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.
npx skills add guanyang/open-agent-hub --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
The skill facilitates creating new skills, modifying and improving existing ones, and measuring skill performance. It supports workflows for drafting a skill, running test prompts with Claude Code access to the skill, evaluating results both qualitatively and quantitatively, and iterating based on feedback. It can trigger evaluation and benchmarking processes, draft and present quantitative metrics, and guide rewriting the skill based on user feedback. It also includes an optional step to optimize a skill's triggering description after completion.
How it works
- Start by understanding the user's intent to capture a skill goal and desired outputs.
- Draft the skill and create test prompts. Adjust prompts and test cases as needed.
- Use Claude with access to the skill to run tests on the prompts.
- While runs proceed, draft quantitative evals and explain them to the user. Use the eval-viewer/generate_review.py script to present results and metrics.
- Rewrite the skill according to user feedback and observed flaws from benchmarks.
- Repeat the cycle until the user is satisfied, then optionally run a separate script to optimize the triggering description.
- For testing, generate and manage evals.json style entries and store results in a structured workspace with iteration and eval subfolders; spawn both with-skill and baseline runs for each test case.
When to use it
Use when a user wants to create a skill from scratch, edit or optimize an existing skill, or run evaluations and benchmarks to measure performance and triggering accuracy. Also use when expanding the test set and retesting at larger scale.
What it can touch
- It references the eval-viewer/generate_review.py script to show results.
- It operates with the workflow of spawning with-skill and baseline runs, and saving outputs to a workspace structure (iteration-<N>/eval-<ID>/with_skill/outputs/ and without_skill/outputs/).
- It uses a JSON structure for eval metadata and results, and can snapshot skills for baseline comparisons.
Caveats
- The description does not specify any license restrictions beyond the repository’s MIT license for the overall project.
- It relies on external scripts (eval-viewer/generate_review.py) and a particular workspace organization to function correctly.
- The process assumes the user understands evaluation concepts and can interpret qualitative and quantitative results in the viewer.
# 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 guanyang/open-agent-hub --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 guanyang/open-agent-hub, a repository with 940 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.