wiki_graph_indexlisted

# LLM Wiki — Graph Index Skill (wiki_graph_index) > **CLI (read first):** This skill drives the `magi` CLI (MAGI research workspace tool, assumed installed on PATH). If unsure of your surroundings, run `magi sync` first to locate the workspace. For the full syntax of any command: `magi <command> --help`. This skill extracts the Markdown-based knowledge graph (comprised of `[[wikilinks]]`, tags, and aliases) into a structured SQLite database (`output/graph.db`) that an AI agent can easily query using standard SQL. ## Usage When the user asks to extract, index, or query the knowledge graph of their wiki: ### 1. Build the Graph Database Run the deterministic graph builder to extract the graph from the markdown files: ```bash magi graph build <TOPIC_DIR> ``` *This will parse all markdown files under `wiki/` (ignoring `_index.md`), extract frontmatter (tags, aliases) and body links, and rebuild the SQLite database located at `output/graph.db`.* ### 2. Query the Graph Database Once built, use `magi graph query "<SQL>" --db <TOPIC_DIR>/output/graph.db` to query the knowledge graph. Fall back to a temporary Python script using the `sqlite3` module only for complex multi-step traversals that a single SQL statement cannot express. Do not use direct `sqlite3` command line execution. The database schema is as follows: - `nodes(id, path, title, type, category, summary, created, updated)` - `id`: The topic-relative file path without extension, WITH the `wiki/` prefix (e.g., 'wiki/