skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update 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.
npx skills add hAcKlyc/MyAgents --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
Helps create new skills and iteratively improve them. Guides the user through drafting a skill, creating test prompts, running evals with Claude (via claude-with-access-to-the-skill), evaluating results both qualitatively and quantitatively, and rewriting the skill based on feedback. It also supports expanding the test set and re-running at larger scale, including a subsequent step to optimize the triggering description.
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 happen, draft quantitative evals if none exist, or modify existing ones as needed, then explain them to the user.
- Use the
eval-viewer/generate_review.pyscript to show results and the quantitative metrics.
- Rewrite the skill based on user evaluation feedback and any glaring flaws from benchmarks.
- Repeat until content with results.
- Expand the test set and run again at larger scale.
Your job is to identify the user’s stage in this process and intervene to move them forward, whether drafting, writing test cases, specifying evaluation criteria, running prompts, or iterating the skill. After completion, you can also run the separate script to optimize the triggering description of the skill.
When to use it
Use when a user wants to create a skill from scratch, update or optimize an existing skill, run evaluations to test a skill, benchmark performance with variance analysis, or optimize the skill’s description for triggering accuracy. The workflow covers drafting, testing, evaluating, rewriting, and scaling tests.
What it can touch
The process involves running external scripts and tools, notably:
claude-with-access-to-the-skillfor evaluation promptseval-viewer/generate_review.pyto display results and metrics- evaluation prompts and test prompts managed within the workspace
Caveats
The workflow relies on executing multiple runs and generating quantitative/evaluation data. It mentions creating and editing tests, snapshots, and benchmarking outputs, but does not guarantee specific outcomes. It includes guidance to spawn with-skill and baseline runs, generate and store timing data, and use grading and aggregation scripts to produce benchmark results. It recommends using a viewer for results and feedback, and provides steps for handling headless environments. No guarantees on performance improvements are stated; outcomes depend on user-driven iterations and evaluation results.
# 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, update 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 hAcKlyc/MyAgents --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 hAcKlyc/MyAgents, a repository with 795 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.