Official agent skill

Sensei

by microsoft in microsoft/GitHub-Copilot-for-Azure

Iteratively improve skill frontmatter to achieve good routing test coverage.

OfficialMITAuto-check passedTesting & QA

Install Sensei

skills CLI
$ npx skills add microsoft/GitHub-Copilot-for-Azure --skill sensei -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install microsoft/GitHub-Copilot-for-Azure sensei --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/microsoft/GitHub-Copilot-for-Azure.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/sensei .claude/skills/sensei && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sensei
GitHub stars
255
Used in
1 other repo
Token cost
~861 tokens
SKILL.md length
222 words
Files
2 (incl. references)
Skills in repo
56
Repo updated
First seen
Licence
MIT

At a glance

Iteratively improve skill frontmatter to achieve good routing test coverage.

  • Works in 8 steps: READ - Load… → VERIFY - Compare the skill frontmatter… → SCAFFOLD - If evals/{skill-name}/… → …
  • Tasks that involve Test coverage
  • SKILL.md covers Help, Main Loop, Constraints and Related Skills
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sensei is an agent skill from microsoft/GitHub-Copilot-for-Azure, published by the product's own GitHub organization. Iteratively improve skill frontmatter to achieve good routing test coverage. WHEN: run sensei, sensei help, improve skill routing

Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/CONVENTIONS.md`).

It sits in Testing & QA, covering Test coverage. It works with Microsoft Azure. The repository describes itself as: GitHub Copilot for Azure. The licence is MIT.

When your agent uses it

  • Tasks that involve Test coverage

Example prompts

  • “/sensei”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. READ - Load plugins/{plugin}/skills/{skill-name}/SKILL.md, and vally eval suites in evals/{skill-name}/*.yaml.
  2. VERIFY - Compare the skill frontmatter with conventions in CONVENTIONS. If the skill's frontmatter violates any written convention, notify…
  3. SCAFFOLD - If evals/{skill-name}/ doesn't exist, follow instructions in vally-eval skill to scaffold a set of routing tests. The routing…
  4. IMPROVE - If the skill description doesn't already have WHEN: triggers, add them.
  5. TEST - Follow instructions in vally-eval skill to run the routing tests. If there are failed tests, suggest fixes.
  6. SUMMARY - Display before/after comparison with unimplemented suggestions.
  7. PROMPT - Ask user to commit the fixes or take any alternative actions.
  8. REPEAT - Go to step 2 (max 5 iterations per skill)

What it can do on your machine

Read from SKILL.md and the folder at commit fcf2f3b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sensei loads about 861 tokens when it runs, and up to ~1.4k if it reads all its reference files. Until then it costs about 34 tokens; SKILL.md has 222 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~861
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microsoft/GitHub-Copilot-for-Azure at commit fcf2f3b, republished under its MIT licence (© microsoft). 222 words, ~861 tokens.

Download SKILL.mdSave it as .claude/skills/sensei/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sensei
description
Iteratively improve skill frontmatter to achieve good routing test coverage. WHEN: run sensei, sensei help, improve skill routing
license
MIT
metadata.author
Microsoft
metadata.version
1.0.6

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:

  1. READ - Load plugins/{plugin}/skills/{skill-name}/SKILL.md, and vally eval suites in evals/{skill-name}/*.yaml.
  2. 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.
  3. SCAFFOLD - If evals/{skill-name}/ doesn't exist, follow instructions in vally-eval skill 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.
  4. IMPROVE - If the skill description doesn't already have WHEN: triggers, add them.
  5. TEST - Follow instructions in vally-eval skill to run the routing tests. If there are failed tests, suggest fixes.
  6. SUMMARY - Display before/after comparison with unimplemented suggestions.
  7. PROMPT - Ask user to commit the fixes or take any alternative actions.
  8. 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
  • vally-eval - vally eval suite writing guidelines

© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .github/skills/sensei of microsoft/GitHub-Copilot-for-Azure.

  • SKILL.md
  • references/CONVENTIONS.md

Open the folder on GitHubat commit fcf2f3b

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in microsoft/GitHub-Copilot-for-Azure, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Sensei next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sensei compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sensei this skillmicrosoft/GitHub-Copilot-for-Azure2551 repos~861Automated safety check: PassMIT
Verify PRAzure/LogicAppsUX114—~2.4kAutomated safety check: PassMIT
Code ReviewAzure/sap-automation145—~7kAutomated safety check: PassMIT
Test Writing WorkflowiOfficeAI/AionUi33k1 repos~1.2kAutomated safety check: PassApache-2.0
Evaluate PR Testsdotnet/maui23k—~2.9kAutomated safety check: PassMIT
Integration Testtracewayapp/traceway1.6k1 repos~2.4kAutomated safety check: PassMIT

Similar skills

  • Verify PR

    Azure/LogicAppsUX

    Official

    Verify PR readiness before requesting review or merging. An agent skill from Azure/LogicAppsUX.

    114 GitHub stars~2.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Code Review

    Azure/sap-automation

    Official

    Review pull requests in the SAP Deployment Automation Framework.

    145 GitHub stars~7k tokensUpdated today
    DevelopmentAuto-check passed
  • Test Writing Workflow

    iOfficeAI/AionUi

    Sets the test-writing workflow for the repository: risk-first scenario lists, behavior-focused Vitest tests, a full run before each commit and a coverage target.

    33k GitHub starsUsed in 1 repo~1.2k tokens
    Testing & QAAuto-check passed
  • Official

    Reviews the tests added in a pull request for fix coverage, quality, edge cases and test type, and recommends lighter test types where they would do.

    23k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check passed
  • Integration Test

    tracewayapp/traceway

    Run a live-instance verification of traceway-cli that goes beyond the Go smoke suite — exercises real-data detail endpoints, TTY-default rendering, adaptive metric-name discovery, and emits a…

    1.6k GitHub starsUsed in 1 repo~2.4k tokens
    Testing & QAAuto-check passed
  • Requirements

    rizsotto/Bear

    Write, modify, or review a requirement file under docs/requirements -- pick the single owning file, keep the text contract-only, name IDs so they need no explanation, and verify cross-references and…

    6.5k GitHub stars~2k tokensUpdated yesterday
    Testing & QAAuto-check passed

More from microsoft/GitHub-Copilot-for-Azure

All 56 skills in this repo
  • Capacity

    microsoft/GitHub-Copilot-for-Azure

    Official

    Discovers available Azure OpenAI model capacity across regions and projects.

    255 GitHub starsUsed in 2 repos~1.7k tokens
    Auto-check passed
  • Deploy Model

    microsoft/GitHub-Copilot-for-Azure

    Official

    Unified Azure OpenAI model deployment skill with intelligent intent-based routing.

    255 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Entra Agent Id

    microsoft/GitHub-Copilot-for-Azure

    Official

    Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant)…

    255 GitHub starsUsed in 3 repos~4k tokens
    Auto-check passed
  • Microsoft Foundry

    microsoft/GitHub-Copilot-for-Azure

    Official

    Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end.

    255 GitHub starsUsed in 1 repo~6.7k tokens
    Auto-check passed
  • Azure Storage

    microsoft/GitHub-Copilot-for-Azure

    Official

    Azure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake.

    255 GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check passed
  • Preset

    microsoft/GitHub-Copilot-for-Azure

    Official

    Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions.

    255 GitHub starsUsed in 2 repos~1.2k tokens
    Auto-check passed

Works with

Categories

Questions about Sensei

What does Sensei do?

Iteratively improve skill frontmatter to achieve good routing test coverage. Sensei is an agent skill from microsoft/GitHub-Copilot-for-Azure, published by the product's own GitHub organization. Iteratively improve skill frontmatter to achieve good routing test coverage.

When should I use Sensei?

Sensei fits situations like: tasks that involve Test coverage.

How do I install Sensei in Claude Code?

Run `npx skills add microsoft/GitHub-Copilot-for-Azure --skill sensei -a claude-code`. Or copy the skill folder (.github/skills/sensei in microsoft/GitHub-Copilot-for-Azure) into .claude/skills/sensei in your project. Claude Code loads it when a task matches its description.

How do I install Sensei in Codex?

Run `npx skills add microsoft/GitHub-Copilot-for-Azure --skill sensei -a codex`. Or copy the skill folder (.github/skills/sensei in microsoft/GitHub-Copilot-for-Azure) into .agents/skills/sensei in your project. Codex loads it when a task matches its description.

Can I use Sensei in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/GitHub-Copilot-for-Azure --skill sensei -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sensei, .gemini/skills/sensei, .github/skills/sensei and .opencode/skills/sensei in your project.

What does Sensei need to run?

SKILL.md names no scripts, command-line tools or credentials: Sensei is instructions for the agent only.

Does Sensei access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sensei safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sensei use?

Sensei is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sensei use?

About 861 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 529 tokens, read only when the agent opens those files.

What are the alternatives to Sensei?

Skills that share tags, products or a category with Sensei: Verify PR (Azure/LogicAppsUX, 114 stars), Code Review (Azure/sap-automation, 145 stars), Test Writing Workflow (iOfficeAI/AionUi, 33k stars) and Evaluate PR Tests (dotnet/maui, 23k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sensei?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/GitHub-Copilot-for-Azure, which has 255 GitHub stars. The repository holds 56 skills in this directory. The repository was last updated on October 8, 2026.

Source: microsoft/GitHub-Copilot-for-Azure on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.