po4yka/llm-wiki-skills / skills/wiki-lint
wiki-lint
VerifiedRun 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.0 KB |
| assets/worked-example.md | markdown | 1.6 KB |
| scripts/wiki-lint-core.mjs | script | 15.7 KB |
assets/worked-example.md
View on GitHub# Worked example: final lint report
The final report merges the `scripts/wiki-lint-core.mjs` draft with the
judgement-only and contradiction checks, and is saved as
`_agent/reports/2026-07-08-lint.md`:
````markdown
# Wiki lint report: 2026-07-08
## Summary
- pages scanned: 12
- findings: 6 (critical: 1, high: 2, medium: 1, low: 1, judgement: 1)
## Critical issues
- [critical] wiki/concepts/agent-memory.md: ai_confidence 0.55 < 0.7 without review_required: true
## High-priority review queue
- [high] wiki/sources/vendor-post.md: verified page past stale_after (2026-05-01)
- [high] wiki/entities/tool-x.md: broken wikilink [[tool-x-benchmarks]]
## Broken links
- [high] wiki/entities/tool-x.md: broken wikilink [[tool-x-benchmarks]]
## Orphans
- [medium] wiki/concepts/spare-note.md: not referenced by any page or wiki/index.md
## Provenance gaps
- none found
## Stale pages
- [high] wiki/sources/vendor-post.md: verified page past stale_after (2026-05-01)
## Contradictions
- wiki/entities/tool-x.md describes Tool X as local-first; wiki/comparisons/stacks.md lists it as cloud-only. Both cited; not auto-resolved.
## Taxonomy drift
- [low] wiki/concepts/spare-note.md: tag 'notes' not in _meta/taxonomy.md
## Suggested patches
- Demote wiki/sources/vendor-post.md to status: stale pending source refresh.
- Fix or remove the [[tool-x-benchmarks]] link.
## Metrics
- type source: 5
- type concept: 4
- type entity: 3
- trust findings: 3
````
## Invariants shown
- The contradiction is reported with evidence, not auto-resolved.
- Patches are proposed, not applied.
- Mechanical findings keep the `[severity] path: message` shape produced by the script.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |