agentleFS
y-miyazakiy-miyazaki/config/.agents/skills/docs-updater/SKILL.md

docs-updater

Skill1 starsChanged 10 days agoApache-2.0View on GitHub

Detect documentation drift and patch affected docs (candidate survey, git hook, range cursor, or detect JSON). Use in conversation when the user asks to sync or update docs after code changes. Also the loop entry skill for documentation drift automation. Interactive default is survey only; edit docs when the request asks for changes to be made (for example fix, apply, or update) or automation sets agent_edit_allowed in Constraints. Not for new document creation or markdown linting.

3 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

7 rules. About 0 are common, 3 are distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Remove dead links; update paths for renames

    line 37
  2. Distinctive:

    Run detection scripts for other skills or manage caller state

    line 45
  3. Distinctive:

    When intent is unclear, survey and offer to apply — edits are harder to undo than a report.

    line 73
  4. Very specific:

    When agent_edit_allowed is true, resolve agent_edit_target: on the interactive path use fix (this skill).

    line 75
  5. Very specific:

    IF detect reports skip OR no documentation impact after gathering → emit survey no-op per common-output-format.md (Overview explains no-op).

    line 80
  6. Very specific:

    IF agent_edit_allowed is false OR agent_edit_target is not fix → emit survey shape per common-output-format.md.

    line 82
  7. Very specific:

    When detect JSON and ## Constraints are present: follow category-automation-envelope.md for edit gate, report shape, and synthesis.

    line 87

≈ “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

UTILITY SKILL — automated diff-sync and drift repair, not content authoring.

Input

  • Interactive / hook (required): resolve scope per category-detect-scope.md — Interactive free-form → all (full candidate docs); git hook → staged; automation cursor → range with --since — triage per common-impact-map.md; validate patches per common-checklist.md
  • Automation (optional): detect JSON in prompt — from a caller or optional skill detect script; not required for interactive runs. Read agent_edit_allowed and agent_edit_target from ## Constraints per category-automation-envelope.md; load category-input-schema.md on that path only

Path allowlist, when present, arrives in ## Constraints.

Output Specification

Report per common-output-format.md. On the automation path, also follow common-output-format-automation.md and category-automation-envelope.md. Stay within category-scope.md.

Execution Scope

Target: candidate documentation per common-impact-map.md Search Scope — typically root *.md, the repository's documentation tree, nested README.md files (excluding generated directories), and site nav config when present.

USE FOR:

  • Survey candidate documentation for drift and sync opportunities (Interactive all); update cross-references, tables, lists, and nav entries for changed paths
  • Remove dead links; update paths for renames
  • Apply minimal documentation patches per common-checklist.md and category-documentation-maintenance.md

DO NOT USE FOR:

  • New document creation or content improvement
  • Non-documentation file edits
  • Markdown linting
  • Run detection scripts for other skills or manage caller state

Reference Files Guide

  • common-checklist.md (always read)
  • common-output-format.md (always read)
  • common-impact-map.md (read on interactive path)
  • category-documentation-maintenance.md (read when deduplication or same-change sync applies)
  • category-scope.md (always read)
  • category-detect-scope.md (read on interactive path)
  • category-input-schema.md (read when detect JSON is present or the optional detect script is run)
  • category-automation-envelope.md (read on automation path)
  • common-output-format-automation.md (read on automation path)
  • common-troubleshooting.md (read on failure)
  • category-pr-body-links.md (read when synthesizing the PR body)
  • assets/pr-body-template.md and assets/pr-body-template-survey.md (read when synthesizing the PR body)

Workflow

Resolve agent_edit_allowed before patching (git hook runs follow the Interactive rows):

Sourceagent_edit_allowed
Interactive — default: the request asks to look, check, triage, or survey, or only names the skillfalse — survey only; do not edit documentation files
Interactive — the request asks for changes to be made (for example fix, apply, 修正して, 適用して, update, add)true
Interactive — follow-up after a survey asking to applytrue
Automation — ## Constraintsagent_edit_allowed: true or agent_edit_allowed: false from category-automation-envelope.md

When intent is unclear, survey and offer to apply — edits are harder to undo than a report.

When agent_edit_allowed is true, resolve agent_edit_target: on the interactive path use fix (this skill); on the automation path read agent_edit_target from ## Constraints. Do not branch on other caller metadata outside ## Constraints.

Interactive / hook path

  1. Resolve scope (category-scope.md). Parse detect JSON when present; otherwise resolve the detect universe from the prompt (category-detect-scope.md), run this skill's optional detect script with the resolved --scope (default all for Interactive free-form; staged for git hook; range when the user named a SHA range), then Agent-complement beyond mechanical output; if tools for detect are unavailable, gather changed paths from git and the user request instead of silent no-op. On detect script non-zero exit, read stdout and stop.
  2. IF detect reports skip OR no documentation impact after gathering → emit survey no-op per common-output-format.md (Overview explains no-op); stop.
  3. Triage affected docs per common-impact-map.md; grep before full read.
  4. IF agent_edit_allowed is false OR agent_edit_target is not fix → emit survey shape per common-output-format.md; stop — do not edit documentation files or run git add.
  5. ELSE → apply minimal patches per common-checklist.md; when the repository maintains a generated documentation index and documentation files were created/deleted/renamed, regenerate it per UV-05; stage with git add; emit apply shape per common-output-format.md.

Automation path

When detect JSON and ## Constraints are present: follow category-automation-envelope.md for edit gate, report shape, and synthesis. Triage and patch per common-checklist.md and category-documentation-maintenance.md. Do not manage caller state.

Error Handling

ConditionSeverityAction
Detect script non-zero exit or status: "error" (when invoked)FatalRead stdout; stop — do not treat as success-path detect JSON
No git repositoryFatalStop
Empty diff / no documentation impactInfoEmit survey no-op (Overview explains no-op); stop
Affected doc file missingRecoverableSkip file; note in report
Exceeds scope (>3 H2, new top-level document, etc.)RecoverableStop for file; note out of scope for new top-level authoring
mkdocs.yml missingRecoverableSkip nav update
Edit requested but ## Constraints set agent_edit_allowed: falseInfoSurvey only; note that the caller Constraints disallow edits
Automation agent_edit_target mismatchRecoverableSurvey only per category-automation-envelope.md

Examples

  • Prompt: Sync docs after the latest commit diff
  • Result: Survey or apply report per references/common-output-format.md; stay within the UV-04 scope gate in references/common-checklist.md.

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.