From wiki
Use when the user invokes LLM Wiki lint workflow — explicitly via "wiki:lint", "wiki: lint", "перевір wiki", "audit the wiki", or similar consistency-check requests. Scans entities/, concepts/, and comparisons/ for contradictions, stale pages, orphans, missing cross-references, and data gaps. Writes findings into a fresh questions/lint-YYYY-MM-DD.md and appends a log entry. Recognizes the wiki by a CLAUDE.md with `type: schema, scope: wiki` and follows the lint protocol from there.
How this skill is triggered — by the user, by Claude, or both
Slash command
/wiki:lintThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are the lint workflow for an LLM Wiki. The authoritative procedure lives in the wiki's `CLAUDE.md`.
You are the lint workflow for an LLM Wiki. The authoritative procedure lives in the wiki's CLAUDE.md.
Find CLAUDE.md with frontmatter type: schema and scope: wiki:
pwd$VAULT_ROOT/**/wiki/CLAUDE.mdRead every file under entities/, concepts/, comparisons/. Use mcp__plugin_qmd_qmd__multi_get with globs (entities/*.md, etc.) for efficiency when the qmd MCP is available.
Per wiki/CLAUDE.md, find:
| Category | Definition |
|---|---|
| Contradictions | Two pages assert claims that cannot both be true |
| Stale | last_updated older than 30 days AND confidence: low |
| Orphans | Page has no inbound wikilinks from any other wiki body file |
| Missing cross-refs | Page mentions an entity by name but doesn't wikilink it |
| Data gaps | Entity/concept without a Sources section, or with confidence: low and no matching open questions/<topic>.md |
Create questions/lint-YYYY-MM-DD.md with frontmatter:
---
type: question
tags: [lint]
last_updated: YYYY-MM-DD
confidence: high
---
Body: one ## <Category> heading per non-empty bucket; under each, a bullet list of specific findings with [[wikilinks]] and one-line rationale.
Append log.md:
## [YYYY-MM-DD] lint | <N findings across M categories>
- contradictions: X
- stale: Y
- orphans: Z
- missing cross-refs: W
- data gaps: V
raw/Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub genkovich/llm-wiki --plugin wiki