$ loading_
Iteratively audit and fix skill frontmatter compliance, scoring, and token issues.
The material indicates a workflow-style prompt/document skill for improving skill frontmatter, with no required secrets and no declared remote endpoints, so overall risk is low. Caution is still warranted because the description mentions reading skill files, creating tests, and invoking test runners and git commands, which may imply local execution and file modifications in practice.
The material explicitly states that no keys or environment variables are required, and it does not request API tokens, account credentials, or other sensitive authentication data, so credential exposure appears limited.
No remote endpoints are declared, and the system checks do not show outbound connectivity configuration; based on the material, it appears to be a local prompt/workflow artifact with no factual indication of sending user data to third-party services.
The description explicitly says it invokes token counting tools, test runners, and git commands, and includes steps such as creating tests, running tests, and fixing issues; this implies potential local command execution or repository operations. This is a normal tool capability, but execution scope should be constrained.
The README indicates it reads SKILL.md, test files, and token counts, and may add or modify tests and frontmatter; there is no evidence of excessive access beyond the skill repository, but local file read/write is clearly possible.
The source is a Microsoft-associated open-source GitHub repository with auditable code and some community adoption (222 stars); although the license is not stated and maintenance status is unknown, the available positive provenance signals keep supply-chain risk low.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "sensei" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/GitHub-Copilot-for-Azure/main/.github/skills/sensei/SKILL.md 2. Save it as ~/.claude/skills/sensei/SKILL.md 3. Reload skills and tell me it's ready
Run sensei to check whether this skill's frontmatter is compliant, identify missing fields, formatting issues, and token limit risks, then suggest fixes.
A compliance report with issue list, scoring or risk notes, and actionable fix recommendations.
Use sensei to improve this skill's frontmatter: fix formatting and field issues, try to pass tests, and summarize what you changed.
Updated frontmatter, test results, and a summary of the changes made.
Run sensei to evaluate this skill's token usage and overall quality score, identify redundant content, and propose a trimming plan.
Token counts, quality evaluation, redundancy analysis, and optimization suggestions for a leaner version.
"A true master teaches not by telling, but by refining." - The Skill Sensei
Automates skill frontmatter improvement using the Ralph loop pattern - iteratively improving skills until they reach Medium-High compliance with passing tests, then checking token usage and prompting for action.
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 <skill-name> --skip-integration # Fast mode ║
║ Run sensei on <skill1>, <skill2>, ... # Multiple skills ║
║ Run sensei on all Low-adherence skills # Batch by score ║
║ Run sensei on all skills # All skills ║
║ ║
║ EXAMPLES: ║
║ Run sensei on appinsights-instrumentation ║
║ Run sensei on azure-security --skip-integration ║
║ Run sensei on azure-security, azure-observability ║
║ Run sensei on all Low-adherence skills ║
║ ║
║ WHAT IT DOES: ║
║ 1. READ - Load skill's SKILL.md, tests, and token count ║
║ 2. SCORE - Check compliance (Low/Medium/Medium-High/High) ║
║ 3. SCAFFOLD - Create tests from template if missing ║
║ 4. IMPROVE - Add WHEN: triggers (cross-model optimized) ║
║ 5. TEST - Run tests, fix if needed ║
║ 6. REFERENCES- Validate markdown links ║
║ 7. TOKENS - Check token budget, gather suggestions ║
║ 8. SUMMARY - Show before/after with suggestions ║
║ 9. PROMPT - Ask: Commit, Create Issue, or Skip? ║
║ 10. REPEAT - Until Medium-High score + tests pass ║
║ ║
║ TARGET SCORE: Medium-High ║
║ ✓ Description > 150 chars, ≤ 60 words ║
║ ✓ Has "WHEN:" trigger phrases (preferred) ║
║ ✓ No "DO NOT USE FOR:" (unless disambiguation-critical) ║
║ ✓ SKILL.md < 500 tokens (soft limit) ║
║ ║
║ MORE INFO: ║
║ See .github/skills/sensei/README.md for full documentation ║
║ ║
╚══════════════════════════════════════════════════════════════════╝
Run sensei on azure-deploy
Run sensei on azure-security, azure-observability
Run sensei on all Low-adherence skills
Run sensei on all skills
Run sensei on my-skill --gepa
Run sensei on my-skill --gepa --skip-integration
Run sensei on all skills --gepa
When --gepa is used, Step 5 (IMPROVE) is replaced with GEPA evolutionary optimization.
Instead of template-based improvements, GEPA parses trigger prompt arrays from the existing
…
Set up Entra ID app registration, OAuth, permissions, and MSAL integration.
Set up Azure Application Insights telemetry for web apps with best practices.
Troubleshoot Azure Event Hubs and Service Bus SDK connection and messaging issues.
Find, list, and inspect Azure resources across subscriptions and resource groups.
Deploy, evaluate, fine-tune, and optimize Microsoft Foundry agents and models.
Deploy prepared Azure apps with built-in recovery for common release errors.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Review skill PRs with severity-rated feedback on quality and repository conventions.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Turn a repeated workflow into a reusable skill file from the current session.
Generate test scenarios and measure how well agents follow skills and rules.
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.