Individual skill
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.
skills/skill-creator/SKILL.md
Source commit 95dab59a62b2031adcb7abf25ae0a60b8a13fdb2
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 3, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,675
- Repository last updated
- Nov 5, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agentic-ai Repository topic
- ai Repository topic
- claude-code Repository topic
- vibe-coding Repository topic
- agents Repository topic
- copilot Repository topic
- litellm Repository topic
- codex Repository topic
- claude-skills Repository topic
- claude-code-agents Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
LICENSE.txtdoc · 11,357 bytesREADME.mddoc · 462 bytesSKILL.mdcore · 30,672 bytesSKILL.mdcore · 30,672 bytesSKILL.mdcore · 30,672 bytesSKILL.mdcore · 30,672 bytesSKILL.mdcore · 30,672 bytesSKILL.mdcore · 30,672 bytesagents/analyzer.mddoc · 10,673 bytesagents/comparator.mddoc · 7,092 bytesagents/grader.mddoc · 9,276 bytesassets/eval_review.htmlasset · 7,058 byteseval-viewer/generate_review.pyruns · 16,365 byteseval-viewer/viewer.htmlasset · 44,998 bytesreferences/schemas.mddoc · 11,910 bytesscripts/__init__.pyruns · 0 bytesscripts/aggregate_benchmark.pyruns · 14,825 bytesscripts/generate_report.pyruns · 13,265 bytesscripts/improve_description.pyruns · 16,557 bytesscripts/package_skill.pyruns · 4,207 bytesscripts/platforms/__init__.pyruns · 54 bytesscripts/platforms/base.pyruns · 2,260 bytesscripts/platforms/claude_code.pyruns · 6,428 bytesscripts/platforms/codex.pyruns · 5,545 bytesscripts/platforms/openclaw.pyruns · 4,445 bytesscripts/quick_validate.pyruns · 9,840 bytesscripts/run_eval.pyruns · 8,400 bytesscripts/run_loop.pyruns · 15,323 bytesscripts/utils.pyruns · 3,447 bytes
Read excerpt
# 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