spboyer/sensei
Skill for iteratively improving SKILL.md frontmatter compliance using the Ralph loop pattern
This tool helps AI engineers and prompt engineers refine the descriptive 'frontmatter' for their custom AI agent skills. It takes your existing skill definitions, analyzes them for common issues like missing triggers or brief descriptions, and then iteratively improves the frontmatter so that your AI agents activate the correct skills more reliably. The output is a more robust skill definition that leads to fewer 'skill collisions' and more precise agent behavior.
Use this if you manage or develop AI agents and frequently encounter issues where your agents struggle to choose the right skill for a given user prompt.
Not ideal if you are looking for a tool to develop the core logic or functionality of an AI skill itself, rather than optimizing its descriptive metadata.
Stars
29
Forks
5
Language
TypeScript
License
MIT
Category
Last pushed
Mar 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/spboyer/sensei"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
runkids/skillshare
📚 Sync skills across all AI CLI tools with one command and simplify team sharing. Supporting...
NeuZhou/repo2skill
Convert any GitHub repo into an OpenClaw skill. One command.
samber/cc-skills-golang
🧑🎨 A collection of Golang agentic skills that works
managedcode/dotnet-skills
Installable .NET skill catalog and CLI for Codex, Claude Code, GitHub Copilot, and Gemini.
ivan-magda/claude-superpowers
Personally curated and maintained collection of Claude Code plugins