🎯

second-brain-ingest

🎯Skill

from nicholasspisak/second-brain

What it does

Process raw sources in a Second Brain vault (`raw/` folder — articles, papers, notes, transcripts clipped via Obsidian Web Clipper) into structured `wiki/` pages — one summary per source under `wiki/sources/`, plus extracted `entities/`, `concepts/`, and `synthesis/` notes with bidirectional `[[wikilinks]]` and an updated `wiki/index.md` and `log.md`.

📦

Same repository

nicholasspisak/second-brain(4 items)

second-brain-ingest

Installation

Vibe Index InstallInstalls to .claude/skills/ - auto-recognized by Claude Code

npx vibeindex add nicholasspisak/second-brain --skill second-brain-ingest

skills.sh Install⚠ Installs to .agents/skills/ - may not be auto-recognized by Claude Code

npx skills add nicholasspisak/second-brain --skill second-brain-ingest

Manual InstallCopy SKILL.md content and save to the path below

~/.claude/skills/second-brain-ingest/SKILL.md

SKILL.md

999Installs

AddedApr 9, 2026

View on GitHub Back to Skills

More from this repository3

🎯

second-brain🎯Skill

Guided wizard that sets up a new Second Brain vault — an LLM-maintained personal knowledge base on Andrej Karpathy's LLM Wiki pattern. Drop articles/papers/notes into `raw/`, and the LLM compiles them into structured `wiki/` pages (sources, entities, concepts, synthesis) with cross-references and an index you browse in Obsidian. Works with Claude Code, Codex, Cursor, Gemini CLI, and other Agent Skills–compatible agents.

🎯

second-brain-query🎯Skill

Ask questions against a Second Brain wiki — the skill answers from the LLM-maintained `wiki/` pages (sources, entities, concepts, synthesis) and their `[[wikilinks]]`. Automatically uses `qmd` (hybrid local markdown search) when installed for fast retrieval as the vault grows; otherwise reads the wiki directly.

🎯

second-brain-lint🎯Skill

Health-check a Second Brain wiki — verifies that `wiki/index.md` is consistent with the actual pages, scans for broken `[[wikilinks]]` after renames, and reports which files need updating. Recommended after every ~10 ingests (or monthly) and before any major query or synthesis work.