PopularFree✓ Official
developmentPopularFree✓ Official
skill-creator
Build and refine custom skills using automated testing, benchmarking, and description optimization for perfect triggering.
12.4kdownloads·110.3kfavorites
A
by anthropicsBuild and refine custom skills using automated testing, benchmarking, and description optimization for perfect triggering.
Building reliable skills often involves tedious manual testing and guesswork around triggering accuracy. You automate the entire lifecycle by drafting SKILL.md files, running parallel evaluations with baselines, and optimizing descriptions for precision. You package complex workflows into reusable, high-performance tools, making this ideal for developers and power users.
Copy the prompt below and paste it into OpenClaw:
Please follow the instructions at https://clawshelf.com/api/skills/anthropics-skill-creator/install to download and install this skill to the local ~/.openclaw/skills/ directory.
Package contents
---
name: skill-creator
description: 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.
---
# 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 and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.
On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.
Of course, you should always No reviews yet. Be the first to review this skill.
100% native OpenClaw / Claude support