Sensei

Automates the tedious work of bringing skill frontmatter up to spec using an iterative improvement loop. It scores your skills against the agentskills.io specification, adds WHEN triggers, scaffolds missing tests, validates markdown references, and checks token budgets. The Ralph loop pattern keeps refining until you hit Medium-High compliance with passing tests, then prompts you to commit, skip, or create an issue. Works on single skills, batches, or your entire skill set. The GEPA mode is interesting if you want evolutionary optimization instead of template-based improvements, though it adds complexity. Most useful when you're maintaining a large skill library and want consistent, discoverable frontmatter without manually tracking sixty-word limits and trigger patterns.

Install to Claude Code

npx -y skills add microsoft/github-copilot-for-azure --skill sensei --agent claude-code