Map

second-brain

second-brain

A personal knowledge base maintained by an LLM following the LLM Wiki pattern. Human (bigbes) curates sources and directs exploration; Claude reads, summarizes, cross-references, and keeps the graph consistent.

The vault is designed to be opened directly in Obsidian.

Layout

second-brain/
β”œβ”€β”€ CLAUDE.md           β€” schema, conventions, workflows (read this first)
β”œβ”€β”€ meta/               β€” docs about the wiki itself (writing style, tropes to avoid)
β”œβ”€β”€ sources/            β€” raw immutable source documents
β”œβ”€β”€ inbox/              β€” Obsidian web clips waiting to be ingested
β”œβ”€β”€ inbox-processed/    β€” clips after ingest (backup, not deleted)
β”œβ”€β”€ toolbox/            β€” tool/project pages (type: toolbox)
β”œβ”€β”€ wiki/               β€” LLM-maintained markdown pages
β”‚   β”œβ”€β”€ index.md        β€” content catalog
β”‚   └── log.md          β€” append-only activity log
└── tools/              β€” utility scripts (webfetch, etc.)

Every file under wiki/ and toolbox/ has YAML frontmatter with type, summary, tags, sources, created, updated. Cross-references use [[wikilinks]] resolved by Obsidian.

Workflows

The main entry points live as Claude Code skills under .claude/skills/:

  • ingest β€” read a new source, create/update pages, cross-reference, log it.
  • query β€” look up an answer across the wiki, optionally save as an analysis page.
  • lint β€” find contradictions, orphans, stale claims, missing cross-references.

See CLAUDE.md for the full schema and meta/ for style conventions.

License

Content is personal notes and aggregation. Underlying sources retain their original licenses.