microsoft-docs
Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 and Aspire MCP for content that lives outside learn.microsoft.com.
About this skill
This skill empowers AI agents to intelligently query and retrieve information from Microsoft's extensive official documentation ecosystem. It provides access to a vast array of resources, including conceptual articles, in-depth tutorials, and practical code examples across critical Microsoft technologies like Azure, .NET, Agent Framework, Aspire, Visual Studio Code, and GitHub. The skill primarily leverages `learn.microsoft.com` via the Microsoft Learn MCP (Master Content Provider) but is also configured to access content residing outside this domain, utilizing specific MCPs like Context7 and Aspire MCP for comprehensive coverage. This ensures agents can provide accurate, up-to-date, and authoritative answers to complex technical queries, facilitating development, learning, and troubleshooting for users.
Best use case
Enables AI agents to serve as expert knowledge bases for Microsoft technologies, quickly fetching relevant documentation, tutorials, and code examples to assist developers, answer user questions, or generate educational content. It's ideal for scenarios where an agent needs to provide authoritative, official information directly from Microsoft sources.
Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 and Aspire MCP for content that lives outside learn.microsoft.com.
Upon successful execution, the AI agent will retrieve and present relevant, accurate information directly from official Microsoft documentation. This may include direct answers, summaries, links to specific documentation pages on `learn.microsoft.com`, or applicable code snippets, enabling the user to understand or implement Microsoft technologies effectively.
Practical example
Example input
How do I set up a CI/CD pipeline for an Azure Static Web App using GitHub Actions?
Example output
To set up a CI/CD pipeline for an Azure Static Web App with GitHub Actions, you'll typically configure a workflow file in your repository's `.github/workflows` directory. Microsoft Learn provides a comprehensive guide on this process.
[Link to Microsoft Learn: Tutorial - Build and deploy static web app with GitHub Actions]
The process generally involves:
1. **Trigger**: Defining when the workflow runs (e.g., on push to `main` branch).
2. **Build and Deploy**: Using the `azure/static-web-apps-deploy@v1` action.
3. **Configuration**: Specifying `app_location`, `api_location`, `output_location`, and providing your Static Web App API token as a secret.
For example, a basic workflow might look like this (simplified):
```yaml
name: Azure Static Web Apps CI/CD
on:
push:
branches:
- main
jobs:
build_and_deploy_job:
runs-on: ubuntu-latest
name: Build and Deploy Job
steps:
- uses: actions/checkout@v3
with:
submodules: true
lfs: false
- name: Build And Deploy
id: builddeploy
uses: Azure/static-web-apps-deploy@v1
with:
azure_static_web_apps_api_token: ${{ secrets.AZURE_STATIC_WEB_APPS_API_TOKEN }}
repo_token: ${{ secrets.GITHUB_TOKEN }}
action: 'upload'
app_location: '/'
api_location: 'api'
output_location: 'dist'
```
This skill leverages official Microsoft documentation to ensure accuracy and provide up-to-date guidance.When to use this skill
- Use this skill when an AI agent needs to: - Answer specific questions about Microsoft products or services (e.g., Azure features, .NET development). - Find official tutorials or how-to guides for Microsoft technologies. - Retrieve code examples for integrating with Microsoft APIs or services. - Provide authoritative information from Microsoft's vast documentation ecosystem. - Aid in debugging or understanding concepts related to Microsoft development tools.
When not to use this skill
- Avoid using this skill when: - The query is not related to Microsoft technologies or documentation. - The information required is about real-time events, news, or non-static data. - The goal is to query third-party documentation or general internet knowledge not covered by Microsoft's official sources. - You need to generate creative content or perform tasks not involving information retrieval from documentation.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/microsoft-docs/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How microsoft-docs Compares
| Feature / Agent | microsoft-docs | Standard Approach |
|---|---|---|
| Platform Support | ChatGPT, Claude, GitHub Copilot, Gemini | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 and Aspire MCP for content that lives outside learn.microsoft.com.
Which AI agents support this skill?
This skill is designed for ChatGPT, Claude, GitHub Copilot, Gemini.
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# Microsoft Docs Research skill for the Microsoft technology ecosystem. Covers learn.microsoft.com and documentation that lives outside it (VS Code, GitHub, Aspire, Agent Framework repos). --- ## Default: Microsoft Learn MCP Use these tools for **everything on learn.microsoft.com** — Azure, .NET, M365, Power Platform, Agent Framework, Semantic Kernel, Windows, and more. This is the primary tool for the vast majority of Microsoft documentation queries. | Tool | Purpose | |------|---------| | `microsoft_docs_search` | Search learn.microsoft.com — concepts, guides, tutorials, configuration | | `microsoft_code_sample_search` | Find working code snippets from Learn docs. Pass `language` (`python`, `csharp`, etc.) for best results | | `microsoft_docs_fetch` | Get full page content from a specific URL (when search excerpts aren't enough) | Use `microsoft_docs_fetch` after search when you need complete tutorials, all config options, or when search excerpts are truncated. --- ## Exceptions: When to Use Other Tools The following categories live **outside** learn.microsoft.com. Use the specified tool instead. ### .NET Aspire — Use Aspire MCP Server (preferred) or Context7 Aspire docs live on **aspire.dev**, not Learn. The best tool depends on your Aspire CLI version: **CLI 13.2+** (recommended) — The Aspire MCP server includes built-in docs search tools: | MCP Tool | Description | |----------|-------------| | `list_docs` | Lists all available documentation from aspire.dev | | `search_docs` | Weighted lexical search across aspire.dev content | | `get_doc` | Retrieves a specific document by slug | These ship in Aspire CLI 13.2 ([PR #14028](https://github.com/dotnet/aspire/pull/14028)). To update: `aspire update --self --channel daily`. Ref: https://davidpine.dev/posts/aspire-docs-mcp-tools/ **CLI 13.1** — The MCP server provides integration lookup (`list_integrations`, `get_integration_docs`) but **not** docs search. Fall back to Context7: | Library ID | Use for | |---|---| | `/microsoft/aspire.dev` | Primary — guides, integrations, CLI reference, deployment | | `/dotnet/aspire` | Runtime source — API internals, implementation details | | `/communitytoolkit/aspire` | Community integrations — Go, Java, Node.js, Ollama | ### VS Code — Use Context7 VS Code docs live on **code.visualstudio.com**, not Learn. | Library ID | Use for | |---|---| | `/websites/code_visualstudio` | User docs — settings, features, debugging, remote dev | | `/websites/code_visualstudio_api` | Extension API — webviews, TreeViews, commands, contribution points | ### GitHub — Use Context7 GitHub docs live on **docs.github.com** and **cli.github.com**. | Library ID | Use for | |---|---| | `/websites/github_en` | Actions, API, repos, security, admin, Copilot | | `/websites/cli_github` | GitHub CLI (`gh`) commands and flags | ### Agent Framework — Use Learn MCP + Context7 Agent Framework tutorials are on learn.microsoft.com (use `microsoft_docs_search`), but the **GitHub repo** has API-level detail that is often ahead of published docs — particularly DevUI REST API reference, CLI options, and .NET integration. | Library ID | Use for | |---|---| | `/websites/learn_microsoft_en-us_agent-framework` | Tutorials — DevUI guides, tracing, workflow orchestration | | `/microsoft/agent-framework` | API detail — DevUI REST endpoints, CLI flags, auth, .NET `AddDevUI`/`MapDevUI` | **DevUI tip:** Query the Learn website source for how-to guides, then the repo source for API-level specifics (endpoint schemas, proxy config, auth tokens). --- ## Context7 Setup For any Context7 query, resolve the library ID first (one-time per session): 1. Call `mcp_context7_resolve-library-id` with the technology name 2. Call `mcp_context7_query-docs` with the returned library ID and a specific query --- ## Writing Effective Queries Be specific — include version, intent, and language: ``` # ❌ Too broad "Azure Functions" "agent framework" # ✅ Specific "Azure Functions Python v2 programming model" "Cosmos DB partition key design best practices" "GitHub Actions workflow_dispatch inputs matrix strategy" "Aspire AddUvicornApp Python FastAPI integration" "DevUI serve agents tracing OpenTelemetry directory discovery" "Agent Framework workflow conditional edges branching handoff" ``` Include context: - **Version** when relevant (`.NET 8`, `Aspire 13`, `VS Code 1.96`) - **Task intent** (`quickstart`, `tutorial`, `overview`, `limits`, `API reference`) - **Language** for polyglot docs (`Python`, `TypeScript`, `C#`)
Related Skills
jupyter-notebook
Use 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 `new_notebook.py` to generate a clean starting notebook.
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
fixing-streamlit-ci
Analyze and fix failed GitHub Actions CI jobs for the current branch/PR. Use when CI checks fail, PR checks show failures, or you need to diagnose lint/type/test errors and verify fixes locally.
fixing-flaky-e2e-tests
Diagnose and fix flaky Playwright e2e tests. Use when tests fail intermittently, show timeout errors, have snapshot mismatches, or exhibit browser-specific failures.
finalizing-pr
Finalizes branch changes for merging by simplifying code, running checks, reviewing changes, and creating a PR if needed. Use when ready to merge changes into the target branch.
discovering-make-commands
Lists available make commands for Streamlit development. Use for build, test, lint, or format tasks.
debugging-streamlit
Debug Streamlit frontend and backend changes using make debug with hot-reload. Use when testing code changes, investigating bugs, checking UI behavior, or needing screenshots of the running app.
creating-pull-requests
Creates a draft pull request on GitHub with proper labels, branch naming, and description formatting. Use when changes are ready to be submitted as a PR to the streamlit/streamlit repository.
checking-changes
Validates all code changes before committing by running format, lint, type, and unit test checks. Use after making backend (Python) or frontend (TypeScript) changes, before committing or finishing a work session.
assessing-external-test-risk
Assesses whether branch or PR changes are high-risk for externally hosted or embedded Streamlit usage and recommends whether external e2e coverage with `@pytest.mark.external_test` is needed. Use during code review, PR triage, or test planning when changes touch routing, auth, websocket/session behavior, embedding, assets, cross-origin behavior, SiS/Snowflake runtime, storage, or security headers.
addressing-pr-review-comments
Address all valid review comments on a PR for the current branch in the streamlit/streamlit repo. Covers both inline review comments and general PR (issue) comments. Use when a PR has reviewer feedback to address, including code changes, style fixes, and documentation updates.
n8n-expression-syntax
Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with webhook data in workflows.