skill-creator
Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.
npx skills add feiskyer/claude-code-settings --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
Aimed at creating new skills and iteratively improving them, this skill walks the user through planning, drafting, testing with prompts, and evaluating results. It supports evaluating both qualitative and quantitative outcomes, using an eval-viewer script to display results and metrics, and prompts the user to rewrite the skill based on feedback. It also covers expanding the test set and re-running at larger scales, and suggests using a separate script to improve trigger descriptions after the skill is completed.
How it works
- Decide what the skill should do and draft a plan for how it should operate.
- Write a draft of the skill.
- Create several test prompts and run the agent with the skill loaded on them.
- Help the user evaluate results qualitatively and quantitatively.
- While runs happen, draft quantitative evals if none exist, or modify existing ones as needed, and explain them to the user.
- Use the
eval-viewer/generate_review.pyscript to show results and metrics.
- Rewrite the skill based on user feedback and evident flaws from benchmarks.
- Repeat until satisfied; expand the test set and re-run at larger scale.
- If desired, run the skill description improver to optimize triggering.
When to use it
Use when creating a new skill, updating an existing one, running evaluations, checking trigger quality, or improving a skill description. It is applicable whether starting from a draft or continuing from an existing draft.
What it can touch
The workflow references the following: eval-viewer/generate_review.py script for results display, and various testing prompts and evaluation steps. The skill guides how to run tests, collect outputs, and present metrics, but specific touch points depend on the user's current stage in the process.
Caveats
The description emphasizes iterative refinement and evaluation, but does not guarantee outcomes. It instructs producing both qualitative and quantitative assessments and expanding tests, and relies on user feedback to drive rewrites. The content does not specify licensing beyond the repository context, and it assumes the user has access to the eval-viewer/generate_review.py script and related evaluation tooling.
# 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 the agent with the skill loaded 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, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.
How do I install it?
Run `npx skills add feiskyer/claude-code-settings --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 feiskyer/claude-code-settings, a repository with 1,619 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.