agentsclimarketplace

Wiki lint

Skill po4yka/llm-wiki-skills/skills/wiki-lint

Run structural and trust health checks for an LLM-Wiki vault. Use for broken links, orphan pages, missing provenance, stale claims, contradiction reports, taxonomy drift, protected-section edits, and review queue generation.From its SKILL.md

Install
npx -y skills add po4yka/llm-wiki-skills --skill wiki-lint

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

5.0 KB, 997 tokens by cl100k_base, as published. Nobody here has run it

Wiki Lint

Goal

Detect structural decay, provenance gaps, stale claims and contradictions without silently rewriting truth.

When to use

  • The vault needs a structural or trust health check.
  • Before large refactors or after bulk ingestion.
  • A review queue should be generated from mechanical findings.

A filled final report ships in assets/worked-example.md.

Inputs

  • wiki/index.md
  • wiki/log.md
  • all wiki/**/*.md pages
  • _meta/taxonomy.md
  • _meta/schemas/*
  • optional git history

Write permissions

Allowed:

  • create reports under _agent/reports/;
  • append to wiki/log.md when a report is created;
  • propose patches;
  • fix trivial broken links only when the user explicitly asks for apply mode.

Not allowed by default:

  • resolve contradictions;
  • rewrite synthesis pages;
  • mark pages verified;
  • delete pages;
  • bulk-normalize frontmatter without a dry run.

Procedure

1. Run deterministic checks

node scripts/wiki-lint-core.mjs <vault-path>

The bundled script is read-only and prints a draft report covering the mechanical checks. Do not re-derive these by hand; re-run the script instead:

  • inventory: page counts by type/status, missing or malformed required frontmatter;
  • links: broken wikilinks and relative links, orphan pages, pages with no outbound links, duplicate titles, near-duplicate slugs;
  • provenance: generated or reviewed/verified factual pages without source_paths/source_urls, high-confidence pages with no source reference;
  • trust: ai_confidence < 0.70 without review_required: true, review_required: false on draft pages, verified pages past stale_after, ambiguous claim support outside review;
  • taxonomy: unknown types/statuses, tags missing from _meta/taxonomy.md, unused taxonomy tags.

Use --strict in CI to fail on critical/high findings.

2. Add judgement-only checks

The script cannot see these; check them manually:

  • pages changed since the last lint and pages without source backlinks in git history;
  • protected human sections changed by recent agent commits;
  • stale source hashes when available;
  • generated pages that cite only other generated pages;
  • pages missing from wiki/index.md that are likely important;
  • spelling-variant and overbroad tags beyond exact taxonomy mismatches.

3. Contradiction checks

Look for tensions such as incompatible tool maturity claims, local-first vs cloud-only descriptions, stale landscape claims contradicting newer source pages, lifecycle status conflicts or incompatible defaults.

Report contradictions with evidence. Do not auto-resolve them.

4. Report

Start from the script's draft report, merge in the judgement-only and contradiction findings, and save it as _agent/reports/YYYY-MM-DD-lint.md:

# Wiki lint report: YYYY-MM-DD

## Summary

## Critical issues

## High-priority review queue

## Broken links

## Orphans

## Provenance gaps

## Stale pages

## Contradictions

## Taxonomy drift

## Suggested patches

## Metrics

Append to wiki/log.md if the report is saved.

Output

A structured lint report saved to _agent/reports/YYYY-MM-DD-lint.md, using the section skeleton from step 4 (Summary, Critical issues, High-priority review queue, Broken links, Orphans, Provenance gaps, Stale pages, Contradictions, Taxonomy drift, Suggested patches, Metrics). Each finding names the affected page path and the check that raised it, tagged with a severity from the table below so a reviewer can triage top-down. Saving a report also appends a one-line entry to wiki/log.md; no other vault content is modified.

Severity levels

SeverityMeaningAction
criticalcould corrupt trust or delete human workstop and review
highimportant provenance or contradiction issuereview soon
mediumstructural decayschedule cleanup
lowcosmetic or taxonomy cleanupbatch later

Safety gates

  • Deterministic checks run through node scripts/wiki-lint-core.mjs are read-only; the script never edits vault files.
  • Contradictions, stale claims and confidence conflicts are reported with evidence, never auto-resolved.
  • Trivial broken-link fixes only run in apply mode when the user explicitly asks for it; every other write stays report-only.
  • Deleting pages, rewriting synthesis pages, marking pages verified, and bulk frontmatter normalization without a dry run are out of scope for this skill.
  • Every saved report is appended as an audit entry to wiki/log.md.

What ships with it: 2 files

17.4 KB alongside SKILL.md, 1 of them executable

assets/

scripts/

Keep looking

Skills are one crate of 326,834. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.