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.
- installs
- 1K
- GitHub stars
- 217
- last updated
- Jun 11, 2026
Install
$ npx -y skills add microsoft/github-copilot-for-azure --skill sensei --agent claude-codeInstalls into .claude/skills of the current project.
Files
Help
When user says "sensei help" or asks how to use sensei, show this:
╔══════════════════════════════════════════════════════════════════╗
║ SENSEI - Skill Frontmatter Compliance Improver ║
╠══════════════════════════════════════════════════════════════════╣
║ ║
║ USAGE: ║
║ Run sensei on <skill-name> # Single skill ║
║ Run sensei on <skill1>, <skill2>, ... # Multiple skills ║
║ Run sensei on all skills # All skills ║
║ ║
║ EXAMPLES: ║
║ Run sensei on appinsights-instrumentation ║
║ Run sensei on azure-ai, azure-compute ║
║ ║
║ WHAT IT DOES: ║
║ 1. READ - Load skill's SKILL.md and tests ║
║ 2. VERIFY - Compare skill frontmatter with convention ║
║ 3. SCAFFOLD - Create tests from frontmatter if missing ║
║ 4. IMPROVE - Add WHEN: triggers ║
║ 5. TEST - Run tests, fix if needed ║
║ 6. SUMMARY - Show before/after with suggestions ║
║ 7. PROMPT - Ask: Commit, Create Issue, or Skip? ║
║ 8. REPEAT - Until routing tests pass ║
╚══════════════════════════════════════════════════════════════════╝
Main Loop
For each skill, execute this loop until the frontmatter aligns with convention, have thorough routing tests AND routing tests pass:
- READ - Load
plugins/{plugin}/skills/{skill-name}/SKILL.md, and vally eval suites inevals/{skill-name}/*.yaml. - VERIFY - Compare the skill frontmatter with conventions in CONVENTIONS. If the skill's frontmatter violates any written convention, notify the user and propose a fix to align the frontmatter with the convention.
- SCAFFOLD - If
evals/{skill-name}/doesn't exist, follow instructions invally-evalskill to scaffold a set of routing tests. The routing tests test if the skill can be invoked for target user prompts. Generate user prompts that match the target scenario of the skill's description. - IMPROVE - If the skill description doesn't already have WHEN: triggers, add them.
- TEST - Follow instructions in
vally-evalskill to run the routing tests. If there are failed tests, suggest fixes. - SUMMARY - Display before/after comparison with unimplemented suggestions.
- PROMPT - Ask user to commit the fixes or take any alternative actions.
- REPEAT - Go to step 2 (max 5 iterations per skill)
Constraints
- Only modify
plugins/{plugin}/skills/- these are the Azure skills used by Copilot - Files in
.github/skills/should be left as is - Max 5 iterations per skill before moving on
Related Skills
- vally-eval - vally eval suite writing guidelines
Sponsors
Details
- Repository
- github.com/microsoft/github-copilot-for-azure
- Categories
- Testing & QA, Git & Pull Requests, AI & Agent Building, Debugging, Automation & Workflows, Cloud & Infrastructure, CLI & Terminal
- First seen
- Apr 16, 2026
