LI
lisa-lint
Health-check the LLM Wiki: orphan pages, contradictions, stale claims, broken internal links, missing index/log coverage, structure violations, and secret/tenant leaks. Read-only — reports findings, does not fix them.
Install
mkdir -p .claude/skills/lisa-lint && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13641" && unzip -o skill.zip -d .claude/skills/lisa-lint && rm skill.zipInstalls to .claude/skills/lisa-lint
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Health-check the LLM Wiki: orphan pages, contradictions, stale claims, broken internal links, missing index/log coverage, structure violations, and secret/tenant leaks. Read-only — reports findings, does not fix them.217 charsno explicit “when” trigger
About this skill
Lisa Command Compatibility
- Original Claude command:
/lisa:lint - Codex invocation:
$lisa-lintor a plain-English request that matches this skill. - Treat the user's surrounding request as the command arguments.
Use the lisa-wiki-lint skill to run the wiki's integrity checks and report findings by severity (PASS/WARN/FAIL). It diagnoses only — fixes go through /ingest, /setup, or /migrate. Use the user's surrounding request as this command's arguments.