command or a skill that triggers when it should not? Email [email protected] with the skill name and what you expected. Corrections are prioritised over new skills.
Independence
Claude Skills is an independent, community-run directory. It is not affiliated with, endorsed by, or sponsored by Anthropic. "Claude" and "Claude Code" are trademarks of Anthropic, PBC, used here only to describe the tool these skills are written for. For authoritative product behaviour, consult the official Claude Code skills documentation.