Second Brain Ingest

Takes articles, papers, and other documents from a raw folder and transforms them into a structured personal wiki with interlinked pages. Creates source summaries, extracts entities and concepts into their own pages, and maintains a knowledge graph using wikilinks. The workflow is thorough: it discusses key takeaways before writing anything, updates existing pages when new information appears, and flags contradictions between sources. You'll end up touching 10-15 wiki pages per source, which sounds like a lot until you realize that's exactly how knowledge actually connects. Best for people who read a lot and want their notes to compound rather than pile up.

skills.sh installs: 2.6K
GitHub stars: 774
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add nicholasspisak/second-brain --skill second-brain-ingest --agent claude-code

Installs into .claude/skills of the current project.

Files

Second Brain — Ingest

Process raw source documents into structured, interlinked wiki pages.

Identify Sources to Process

Determine which files need ingestion:

If the user specifies a file or files, use those
If the user says "process new sources" or similar, detect unprocessed files:
- List all files in raw/ (excluding raw/assets/)
- Read wiki/log.md and extract all previously ingested source filenames from ingest entries
- Any file in raw/ not listed in the log is unprocessed
If no unprocessed files are found, tell the user

Process Each Source

For each source file, follow this workflow:

1. Read the source completely

Read the entire file. If the file contains image references, note them — read the images separately if they contain important information.

2. Discuss key takeaways with the user

Before writing anything, share the 3-5 most important takeaways from the source. Ask the user if they want to emphasize any particular aspects or skip any topics. Wait for confirmation before proceeding.