From mimirs
Surfaces underdocumented or hard-to-retrieve topics in a project by analyzing search queries that returned no or low-relevance results. Use when improving docs or wiki.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mimirs:doc-gapsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Goal: surface where the index (and likely the docs) fail to answer real queries.
Goal: surface where the index (and likely the docs) fail to answer real queries.
search_analytics for queries that returned no results or only low-relevance hits; these are topics people look for but the codebase/docs don't surface well.search / read_relevant on the weak query yourself: is the content genuinely missing, or just poorly named / undocumented?write_relevant "<topic>" for the best insertion point for new docs or a doc-comment.Finish: a prioritized list — the query, whether content is missing vs. undiscoverable, and the suggested place to document it (file:line).
npx claudepluginhub thewinci/mimirs --plugin mimirsScans workspace for docs (READMEs, docs/, ADRs, API specs), assesses accuracy/freshness/completeness/discoverability, identifies gaps/risks. For doc audits.
Documentation reconnaissance for takeover — find all docs, assess accuracy, freshness, coverage, and discoverability, and identify critical knowledge gaps. Use when asked "what docs exist", "documentation assessment", or "knowledge gaps".
Searches markdown knowledge bases via GitMark CLI (FTS5 BM25 + trigram/fuzzy matching). Use to find where something is documented instead of random file reads.