agentleFS
MicrosoftKnown publishermicrosoft/nacelle/.github/skills/docs-review/SKILL.md

docs-review

Skill6 starsChanged 14 days agoMITView on GitHub

Review Nacelle README, rustdoc, Markdown, mdBook navigation, commands, links, API contracts, and readiness wording against implementation and validation evidence.

25 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this workflow for documentation-only changes and the documentation portion of mixed changes.

    line 8
  2. Distinctive:

    Read the documentation instructions and general communication and documentation styles.

    line 14
  3. Distinctive:

    Verify names, defaults, feature gates, errors, limits, and wire behavior.

    line 22
  4. Distinctive:

    Check decoder progress and buffer ownership when codec documentation changes.

    line 23
  5. Very specific:

    Verify commands from their stated working directory.

    line 24
  6. Very specific:

    Check relative file links and heading anchors.

    line 28
  7. Distinctive:

    Do not assume a successful render proves external links or commands work.

    line 30
  8. Distinctive:

    Check that public API and behavior changes update the relevant crate README and reference pages.

    line 31
  9. Distinctive:

    Keep correctness, security, performance, operability, compatibility, and documentation evidence distinct.

    line 36

“Common” is measured: kept by at least 6 in 10 of the 24 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

Reviewing Nacelle Documentation

Use this workflow for documentation-only changes and the documentation portion of mixed changes. Apply the general review evidence and severity rules without calling another review agent.

Procedure

  1. Read the documentation instructions and general communication and documentation styles.
  2. Identify the audience and contract: introductory use, tutorial, operator procedure, architecture explanation, or API/configuration reference. Keep working assessments and requested plans in their ignored locations.
  3. Compare claims with the owning crate, manifests, tests, examples, and scripts. Verify names, defaults, feature gates, errors, limits, and wire behavior. Check decoder progress and buffer ownership when codec documentation changes.
  4. Verify commands from their stated working directory. Confirm package names, binary targets, flags, config paths, prerequisites, and supported TLS combinations. Do not suggest workspace --all-features where it enables mutually exclusive providers.
  5. Check relative file links and heading anchors. For published pages, trace navigation from docs/SUMMARY.md and verify mdBook paths in book.toml. Do not assume a successful render proves external links or commands work.
  6. Check that public API and behavior changes update the relevant crate README and reference pages. Avoid duplicate authoritative descriptions that can diverge.
  7. Assess performance and readiness language against the stated platform, feature flags, workload, security mode, measurements, and rollback posture. Keep correctness, security, performance, operability, compatibility, and documentation evidence distinct. Do not import deployment requirements from another product or treat experimental status as a reason to omit safety contracts.
  8. Apply style to authored prose without changing identifiers, protocol tokens, quotations, or required technical details. Report consequential ambiguity or explicit rule violations, not subjective rewrites.
  9. Inspect or, when authorized, run mdbook build for book changes. For rustdoc, assess owning-crate doc tests or the documented cargo doc command under the affected feature set. Report checks not run and unavailable tooling.

Output

Lead with verified findings: location, inaccurate or missing contract, affected reader or operation, evidence, and a concrete correction. Separate optional wording suggestions and unresolved evidence gaps from defects. If no verified findings remain, say so and state the validation scope.

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.