agentleFS
Sign inStart free
grimoire-rsgrimoire-rs/grimoire/.agents/skills/docs-review/SKILL.md

docs-review

Skill15 starsChanged 19 days agoApache-2.0View on GitHub

Grade documentation pages against the docs-quality rule set on demand, in any directory and any markup format (Markdown, MDX, reStructuredText, MyST, AsciiDoc). Use when someone asks to review, check, grade, lint or audit a doc page, a README, a changelog, a docs directory or the docs changed on a branch, asks whether a page meets docs-quality, or wants the docs gate run by hand. Not for deciding which pages to write, which is docs-plan, and not for wiring the checks into CI, which is docs-instrument.

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use code-review.

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.
  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Stop when every target page has a verdict: each finding as path:line: DOC-XXX-nn: message, or clean.

    line 18
  2. Very specific:

    Read the installed docs-quality rule index, then only the depth files its routing table names for the target page types.

    line 32
  3. Very specific:

    Add doc_examples.py, nav_depth.py and links_raw.py when the review covers a whole docs tree rather than single pages.

    line 57

“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

docs-review

The docs-quality rule loads when an agent edits a page. This skill is the explicit trigger: grade pages nobody is editing, pages in unusual places, and pages in a format the scripts only partly read.

Stop condition

Stop when every target page has a verdict: each finding as path:line: DOC-XXX-nn: message, or clean. Mark any finding no script produced unverified: reading heuristic. Report; never fix unless asked.

1. Pick the targets

  • Named paths or directories: use them as given, whatever their location.
  • Nothing named: the branch diff, git diff --name-only --diff-filter=d "$(git merge-base HEAD origin/HEAD)" -- '*.md' '*.mdx' '*.rst' '*.adoc' '*.asciidoc'.
  • Drop agent config (CLAUDE.md, AGENTS.md, SKILL.md, .claude/, .agents/), vendored copies and build output. The rule excludes them too.

2. Load the rule

Read the installed docs-quality rule index, then only the depth files its routing table names for the target page types. Find it with find . -path '*docs-quality*' -name 'docs-quality.md' -not -path '*/node_modules/*'. Its checks/ directory sits beside it. No hit means the rule is not installed: say grim add ghcr.io/ocx-sh/lore/docs-quality and stop.

3. Run the checks by format

CHECKS below is that checks/ directory. Every script takes explicit paths, so pass the targets rather than --root.

FormatScriptedRead by hand
.md, .mdxthe whole gate, in the rule's orderrows the scripts mark heuristic
.rst, MyST, .adocdoc_declaration.pyeverything else, or convert first

Markdown and MDX:

python3 "$CHECKS/doc_declaration.py" PAGE...
python3 "$CHECKS/prose.py"           PAGE...
python3 "$CHECKS/page_type.py"       PAGE...
python3 "$CHECKS/landing_check.py"   PAGE...

Add doc_examples.py, nav_depth.py and links_raw.py when the review covers a whole docs tree rather than single pages. Their inputs are a tree.

reStructuredText and AsciiDoc: run doc_declaration.py on the source. The prose and page-type scripts parse Markdown only. When pandoc is on the PATH, convert each page into a scratch directory and run them on the copy:

pandoc -f rst -t gfm PAGE.rst -o "$SCRATCH/PAGE.md"   # asciidoc: asciidoctor -b docbook | pandoc -f docbook

Line numbers from a converted copy point at the copy. Map each finding back to the source line by its quoted text before reporting it. No converter means the non-negotiables are read by hand and every such finding is marked unverified.

4. Report

One line per finding, grouped by page, ordered by the rule's non-negotiable number. End with a count per page. Undeclared pages are listed first, because every type-scoped check skipped them.

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.

Check your setup, free