Dispatched sub-agent that ingests a new source into an LLM Wiki vault. Reads the source, proposes TL;DR and key claims, identifies which entity/concept/synthesi
所属插件包：llm-wiki
Dispatched sub-agent that answers queries against an LLM Wiki vault. Reads index.md first, drills into 3-10 relevant pages across categories, synthesizes an ans
所属插件包：llm-wiki
Dispatched sub-agent that runs a periodic health check on an LLM Wiki vault. Runs mechanical checks via scripts (orphans, broken links, stale pages, missing fro
所属插件包：llm-wiki
Ingest a source file from raw/ into the LLM Wiki — read, discuss, write summary page, update cross-references across 5-15 pages, regenerate index, append to log
所属插件包：llm-wiki
Bootstrap a fresh LLM Wiki vault with the three-layer structure, schema files, and starter templates. Usage /wiki-init <path> --topic "<topic>" [--tool all|clau
所属插件包：llm-wiki
Run a health check on the LLM Wiki vault — mechanical checks (orphans, broken links, stale pages, missing frontmatter, log gap, duplicates) plus semantic checks
所属插件包：llm-wiki
Show recent entries from the LLM Wiki log (wiki/log.md). Uses the standardized
所属插件包：llm-wiki
Query the LLM Wiki — reads index.md first, drills into 3-10 relevant pages, synthesizes an answer with inline [[wikilink]] citations, and offers to file the ans
所属插件包：llm-wiki
Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/conc
所属插件包：llm-wiki
