skill-creator

Official

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from…

anthropics ↓ 324k
Claude Code
View source ↗

What it does

  • Decide what you want the skill to do and roughly how it should do it
  • Write a draft of the skill
  • Create a few test prompts and run claude-with-access-to-the-skill on them
  • Help the user evaluate the results both qualitatively and quantitatively
  • Use the eval-viewer/generatereview.py script to show the user the results for them to look at, and also let them look at the quantitative metrics
  • Repeat until you're satisfied
  • Expand the test set and try again at larger scale

Requirements & configuration

  • Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead.
  • Baseline run (same prompt, but the baseline depends on context):
  • Note: please use generatereview.py to create the viewer; there's no need to write custom HTML.
  • The "Benchmark" tab shows the stats summary: pass rates, timing, and token usage for each configuration, with per-eval breakdowns and analyst observations.
  • This is the heart of the loop. You've run the test cases, the user has reviewed the results, and now you need to make the skill better based on their feedback.

Configuration: VIEWER_PID

Derived from the skill's own SKILL.md documentation · extracted 2026-07-23

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.

Source

Repository: https://github.com/anthropics/skills

skill-creator FAQ

What does the skill-creator skill do?

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. Decide what you want the skill to do and roughly how it should do it Write a draft of the skill

What does skill-creator require?

Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead. Baseline run (same prompt, but the baseline depends on context): Note: please use generatereview.py to create the viewer; there's no need to write custom HTML. The "Benchmark" tab shows the stats summary: pass rates, timing, and token usage for each configuration, with per-eval breakdowns and analyst observations. This is the heart of the loop. You've run the test cases, the user has reviewed the results, and now you need to make the skill better based on their feedback. Configuration keys: VIEWER_PID.

How do I install skill-creator?

Run: npx -y skills add https://github.com/anthropics/skills --skill skill-creator --agent claude-code — the source lives at github.com/anthropics/skills.

Maintain skill-creator?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

skill-creator on getagentictools
[![skill-creator on getagentictools](https://getagentictools.com/badge/skills/anthropics-skills-skill-creator.svg)](https://getagentictools.com/skills/anthropics-skills-skill-creator?ref=badge)
npx agentictools info skills/anthropics-skills-skill-creator

The second line is the CLI lookup for this page — handy in READMEs and docs.