Obsidian init

--- description: Scan your vault and generate aCLAUDE.md operating manual,index.md catalog, andlog.md pointer category: meta triggersen : ["init vault", "bootstrap vault", "setup vault", "scan vault"] --- Use the obsidian-second-brainskill . Execute/obsidian-init : 1. Calllist_files_in_vault() to map the full vault structure 2. Spawn parallel subagents to discover vault context simultaneously: - Dashboardagent : readHome.md or equivalent dashboard - Templatesagent : read all files inTemplates/ - Boardsagent : read all files inBoards/ - Samplesagent : read one existing note per major folder to capture naming conventions and frontmatter patterns 3. Merge allagent results into a complete picture of the Vault 4. Generate a complete_CLAUDE.md using the template at~/.claude/skills/obsidian-second-brain/references/claude-md-template.md , populated with real values from the vault 5. Generateindex.md at the vault root:a catalog of all pages organized by category: - List every note in the vault grouped by folder (Projects, People, Ideas, etc.) - Include a one-line description for each note (from the frontmatter or first paragraph) -Claude reads this file FIRST when navigating the vault:cheaper and faster than searching - Format:- [[Note Name]] : brief description 6. Initialize the vault operations log: - Create theLogs/ directory at the vault root - Write `log.md at the vault root as a thin pointer file: explains the per-day structure, points to Logs/ , and includes the entry template (do NOT put log entries in log.md itself) - Write today’s Logs/YYYY-MM-DD.md with the init entry: **HH:MM** - init | Vault initialized with _CLAUDE.md, index.md, Logs/ - Per-day file format: frontmatter (type: log ,date ,ai-first: true ) + **HH:MM** - action | description entries, append-only 7. CreateBases/ at the vault root if it does not exist. Stamp the four premade base files from~/.claude/skills/obsidian-second-brain/references/bases/ : | Template | Output file | Obsidian-style folder | Wiki-style folder | |---|---|---|---| |projects.base.template |Bases/Projects.base |Projects |wiki/projects | |people.base.template |Bases/People.base |People |wiki/entities | |tasks.base.template |Bases/Tasks.base |Tasks |wiki/tasks | |daily.base.template |Bases/Daily.base |Daily |wiki/daily | Detect the vault style based on the folder structure discovered in step 1: ifwiki/ exists at the root, use wiki-style folder names; otherwise, use obsidian-style. For each template, replace the{{FOLDER}} placeholder with the correct folder name, then write toBases/ . Skip any base file that already exists inBases/ :never overwrite. 8. Write_CLAUDE.md ,index.md , rootlog.md (pointer),Logs/YYYY-MM-DD.md (today’s entries), and any newBases/*.base files 9. Confirm what was written and instruct the user to restart theirClaude session so the new files take effect If_CLAUDE.md already exists: display a diff of the changes and ask for confirmation before overwriting. Ifindex.md already exists: regenerate it (it’s always a fresh catalog of the current vault state). If a monolithiclog.md already exists with## YYYY-MM-DD sections: runpython ~/.claude/skills/obsidian-second-brain/scripts/migrate_log.py --vault <vault-path> to split it intoLogs/YYYY-MM-DD.md files. Do not overwrite manually. --- **AI-first rule:** Every note created or updated by this command MUST followreferences/ai-first-rules.md -## For future Claude preamble, rich frontmatter (type ,date ,tags ,ai-first: true , plus type-specific fields), recency markers per external claim, mandatory[[wikilinks]] for every person/project/concept referenced, sources preserved verbatim with URLs inline, and confidence levels where applicable. The vault is for future-Claude retrieval:not for human reading. **Anti-fabrication:** Search exhaustively before claiming that any note, person, or file is missing:false absence is the most common failure mode:and never invent facts, entities, or dates (mark unknowns as “TBD` ”). See the anti-fabric