Create, test, and optimize AI skills with SKILL.md files.
npx skills add https://github.com/snhrm/slidini --skill skill-creator-snhrm
Please help me install this Agent Skill. Skill: skill-creator Source: https://github.com/snhrm/slidini/tree/main/.agents/skills/skill-creator Command: npx skills add https://github.com/snhrm/slidini --skill skill-creator-snhrm
This Skill streamlines the entire process of creating and improving AI skills, from initial concept to robust performance testing.
SKILL.md, and structuring skill resources.Use the skill-creator skill to help me create a new skill that summarizes meeting transcripts.
High-intent search queries and answers about installing and using this skill.
You create AI agent skills by defining the intent, writing the SKILL.md file, and structuring resources. The skill-creator guides this process and supports iterative refinement through automated evaluation and performance benchmarking against baselines.
Skill description optimization improves skill triggering accuracy through targeted prompt engineering and evaluation. It ensures your AI skill activates correctly when needed, reducing false triggers and improving overall agent performance in execution environments.
Yes, you can benchmark AI skill performance using automated tests that compare execution results against predefined baselines. This performance analysis runs within integrated AI model execution environments to measure improvements accurately.
The best way to refine prompt engineering is through iterative improvement based on user feedback and performance metrics. Use automated evaluation to identify weaknesses, then apply description tuning to optimize skill triggering and execution.
Yes, skill evaluation integrates with AI model execution environments to generate skills via prompts and analyze performance. This integration is necessary to run the automated tests and benchmarking required for iterative refinement.
unfinishablemapGenerate a publish-ready article draft from a topic prompt.
susomejiasAutomate creation, testing, and optimization of AI agent skills.
spideynoloveEvaluate LLM outputs with automated metrics and human evaluation checklists.
felipesantiago-coderCreate AI skills with structured evaluation and benchmarking workflows for GLM Code.