sensei SKILL.md skillA

sensei from microsoft/github-copilot-for-azure is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add microsoft/github-copilot-for-azure/sensei@v1.0.6

Pins v1.0.6 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
microsoft/github-copilot-for-azure
Path
.github/skills/sensei/SKILL.md
Versions recorded
5
Latest version
v1.0.6, committed Aug 4, 2026
First version recorded
Apr 2, 2026
Size
3,930 bytes
Repository stars
259
License
a license file GitHub does not identify

Iteratively improve skill frontmatter to achieve good routing test coverage. WHEN: run sensei, sensei help, improve skill routing.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

## 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      ║
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add microsoft/github-copilot-for-azure/sensei@sha256:b030d55d5b1f946a

The line at the top of this page pins the label v1.0.6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_z5crisemxqaln47l.svg)](https://markdownregistry.com/a/art_z5crisemxqaln47l)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Apr 2, 2026 and Aug 4, 2026, about one every 31 days.

versioncommittedcommitsizeaudit
v1.0.6 latest2026-08-04 34ec86d 3,930 BA view · diff
v1.0.62026-07-08 3c97f15 3,910 BA view · diff
v1.0.52026-07-07 aaed099 12,674 BA view · diff
v1.0.52026-04-09 b342c82 12,705 BA view · diff
v1.0.32026-04-02 70c03ac 12,705 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3930 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

microsoft/github-copilot-for-azure · 259 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_z5crisemxqaln47l
GET https://markdownregistry.com/api/v1/resolve?ref=microsoft/github-copilot-for-azure/sensei
GET https://markdownregistry.com/api/v1/blob/b030d55d5b1f946a197788c9a423c15e53d4be7315ee6679948c2754151b2294

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from microsoft/github-copilot-for-azure

analyze-comparison-tests SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/analyze-comparison-tests/SKILL.md · Collects comparison test run artifacts and answers the user's questions based on the trajectories of each run. WHEN TO…
v1.0.0 · audit A · 259 stars
analyze-skill-issues SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/analyze-skill-issues/SKILL.md · Query the integration-test storage account to find why a specific skill's tests are failing. Reads blob-stored test…
v1.0.1 · audit A · 259 stars
analyze-test-run SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/analyze-test-run/SKILL.md · Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues…
v1.0.6 · audit A · 259 stars
file-test-bug SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/file-test-bug/SKILL.md · File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for…
v1.0.0 · audit A · 259 stars
investigate-integration-test SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/investigate-integration-test/SKILL.md · Investigate a failing integration test from a GitHub issue. Downloads logs/artifacts, analyzes the failure, examines…
v1.0.0 · audit A · 259 stars
markdown-token-optimizer SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/markdown-token-optimizer/SKILL.md · Analyzes markdown files for token efficiency. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too…
v1.0.0 · audit A · 259 stars
onboard-plugin SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/onboard-plugin/SKILL.md · Scaffold a new plugin and prepare it for distribution. WHEN: 'create a new plugin', 'scaffold a new plugin'
v1.1.1 · audit A · 259 stars
skill-authoring SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/skill-authoring/SKILL.md · Guidelines for writing Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new…
v1.0.2 · audit A · 259 stars
skill-reviewer SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/skill-reviewer/SKILL.md · Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, and repo…
v1.0.4 · audit A · 259 stars
vally-eval SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/vally-eval/SKILL.md · Author, validate, and run Vally evaluation suites for agent skills. TRIGGERS: create eval, write eval, add eval, run…
v1.1.0 · audit A · 259 stars
aks-cost-optimization SKILL.md skill
microsoft/github-copilot-for-azure · plugins/aks-skills/skills/aks-cost-optimization/SKILL.md · Analyze advanced AKS cost efficiency. WHEN: "AKS NAP readiness", "AKS bin packing", "AKS node scaling bottleneck", "AKS…
v0.0.0-placeholder · audit A · 259 stars
aks-gpu-inference SKILL.md skill
microsoft/github-copilot-for-azure · plugins/aks-skills/skills/aks-gpu-inference/SKILL.md · Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient…
v0.0.0-placeholder · audit A · 259 stars

Every file in microsoft/github-copilot-for-azure

Browse by kind, by grade A, or by owner.