agentleFS
ericwood8ericwood8/skills/microsoft-docs/SKILL.md

microsoft-docs

Skill1 starsChanged 13 days agoMITView on GitHub

Use when answering how a .NET, MSBuild, Windows, WinUI, Azure, M365 or Power Platform feature works, or any API, configuration or limit question where the exact current behavior for a specific SDK or tool version matters. Looks the answer up in Microsoft Learn instead of relying on memory.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use microsoft-code-reference.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GitHubSkill

    microsoft-code-reference

    Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure SDKs, .NET libraries, or Microsoft APIs—to find the right method, check parameters, get working examples, or troubleshoot errors. Catches hallucinated methods, wrong signatures, and deprecated patterns by querying official docs.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search results are often excerpts.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Microsoft Docs Lookup

Training data goes stale, especially for fast-moving surfaces like .NET, MSBuild, and Azure SDKs. When a question hinges on current, version-specific behavior, check Microsoft Learn rather than guessing from memory.

How to look things up

  1. Prefer a Microsoft Learn MCP server if one is connected (tools named like microsoft_docs_search / microsoft_docs_fetch, or similar). Check with ToolSearch if unsure. It returns live, current doc content.
  2. Otherwise use WebSearch/WebFetch against learn.microsoft.com — search for the specific API/feature, then fetch the page for full detail when the summary isn't enough.

When to reach for docs instead of guessing

  • Understanding a concept — "how does X actually work"
  • API signatures, config options, CLI flags — especially anything version-specific
  • Limits, quotas, defaults
  • Confirming something changed between versions (e.g. .NET 8 → .NET 10, an MSBuild SDK bump)
  • Anything where being wrong would waste a build/test cycle rather than just being imprecise in conversation

Skip this for things you're confident about from well-established, stable APIs (e.g. basic C# syntax) — the point is to catch drift on things that change, not to look up everything.

Query effectiveness

Be specific — vague queries return vague results.

❌ "MSBuild items"
✅ "MSBuild ItemGroup Include exclude wildcard syntax"

❌ ".NET HttpClient"
✅ ".NET 10 HttpClient SocketsHttpHandler connection pooling defaults"

Include version and platform when relevant (.NET 10, EF Core 9, Windows App SDK 1.6) — docs for the same API surface can differ meaningfully across versions.

Fetching the full page

Search results are often excerpts. Fetch the full page when:

  • It's a tutorial/quickstart and you need every step, not a fragment
  • A config/CLI reference needs the complete option list
  • The excerpt is visibly cut off mid-explanation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.