skill-creator
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.
Profile →npx skills add anthropics/claude-plugins-official --skill skill-creator --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
A skill for creating new skills and iteratively improving them. It guides users through defining the desired capability, drafting the skill, creating test prompts, running Claude with access to the skill, evaluating results, drafting quantitative evals, and rewriting the skill based on feedback. It can also expand the test set and re-run at larger scale. After finishing, it supports using a separate script to optimize triggering descriptions.
How it works
- Decide what the skill should 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 results both qualitatively and quantitatively.
- While runs occur, draft quantitative evals if none exist, or modify existing ones.
- Show results using the
eval-viewer/generate_review.pyscript and let the user see quantitative metrics.
- Rewrite the skill based on user feedback and any glaring flaws from benchmarks.
- Repeat until satisfied, then expand the test set and retry at larger scale.
- When done, run the skill description improver to optimize triggering accuracy.
When to use it
Use when you need to create a new skill, edit an existing one, run evaluations to test it, benchmark performance with variance analysis, or optimize the triggering description for better accuracy.
What it can touch
- Tools:
claude-code(declared tool). - It references the
eval-viewer/generate_review.pyscript to display results and metrics. - It mentions spawning with-skill and baseline runs, snapshotting old skill versions, and saving outputs in a structured workspace (iteration-based) during evaluation workflows.
Caveats
- The workflow emphasizes iterative evaluation and explicit branching between with-skill and baseline runs.
- The guidance for evaluating results relies on creating and updating a JSON evals structure and using a grader and analyzer in subsequent steps.
- It requires access to scripts like
eval-viewer/generate_review.pyand a benchmarking/aggregation process to producebenchmark.jsonandbenchmark.md.
# Skill Creator A skill for creating new skills and iteratively improving them. At a high level, the process of creating a skill goes like this: - 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 - While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist) - Use the `eval-viewer/generate_review.py` script to show the user the results for them to look at, and also let them look at the quantitative metrics - Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks) - Repeat until you're satisfied - Expand the test set and try again at larger scale Your job when using this skill is to figure out where the user is in this process and then jump in
- Communicating with the user
- Creating a skill
- Capture Intent
- Interview and Research
- Write the SKILL.md
- Skill Writing Guide
- Writing Style
- Test Cases
- Running and evaluating test cases
- Step 1: Spawn all runs (with-skill AND baseline) in the same turn
- Step 2: While runs are in progress, draft assertions
- Step 3: As runs complete, capture timing data
- Step 4: Grade, aggregate, and launch the viewer
- What the user sees in the viewer
python -m scripts.aggregate_benchmark <workspace>/iteration-N --skill-name <name> nohup python <skill-creator-path>/eval-viewer/generate_review.py \ kill $VIEWER_PID 2>/dev/null python -m scripts.run_loop \ python -m scripts.package_skill <path/to/skill-folder>
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.
How do I install it?
Run `npx skills add anthropics/claude-plugins-official --skill skill-creator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From anthropics/claude-plugins-official, a repository with 33,027 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.