Create and modify AI skills with SKILL.md files and iterative testing.
npx skills add https://github.com/huynguyenh/skills --skill hnh-create-skill
Please help me install this Agent Skill. Skill: hnh-create-skill Source: https://github.com/huynguyenh/skills/tree/main/skills/hnh-create-skill Command: npx skills add https://github.com/huynguyenh/skills --skill hnh-create-skill
This Skill streamlines the entire process of creating new AI skills, improving existing ones, and measuring their performance, making AI development accessible and efficient.
SKILL.md, and structuring skill components.SKILL.md, create test prompts, run evaluations, and iterate on the description until it triggers reliably.Use the hnh-create-skill to help me create a new skill that summarizes code documentation.
High-intent search queries and answers about installing and using this skill.
To create a new AI skill, define the skill intent, write the SKILL.md file, and structure components like agents and scripts. This skill guides you through the entire creation process to ensure proper formatting and functionality.
Evaluating AI skill performance involves running automated tests and benchmarks to quantify accuracy and efficiency. You can iterate on the description optimization to improve triggering accuracy based on test case evaluations and user feedback.
Yes, you can modify and improve existing AI skills through iterative refinement. The skill facilitates improvements based on test case evaluations and user feedback to enhance overall performance and reliability.
Structuring SKILL.md files involves defining the skill intent clearly, while component scripts handle specific agentic tasks. This skill provides guidance on organizing these elements effectively for optimal prompt engineering and code generation outcomes.
If your AI skill fails to trigger reliably, the description likely needs optimization. Use this skill to run iterative testing and benchmarking, then refine the description based on evaluations until it triggers accurately.
avCreate, edit, and optimize custom AI skills with SKILL.md files.
uzumaki-incMonitor live apps for console errors, performance regressions, and page failures.
devCharuzuDesign prompts and evaluation frameworks for LLM workflows.
pingdiorScore structural prompts on a 1–10 rubric with targeted feedback.