Create, refine, and evaluate AI skills with test cases.
npx skills add https://github.com/caoronglin/copaw-skills --skill skill-creator-caoronglin
Please help me install this Agent Skill. Skill: skill-creator Source: https://github.com/caoronglin/copaw-skills/tree/main/skills/skill-creator Command: npx skills add https://github.com/caoronglin/copaw-skills --skill skill-creator-caoronglin
This Skill empowers users to create new AI skills from scratch, improve existing ones based on performance, and rigorously test their functionality and accuracy.
Use the skill creator to start building a new skill for summarizing meeting notes.
High-intent search queries and answers about installing and using this skill.
To create and test AI skills, you define the skill's purpose, triggers, and instructions, then write test cases and run evaluations to analyze execution results. This end-to-end process supports rapid prototyping and robust skill engineering.
Optimizing AI skill descriptions involves fine-tuning the trigger instructions to ensure accurate AI activation. The skill creator evaluates performance metrics from test cases to refine descriptions for better discovery and execution accuracy.
Improving existing AI skills requires iterative refinement based on performance benchmarking. You run test cases to compare skill versions, identify areas for optimization, and refine the logic until execution results meet accuracy standards.
Yes, you can benchmark AI skill versions during development. The skill creator runs designated test cases to compare versions, analyze execution results, and identify specific areas for optimization and iterative improvement.
Prior prompt engineering experience is not strictly required to build AI skills. The skill creator guides users through defining skill logic, writing test cases, and refining instructions, facilitating the end-to-end development lifecycle for rapid prototyping.
alexandrbasisProvide a foundational template for creating new AI skills in Claude Code.
coolbeevipAnalyze feedback and execution logs to propose skill library improvements.
felipesantiago-coderCreate AI skills with structured evaluation and benchmarking workflows for GLM Code.
mneves75Apply Test-Driven Development to create and test AI skills.
