Create, modify, and evaluate AI skills with SKILL.md drafting and test cases.
npx skills add https://github.com/cuozg/oh-my-skills --skill skill-creator-cuozg
Please help me install this Agent Skill. Skill: skill-creator Source: https://github.com/cuozg/oh-my-skills/tree/main/skills/skill-creator Command: npx skills add https://github.com/cuozg/oh-my-skills --skill skill-creator-cuozg
This Skill streamlines the entire lifecycle of creating and improving AI skills, from initial concept to performance optimization, reducing the complexity and time required for skill development.
SKILL.md, and structuring skill resources.description field.SKILL.md, set up test cases, run evaluations against baseline performance, and iterate on the skill's description for optimal triggering.Use the skill-creator to help me draft a new skill that can summarize markdown files.
High-intent search queries and answers about installing and using this skill.
To create and test an AI agent skill, you define the skill intent, draft the SKILL.md file, generate test cases, and run evaluations against baselines. This skill guides the process while providing iterative feedback loops for refinement.
The best way to optimize AI skill descriptions for triggering accuracy is to automatically test and refine the description field against performance metrics. This skill evaluates triggering behavior and iteratively updates the text for optimal accuracy.
Performance evaluation for prompt engineering skills works by generating test cases, running evaluations with baselines, and analyzing results via a viewer. This allows you to measure outputs against baseline performance and iterate on the skill logic.
Yes, you can use this skill development workflow for an existing SKILL.md file to modify and improve your current skills. It supports iterative improvement by facilitating testing, evaluation, and refinement based on performance metrics and user feedback.
You need testing frameworks to evaluate your AI skills, as this skill integrates with them to run evaluations and analyze results. It leverages these frameworks to generate test cases and provide iterative feedback loops for skill refinement.
You should not use an automated skill evaluation workflow if your task lacks clear intent or baseline metrics for comparison. This workflow relies on generating test cases and running evaluations against baselines to provide meaningful iterative feedback.
tnezInitialize the .docent directory structure and configuration for new projects.
iliaalRefine vague prompts into structured AI instructions with validation.
NicolasPadovamDevelop, evaluate, and optimize custom agent skills within the Opensquad framework.
coreyjaDraft SKILL.md frontmatter and structure guidance for Claude Code skills.