← Explore all agents

DOCUMENTATION CONTRIBUTION / GitHub community

Microsoft Learn contribution guide

Guides a documentation contribution through article structure, Microsoft style, metadata and review feedback.

“Microsoft Learn Contributor chatmode for editing and writing Microsoft Learn documentation following Microsoft Writing Style Guide and authoring best practices.”

01 / THE REASONING

Why this made the selection.

  • It distinguishes conceptual articles, tutorials, quickstarts and reference material before reviewing structure.
  • Its review combines terminology, YAML metadata, descriptive links and repository contribution conventions.
  • The profile mentors a first-time Learn contributor and requires current Microsoft product names, including Entra ID rather than Azure AD.
  • It tells the host to verify current docs through microsoft.docs.mcp before treating a style rule as settled.

02 / THE REVIEW RECORD

What we actually inspected.

Source review has boundaries.
A clear record is more useful than a “safe” badge.

Material inspected

  • agents/microsoft_learn_contributor.agent.md (complete definition)
  • LICENSE (applicable redistribution terms)
  • Host custom-agent documentation; repository installation guidance where applicable
  • Official Learn contribution overview and MCP overview

Our findings

  • The profile declares local edits plus a legacy microsoft.docs.mcp identifier for current documentation lookup.
  • Current Microsoft documentation describes an unauthenticated Streamable HTTP Learn endpoint for search, article fetch and code-sample search.
  • The persona assumes the contributor has never contributed to Microsoft Learn and walks through structure, style, technical accuracy, and accessibility.
  • Product-name rules reject Azure AD, AAD, and Microsoft Docs in favour of Microsoft Entra ID and Microsoft Learn.
  • Tool usage says to call microsoft.docs.mcp for current guidelines, to search the web for branding, and to use editFiles for formatting examples.
  • The file does not merge or publish the article. Quality guidance prefers fewer contributions over many poor ones.

Not established by this review

  • No agent was installed or invoked. Host/model compatibility, task accuracy and runtime behaviour were not tested.
  • The resource was not executed and its tools were not called.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

Use the role in your project.

Upstream setup instructions ↗
  1. Read the pinned definition and MIT licence; review the host permissions before use.
  2. Place the profile in .github/agents/ after adapting tool identifiers; separately configure the official Learn MCP endpoint and review the target repository contribution rules.
  3. Provide an existing article/draft, its Learn repository and the requested contribution scope.

Before you start

  • Copilot and a permitted documentation checkout
  • A GitHub account for submitting documentation changes
  • A separately configured Learn MCP client for live references

04 / FOLLOW THE EVIDENCE

The source trail.

Our notes are separate from the original resource.
Check upstream before adopting a new version.

  1. https://github.com/github/awesome-copilot/blob/f25421d3f1b8b3bb217f78a7c0567cf7ec117cd8/agents/microsoft_learn_contributor.agent.md

    Supports: Workflow, inputs and outputs, Declared tools and constraints, Selection and limitations

  2. https://github.com/github/awesome-copilot/blob/f25421d3f1b8b3bb217f78a7c0567cf7ec117cd8/LICENSE

    Supports: Licence and attribution requirements

  3. https://docs.github.com/en/copilot/reference/custom-agents-configuration

    Supports: Host setup and permission defaults

  4. https://learn.microsoft.com/en-us/contribute/content/

    Supports: Contribution paths and accounts

  5. https://learn.microsoft.com/en-us/training/support/mcp

    Supports: Endpoint, capabilities and authentication

Evidence & Ask