LLM Wiki Lint
SkillDocs & knowledgeValidate Wiki and source note health. Use before commits, after ingests, or when notes were edited by hand.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the LLM Wiki Lint skill
What this skill tells your AI
The instructions your AI receives, as published by gavishap/omnia-vault in .claude/skills/llm-wiki-lint/SKILL.md and read by ahel’s review.
Run the deterministic checks and fix what they report.
Steps
-
Run the full check suite:
python scripts/wiki_tool.py doctor python scripts/wiki_tool.py build python scripts/wiki_tool.py lint python scripts/wiki_tool.py source-lint python scripts/audit_public.py -
For every lint failure, open the offending note and fix the root cause:
- wrong or missing tag → set exactly one allowed tag matching the folder
source_countmismatch → recountsourcesentries- broken source link → fix the path or restore the missing Raw source
- missing source frontmatter → fill in
Title,Reference,Created,Processed,tags - processed-but-uncovered source → either compile it into Wiki notes or
set
Processed: false
-
Re-run until everything passes.
-
See
Schema/lint-checklist.mdfor the full rule list, including the manual checks lint cannot automate (claim support, no invented citations).
Rules
- Fix causes, not symptoms: do not silence a check by deleting
sourcesor downgrading a note's frontmatter. - Never hand-edit generated files (
Wiki/catalog.jsonl, index files,Schema/source-manifest.jsonl); regenerate them instead.
Signals
- GitHub stars
- 62
- Forks
- 6
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
llm-wiki-lint- Source
- github.com/gavishap/omnia-vault