Author SKILL.md files, run trigger evaluations, and optimize descriptions.
npx skills add https://github.com/samurano/ai-brain --skill skill-creator-samurano
Please help me install this Agent Skill. Skill: skill-creator Source: https://github.com/samurano/ai-brain/tree/main/.agents/skills/skill-creator Command: npx skills add https://github.com/samurano/ai-brain --skill skill-creator-samurano
The Skill Creator provides an end-to-end workflow for building AI skills: drafting SKILL.md, defining evaluation prompts, running trigger evaluations, analyzing results, and iterating to improve performance and clarity. It codifies the process so teams can produce reliable, reusable skills that trigger reliably across contexts.
Draft a new skill by outlining its goal and triggers, create its SKILL.md, run an initial evaluation, and iterate based on the results.
High-intent search queries and answers about installing and using this skill.
To create and iterate AI skills, draft a SKILL.md file defining triggers and goals, run trigger evaluations, analyze benchmark results, and refine the description to improve invocation accuracy.
Evaluating and benchmarking prompt-engineering skills involves generating evaluation sets, running triggers against multiple backends, recording results, and producing benchmark summaries to track performance across iterations.
You can optimize skill triggers by automatically refining the triggering description within the SKILL.md frontmatter, testing it against generated evaluation prompts, and iterating based on benchmark summaries.
Yes, you can package completed AI skills into portable artifacts and reuse components across different projects, ensuring reliable and consistent skill triggers throughout your team's workflow.
You track regression and performance history by recording evaluation results across iterations, allowing the system to surface insights on when changes help or hurt the skill's overall clarity and performance.
yangliu2060Extract YouTube transcripts and captions into structured summaries with key points.
ClyptAIMonitor live deployments for errors and performance regressions.
Nuwanda04Analyze prompts, evaluate RAG systems, and design agentic workflows.
luminos-accessibilityCreate, modify, and evaluate Claude Skills with SKILL.md and benchmarking workflows.
