Create, modify, and evaluate AI skills with performance benchmarking.
npx skills add https://github.com/Bigme2020/skills-collection --skill skill-creator-bigme2020
Please help me install this Agent Skill. Skill: skill-creator Source: https://github.com/Bigme2020/skills-collection/tree/main/skill-creator Command: npx skills add https://github.com/Bigme2020/skills-collection --skill skill-creator-bigme2020
This Skill streamlines the entire lifecycle of creating and improving AI-powered skills, from initial concept to performance optimization.
SKILL.md, write test cases, run evaluations against a baseline, and iterate on the skill's instructions and description until it performs reliably.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 build an AI skill from scratch, you define the intent, write instructions, and structure resources. You then run evaluations and benchmark performance with variance analysis to iteratively refine the skill's instructions until it performs reliably.
Optimizing AI skill descriptions for triggering accuracy involves targeted prompt engineering and running evaluations. This process enhances skill discoverability and ensures the AI agent activates the correct skill based on user intent and performance metrics.
Iterative development improves prompt engineering by facilitating repeated testing, evaluation, and refinement of AI skills based on performance metrics and user feedback. This cycle ensures continuous performance tuning and reliable skill execution across varying conditions.
Yes, you can benchmark performance with variance analysis on existing AI skills. The skill-creator facilitates modification and performance measurement, allowing you to run evaluations against a baseline and iterate on instructions to achieve reliable functionality.
To draft a new AI skill for summarizing meeting notes, you need an initial concept. The skill-creator guides you through defining intent, writing the SKILL.md instructions, structuring resources, and generating test cases for evaluation.
Modifying existing AI skills through iterative development requires running evaluations against a baseline to measure performance accurately. Without structured test cases and variance analysis, iterative changes may not reliably improve the skill's triggering accuracy or functionality.
cbemisterCreate a git worktree with base-branch detection and plan initialization.
leonvanzylCreate, evaluate, and iterate Claude skills with automated test prompts.
wx-chevalierCreate, test, and optimize AI skills with SKILL.md and evaluation workflows.
z1439527767Evaluate and benchmark LLM agents for reliability and behavioral quality.