Answer questions from an Obsidian wiki with citations.
npx skills add https://github.com/Michael1Peng/watson --skill wiki-query-michael1peng
Please help me install this Agent Skill. Skill: wiki-query Source: https://github.com/Michael1Peng/watson/tree/main/.agents/skills/wiki-query Command: npx skills add https://github.com/Michael1Peng/watson --skill wiki-query-michael1peng
Answer questions against the compiled Obsidian wiki, not raw source documents. The wiki contains pre-synthesized, cross-referenced knowledge. It helps you answer questions, find information across your wiki, discover what you know about X, find everything related to Y, or synthesize answers with citations from wiki pages. It also supports exploring connections between topics within the wiki and a fast index-only mode for quick results that rely on page summaries and frontmatter without reading page bodies.
Ask it to search your Obsidian wiki for what is known about a topic and present concise results with citations.
High-intent search queries and answers about installing and using this skill.
Searching your Obsidian wiki involves a retrieval pipeline that starts from index.md, scans page frontmatter and summaries, and optionally reads full pages to synthesize cited answers for your questions.
The fastest way to retrieve knowledge is using the index-only mode, which returns answers by scanning page summaries and frontmatter without reading the full page bodies, providing quick results from pre-synthesized information.
Yes, you can explore relationships between topics by cross-referencing compiled wiki pages and their links, allowing you to discover connections and find everything related to a specific subject.
This approach works with a compiled Obsidian wiki containing pre-synthesized, cross-referenced knowledge, not raw source documents, ensuring answers are drawn from structured summaries and frontmatter rather than unprocessed text.
To find everything related to a topic, query the compiled wiki to cross-reference pages and their links, using QMD matching if needed to resolve deeper connections and synthesize answers with citations.
markwang2658Ingest sources into a persistent interlinked markdown wiki with schema compliance.
swarm-ai-safetyIdentify and articulate semantic connections between knowledge vault claims and topic maps.
dapperdiversIndex Obsidian vault metadata into a SQLite database for structured note retrieval.
Astro-HanCompile raw source materials into structured markdown wiki pages.
