Create, refine, and evaluate AI skills with SKILL.md files.
npx skills add https://github.com/tc9011/my-skills --skill skill-creator-tc9011
Please help me install this Agent Skill. Skill: skill-creator Source: https://github.com/tc9011/my-skills/tree/main/skills/skill-creator Command: npx skills add https://github.com/tc9011/my-skills --skill skill-creator-tc9011
This Skill streamlines the entire process of creating new AI skills, improving existing ones, and rigorously testing their performance, making skill development efficient and effective.
SKILL.md, and structuring skill resources.description field.SKILL.md, create test prompts, run evaluations, analyze the results, and iterate on the skill's logic and description until it performs perfectly.Use the skill-creator to help me build a new skill that can generate commit messages from code changes.
High-intent search queries and answers about installing and using this skill.
To build and test AI skills, you define the skill intent, author the SKILL.md file, structure bundled resources, and run automated evaluation loops to verify performance and refine the logic.
Optimizing skill descriptions for accurate triggering involves running automated evaluation loops that test and refine the description field against performance metrics and qualitative feedback.
Prompt engineering evaluation works by integrating testing frameworks that perform deterministic task verification and collect qualitative feedback to measure and iterate on skill performance.
No specific external testing frameworks are required as dependencies, as the skill integrates internal testing frameworks for deterministic task verification and qualitative feedback collection.
Yes, you can use this tool for iterative improvement of existing AI skills by analyzing evaluation results, collecting user feedback, and refining the skill's logic and descriptions.
Automated evaluation loops streamline skill development by continuously testing deterministic tasks and analyzing performance metrics, which is more efficient and scalable than manual prompt testing.
openakitaCreates and iteratively improves AI skills with quantitative benchmarking.
uzumaki-incMonitor live apps for console errors, performance regressions, and page failures.
codeboltaiCreate and refine Claude skills with structured SKILL.md templates and packaging workflows.
ralphjohn29Create, test, and benchmark custom AI skills with SKILL.md files.