agentleFS
jyjeannejyjeanne/dita-skills/review-dita-guide/SKILL.md

review-dita-guide

Skill2 starsChanged 6 months agoMITView on GitHub

Reviews an entire DITA publication from a root bookmap or ditamap. Traverses the full hierarchy — root map → child ditamaps → leaf topics — and produces a consolidated validation report covering structure, DTD compliance, best practices, and cross-guide issues (missing files, circular map references, duplicate topic IDs) that single-file validators cannot detect.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Before a DITA-OT build to catch issues across the whole publication

    line 34
  2. Distinctive:

    After restructuring a guide (moving topics, nesting new child maps)

    line 35
  3. Distinctive:

    When auditing a large guide for quality and best-practice compliance

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

review-dita-guide

Validates an entire DITA guide by walking the full publication hierarchy from a root bookmap or ditamap down through all referenced child maps and leaf topics.

When to use

  • Before a DITA-OT build to catch issues across the whole publication
  • After restructuring a guide (moving topics, nesting new child maps)
  • During CI/CD to gate publishing on guide-wide validity
  • When auditing a large guide for quality and best-practice compliance

What is checked

Per-file (each map and topic)

  • DTD structural validity (via validate_bookmap, validate_ditamap, validate_dita_topic)
  • Best practices (shortdesc, step count, nesting depth, duplicate paragraphs) when --best-practices is supplied

Cross-guide (spanning multiple files)

RuleSeverityDescription
href-target-missingErrorAn @href in a map points to a file that does not exist
circular-referenceErrorA map references itself directly or through a chain of maprefs
duplicate-guide-idWarningTwo or more topics share the same root @id across the guide

Output schema

{
  "root":    "<path>",
  "summary": {
    "total_files": 12,
    "maps": 2, "topics": 10, "missing": 0,
    "valid_files": 12, "invalid_files": 0,
    "errors": 0, "warnings": 3,
    "cross_guide_issues": 0
  },
  "files": [
    {
      "path": "relative/path.dita",
      "type": "topic|map|bookmap|missing",
      "depth": 1,
      "is_valid": true,
      "errors": [],
      "warnings": [],
      "best_practices": []
    }
  ],
  "cross_guide": [
    { "rule": "duplicate-guide-id", "message": "...", "paths": ["a.dita","b.dita"] }
  ]
}

Exit codes

  • 0 — all files valid, no cross-guide errors
  • 1 — one or more errors found
  • 2 — usage or IO error

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.