Health-check the wiki for contradictions, stale claims, orphan pages, missing cross-references, and knowledge gaps. Use periodically or when the user says 'lint the wiki' or 'check wiki health'.
75
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads `memory/wiki/index.md` and then scans the wiki pages’ text/frontmatter to analyze contradictions, stale claims, orphan/missing links, and gaps; that wiki content is outsider-authored unless it is entirely the operating user’s own, creating an indirect prompt-injection risk by feeding arbitrary page text from a wiki into the agent’s LLM context.
d7a8e2e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.