curl -fsSL https://api.cheatcodehq.com/install.sh | sh -s -- anthropic-skill-creator --to allCopies 1 skill into each app's skills folder (Claude Code: ~/.claude/skills), after checking every file against anthropics/skills at commit 3337550. Nothing else on your computer changes. To undo it, run the terminal command with --uninstall at the end; that also removes what the app added.
Then start a new session in your AI app and ask for the work in plain words; it picks the skill from its description. In Claude Code you can also type /anthropic-skill-creator:skill-creator.
See it in use
After installing, start a new session and say: I do this task the same way every week; my notes are in how-i-do-it.md. Turn it into a skill and save it as my-skill/SKILL.md, with two test requests I can try.
What else it can do, and its limits
- One skill for making skills: turns a workflow you describe into a SKILL.md with a name, a description that tells Claude when to use it, steps and rules
- Improves an existing skill and rewrites its description so Claude picks it up at the right moments
- Writes test requests and checks for them, and can compare results with and without the skill
- Running tests side by side, the review page, benchmarks and packaging use its Python scripts, which need a terminal and Claude Code
- Asks about edge cases first unless you tell it not to, and you review the skill it writes
Sample input Recorded Oct 24, 2026 in Claude Code 2.1.308 with Sonnet 5.5. The video replays that session; nothing in it was acted or edited.
What's inside 1 skill
skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
About
Public repository for Agent Skills
Something wrong with this listing, or it did not install? Tell us