agentleFS
omarismailbomarismailb/product-wiki/.agents/skills/reconcile-wiki/SKILL.md

reconcile-wiki

Skill8 starsChanged 5 months agoMITView on GitHub

Use when product wiki, checks, design system, architecture, dependencies, or code may be out of sync after implementation or routine checks.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the relevant routine:

    line 27
  2. Very specific:

    Read the latest local report under .product-wiki/routine-runs/ and .product-wiki/source-map.json if either exists.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Reconcile Wiki

Your job is to keep the product wiki and codebase aligned.

Drift to find

  • Wiki claims with no executable check.
  • Checks with no linked wiki unit.
  • Code paths with no linked capability, story, rule, or PW: anchor.
  • PW: anchors that point to missing or renamed wiki IDs.
  • Decisions contradicted by current implementation.
  • wiki/overview.md that no longer reflects active wiki units.
  • Design system rules not reflected in UI code.
  • Dependencies not declared in the wiki.
  • Stale assumptions that need review.

Workflow

  1. Run node scripts/wiki-lint.mjs.
  2. Run node scripts/wiki-overview-lint.mjs.
  3. Run node scripts/wiki-anchor-lint.mjs --write-report.
  4. Run the relevant routine:
    • node scripts/routine-runner.mjs --routine routine.traceability-drift
    • node scripts/routine-runner.mjs --routine routine.wiki-health
    • node scripts/routine-runner.mjs --routine routine.overview-freshness
    • node scripts/routine-runner.mjs --routine routine.source-map
    • node scripts/routine-runner.mjs --routine routine.ratchet
    • node scripts/routine-runner.mjs --all for a broad maintenance pass.
  5. Read the latest local report under .product-wiki/routine-runs/ and .product-wiki/source-map.json if either exists.
  6. Read references/drift-rubric.md.
  7. Inspect changed files or the requested scope.
  8. Build a traceability summary:
    • wiki unit
    • code paths
    • PW: anchors
    • checks
    • status
  9. Auto-fix objective missing links or stale anchors when safe.
  10. Raise proposals for judgement calls.
  11. Report anything that needs user review.

Output

Return:

  • Fixed links.
  • Fixed or missing PW: anchors.
  • Overview status.
  • Proposed wiki updates.
  • Missing checks.
  • Stale or contradictory claims.
  • Recommended next step.

Related skills

  • generate-checks: when a wiki claim needs executable coverage.
  • propose-change: when drift reveals a product decision that needs human approval.

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.