GitHub organization

Agent skills by microsoft

Every agent skill microsoft publishes on GitHub, ranked by score, with the repositories they come from.
skills
725
official
725
repositories
42

Repositories by microsoft

Skills by microsoft, ranked

Ranked by score. Sort bymost stars,trending,newest,recently updated

Skills by microsoft, ranked
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
1

A skill your agent uses when the user asks to create, scaffold, or edit Jupyter notebooks (.ipynb) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script…

microsoft/ai-agents-for-beginners77k8 repos~1kAutomated safety check: PassApache-2.018 days ago
2

Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

microsoft/garnet12k—~3.1kAutomated safety check: PassMITtoday
3
3.ReleaseOfficial

Prepare and publish stable Agent Lightning releases through the repository's version bump, pull-request checks, merge, tag, PyPI trusted-publishing, and versioned-documentation workflows.

microsoft/agent-lightning19k—~2.8kAutomated safety check: PassMIT8 days ago
4

Generates GitHub Feature Area Status reports for the Windows App SDK repository, scoring issues so teams can see what needs attention in each area.

microsoft/WindowsAppSDK4.7k—~3.4kAutomated safety check: PassApache-2.0today
5

Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

microsoft/SkillOpt18k—~2.3kAutomated safety check: PassMITtoday
6

Solves web tasks by driving a local Playwright browser one bash command at a time, saving a reusable script, screenshots and an action log for each run.

microsoft/CUAWright6k—~2kAutomated safety check: NotesMITyesterday
7

Finds and fixes out-of-range output writes in ONNX Runtime operator shape-inference functions where a getNumOutputs guard admits too few outputs.

microsoft/onnxruntime22k—~3.3kAutomated safety check: PassMITtoday
8

Prepares the triage meeting summary for WinAppSDK Needs-Triage issues, with research-backed area suggestions, draft replies and a diff since the last triage.

microsoft/WindowsAppSDK4.7k—~2.8kAutomated safety check: PassApache-2.0today
9

Runs a nightly or on-demand sleep cycle for a local Codex agent: review past sessions, replay recurring tasks and stage validated skill and memory edits for adoption.

microsoft/SkillOpt18k—~2.3kAutomated safety check: PassMITtoday
10

Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.

microsoft/skills3.1k6 repos~2.8kAutomated safety check: PassMITtoday
11
11.Agent LightningOfficial

Provides the action space, tradeoffs, and evaluation context for improving an editable AI agent against a benchmark while preserving its deployment contract.

microsoft/agent-lightning19k—~1.7kAutomated safety check: PassMIT8 days ago
12
12.Error HandlingOfficial

统一错误处理系统。在添加 API 端点、修改错误处理、添加前端 API 调用、编写错误相关测试时使用. An agent skill from microsoft/data-formulator.

microsoft/data-formulator18k—~3.8kAutomated safety check: PassMITyesterday
13

Explains why editing CUTLASS fused-MHA headers in ONNX Runtime can leave stale CUDA kernels after an incremental build, and how to force and verify a real rebuild.

microsoft/onnxruntime22k—~1.3kAutomated safety check: PassMITtoday
14

Step-by-step guide for adding a new built-in RESP command to Garnet, from the command enum and parser to storage callbacks, command metadata JSON and tests.

microsoft/garnet12k—~9.7kAutomated safety check: PassMITtoday
15

Mines recurring tasks from recent local Cursor sessions, replays them to test bounded skill edits, and stages validated improvements to a project Cursor skill for review.

microsoft/SkillOpt18k—~2.4kAutomated safety check: PassMITtoday
16

Python guidance for the Azure AI Search SDK covering vector, hybrid and semantic search, index management and indexers, with Entra ID authentication preferred over keys.

microsoft/skills3.1k6 repos~4.4kAutomated safety check: PassMITtoday
17

LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息(messagecode)时使用。

microsoft/data-formulator18k—~1.2kAutomated safety check: PassMITyesterday
18
18.Cut ReleaseOfficial

A skill your agent uses to cut an APM release from the current worktree: assess whether the cycle since the last tag warrants a patch or minor bump (semver discipline against the…

microsoft/apm4k—~2.5kAutomated safety check: PassMITtoday
19

Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands.

microsoft/onnxruntime22k—~1.4kAutomated safety check: PassMITtoday
20

Creates and manages Git worktrees with PowerShell scripts so separate issues and Copilot sessions each get an isolated branch, build and test environment.

microsoft/WindowsAppSDK4.7k—~2kAutomated safety check: PassMITtoday
21

Runs a usage-driven self-improvement cycle for the dsh agent: harvest past sessions, mine recurring tasks, replay them and stage validated skill edits.

microsoft/SkillOpt18k—~1.4kAutomated safety check: PassMITtoday
22
22.Azdo InternalOfficial

A skill your agent uses when asked to trigger or inspect Aspire internal Azure DevOps builds, source-index runs, or release validation on dnceng/internal; push to the internal mirror; download build…

microsoft/aspire6.3k—~4.5kAutomated safety check: PassMITtoday
23
23.Prepare ReleaseOfficial

Prepare a release for the Feature Management .NET SDK. An agent skill from microsoft/FeatureManagement-Dotnet.

microsoft/FeatureManagement-Dotnet1.2k—~1.3kAutomated safety check: PassMITyesterday
24
24.Teams DevOfficial

A skill your agent uses whenever the user mentions Microsoft Teams in a development context — whether they're building, integrating, configuring, debugging, or just asking questions.

microsoft/teams-sdk728—~1.2kAutomated safety check: PassMITyesterday
25
25.Path SafetyOfficial

服务端路径安全与文件访问编码规范。在编写文件下载路由、Agent 工具(文件读取/目录列出)、数据连接器/Loader、Workspace 路径操作、沙箱配置时使用。

microsoft/data-formulator18k—~1.2kAutomated safety check: PassMITyesterday
26

A skill your agent uses to run a holistic regrounding pass on the entire microsoft/apm documentation corpus against current source code, page-by-page, and emit surgical fixes for stale claims.

microsoft/apm4k—~2.6kAutomated safety check: PassMITtoday
27

Triggers, re-runs and unblocks the CI checks on an ONNX Runtime pull request, after diagnosing whether a failure is transient or needs a code change.

microsoft/onnxruntime22k—~4.1kAutomated safety check: PassMITtoday
28
28.AspireOfficial

Orchestrates Aspire distributed applications using the Aspire CLI for running, debugging, and managing distributed apps.

microsoft/aspire.dev1964 repos~1.1kAutomated safety check: PassMITtoday
29
29.Draft PROfficial

Creates a pull request for the current branch, generating a clear title and a description that summarizes the changes and includes instructions on how to test them.

microsoft/roosterjs1.3k—~989Automated safety check: PassUnknowntoday
30
30.Backport PROfficial

Backports a merged PR to a release branch by triggering the /backport bot, waiting for the bot-created PR, and filling in the shiproom template (Customer Impact, Testing, Risk, Regression?).

microsoft/aspire6.3k—~4.2kAutomated safety check: PassMITtoday
31

Shows a categorized, interactive menu of common Squad operations, such as install, upgrade and team management, and collects arguments before running anything.

microsoft/waza1.4k1 repo~2.7kAutomated safety check: PassMITtoday
32
32.CapacityOfficial

Discovers available Azure OpenAI model capacity across regions and projects.

microsoft/GitHub-Copilot-for-Azure2552 repos~1.7kAutomated safety check: PassMITtoday
33

A skill your agent uses to verify CLAIM-LEVEL grounding of a documentation page (or set of pages) against the source code.

microsoft/apm4k—~1.9kAutomated safety check: PassMITtoday
34

Drafts ONNX Runtime release notes from commit history and contributor metadata using named presets for the full runtime or a scoped component.

microsoft/onnxruntime22k—~1.6kAutomated safety check: PassMITtoday
35

Guide for organizing MSBuild infrastructure with Directory.Build.props, Directory.Build.targets, Directory.Packages.props, and Directory.Build.rsp.

microsoft/testfx1k1 repo~2.5kAutomated safety check: PassMITtoday
36
36.MsagljsOfficial

Use MSAGL-JS (Microsoft Automatic Graph Layout) to lay out and visualize networks in JavaScript or TypeScript.

microsoft/msagljs174—~1.2kAutomated safety check: PassMIT5 days ago
37
37.Dv ConnectOfficial

One-step setup and connection diagnostics for a Dataverse environment — installs tools, authenticates, registers MCP, writes .env, and verifies active profiles and linked ERP endpoints.

microsoft/Dataverse-skills2411 repo~5kAutomated safety check: NotesMITyesterday
38

Create and validate Beachball change files. An agent skill from microsoft/beachball.

microsoft/beachball816—~2kAutomated safety check: PassMIT6 days ago
39

Analyze MSBuild binary logs to diagnose build failures. An agent skill from microsoft/testfx.

microsoft/testfx1k3 repos~730Automated safety check: PassMITtoday
40
40.Trx AnalysisOfficial

Parse and analyze Visual Studio TRX test result files. An agent skill from microsoft/vstest.

microsoft/vstest969—~1.8kAutomated safety check: PassMITyesterday
41
41.HotfixOfficial

Proposes a scoped version bump for a roosterjs hotfix. An agent skill from microsoft/roosterjs.

microsoft/roosterjs1.3k—~2.7kAutomated safety check: PassUnknowntoday
42

Bumps the Aspire repository product version in eng/Versions.props using previous version-bump commits as guidance.

microsoft/aspire6.3k—~1.1kAutomated safety check: PassMITtoday
43

Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.

microsoft/SkillOpt18k—~1.3kAutomated safety check: PassMITtoday
44

Create, build, deploy, and localize declarative agents for M365 Copilot and Teams.

microsoft/work-iq1k—~3.2kAutomated safety check: PassUnknowntoday
45

A skill your agent uses to write the PR description (PR body) for any pull request opened against microsoft/apm.

microsoft/apm4k—~4.1kAutomated safety check: PassMITtoday
46

Runs and debugs ONNX Runtime tests: Google Test executables for C++ and unittest or pytest for Python, with filters and build-directory guidance.

microsoft/onnxruntime22k—~1.8kAutomated safety check: PassMITtoday
47
47.Data LoadingOfficial

Discover connected data sources, add new data connectors through a user-confirmed form, inspect table metadata, and run bounded read-only probes when the current workspace data is insufficient.

microsoft/data-formulator18k—~1.4kAutomated safety check: PassMITyesterday
48
48.File ServerOfficial

ALWAYS LOAD THIS SKILL when working with FileServer, SMB, SMB2, SMB3, CIFS, file sharing, MS-SMB2, MS-FSCC, MS-FSA, MS-DFSC, MS-FSRVP, MS-RSVD, MS-SQOS, or any file server protocol test…

microsoft/WindowsProtocolTestSuites567—~4.1kAutomated safety check: PassMIT21 days ago

Questions, answered from the data.

What is the best skill by microsoft?

Jupyter Notebook (official) from microsoft/ai-agents-for-beginners ranks first of the 725 skills by microsoft listed here, with the highest score: its repository has 77k GitHub stars, 8 other GitHub owners carry a copy, its SKILL.md loads about 1k tokens and it passes the automated safety check with no findings. Next come PR Finalize Review and Release.

Are microsoft's skills official?

725 of the 725 skills by microsoft are official, published by the vendor's own GitHub organization: Jupyter Notebook, PR Finalize Review, Release, Windows App SDK Issue Triage Report, SkillOpt Sleep Cycle and 720 more.

How are these skills ranked?

By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.