agentleFS
jasonmichaelbell78-creatorjasonmichaelbell78-creator/sonash-v0/.claude/skills/docs-maintain/SKILL.md

docs-maintain

Skill2 starsChanged 9 months agoApache-2.0View on GitHub

Check documentation sync and auto-update doc artifacts. Combines sync checking (template-instance validation) with update automation (index regeneration, cross-doc dependencies, archive verification).

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    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:

    When the task doesn't match this skill's scope -- check related skills

    line 23
  2. Distinctive:

    When a more specialized skill exists for the specific task

    line 24
  3. Very specific:

    No placeholder content remains ([e.g., ...], [X], [TODO], etc.)

    line 51
  4. Distinctive:

    All relative links point to existing files

    line 52
  5. Distinctive:

    After creating, moving, or deleting markdown files

    line 87
  6. Very specific:

    When pre-commit blocks due to DOCUMENTATION_INDEX.md not staged

    line 88
  7. Distinctive:

    Before multi-AI audits (ensure audit plans are synced)

    line 89
  8. Distinctive:

    After updating templates (verify instances were updated)

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
<!-- prettier-ignore-start -->

Document Version: 1.0 Last Updated: 2026-02-14 Status: ACTIVE

<!-- prettier-ignore-end -->

Documentation Maintenance

Unified skill for checking doc sync and updating doc artifacts.

When NOT to Use

  • When the task doesn't match this skill's scope -- check related skills
  • When a more specialized skill exists for the specific task

Usage

/docs-maintain            # Run both check + update
/docs-maintain --check    # Check only (no changes)
/docs-maintain --update   # Update only (regenerate + fix)

Check Mode (from docs-sync)

Validate template-instance synchronization.

Execution

npm run docs:sync-check
# With details: npm run docs:sync-check -- --verbose
# As JSON: npm run docs:sync-check -- --json

What It Checks

  1. Template-derived documents are properly synchronized
  2. No placeholder content remains ([e.g., ...], [X], [TODO], etc.)
  3. All relative links point to existing files
  4. Sync dates are recent (<90 days)

Exit Codes

  • 0: All documents synced
  • 1: Sync issues found
  • 2: Error during check

Update Mode (from docs-update)

Auto-update documentation artifacts after file changes.

Execution

npm run docs:index && git add DOCUMENTATION_INDEX.md

What It Does

  1. Regenerate Documentation Index - runs npm run docs:index to update DOCUMENTATION_INDEX.md
  2. Check Cross-Document Dependencies - reviews docs/DOCUMENT_DEPENDENCIES.md for affected triggers
  3. Verify Archive Requirements - checks moved docs have README.md in archive folders
  4. Suggest Updates - lists documents referencing moved/deleted files

When to Use

  • After creating, moving, or deleting markdown files
  • When pre-commit blocks due to DOCUMENTATION_INDEX.md not staged
  • Before multi-AI audits (ensure audit plans are synced)
  • After updating templates (verify instances were updated)
  • After archiving documents

Related

  • DOCUMENTATION_INDEX.md - Auto-generated doc index
  • docs/DOCUMENT_DEPENDENCIES.md - Cross-doc triggers and sync protocols
  • Pre-commit hook (step 8) - Doc index enforcement

Version History

VersionDateDescription
1.02026-02-25Initial implementation

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.

Reviews can't be read right now.

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.