
Second Brain Ingest
Turn files dropped in `raw/` into structured, interlinked wiki pages in a personal second-brain repo without losing source traceability.
Overview
Second Brain — Ingest is an agent skill for the Operate phase that processes `raw/` sources into structured, interlinked wiki pages after you confirm key takeaways.
Install
npx skills add https://github.com/nicholasspisak/second-brain --skill second-brain-ingestWhat is this skill?
- Detects unprocessed files by diffing `raw/` against prior `ingest` lines in `wiki/log.md`
- Requires reading each source end-to-end (including image references) before writing
- Pauses for user confirmation on 3–5 takeaways before creating `wiki/sources/` pages
- Creates structured, interlinked wiki pages from approved emphasis
- Allowed tools: Bash, Read, Write, Edit, Glob, Grep for repo-local ingestion
- 3–5 key takeaways discussed with the user before any wiki write
Adoption & trust: 1.6k installs on skills.sh; 387 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You saved articles and exports in `raw/` but nothing is summarized, linked, or recorded in `wiki/log.md` so your second brain stays unreadable.
Who is it for?
Solo builders maintaining a git-based second brain who add sources regularly and want human-in-the-loop emphasis before pages are written.
Skip if: One-off summaries in chat with no wiki repo, or teams that need automated bulk ingestion without discussing takeaways first.
When should I use this skill?
User adds files to `raw/`, says process/ingest a source, or wants new material incorporated into the knowledge base.
What do I get? / Deliverables
Each approved source becomes a `wiki/sources/` page with interlinks and an `ingest` log entry so future agent sessions can navigate your KB reliably.
- `wiki/sources/` summary page per source
- Updated interlinked wiki structure
- `ingest` entry in `wiki/log.md`
Recommended Skills
Journey fit
Ingest is the recurring maintenance step after you ship a knowledge-base layout—new articles land in raw and must become durable wiki pages with log entries. `iterate` fits ongoing KB hygiene: detect unprocessed raw files, confirm takeaways, then extend `wiki/` and `wiki/log.md` rather than one-off prototyping.
How it compares
Use instead of pasting sources into ad-hoc notes when you want durable, logged wiki pages tied to filenames in `raw/`.
Common Questions / FAQ
Who is second-brain-ingest for?
Solo and indie builders who run a second-brain repo with `raw/` intake and a `wiki/` tree and want agent help turning new files into linked pages.
When should I use second-brain-ingest?
Use it in Operate when you add files to `raw/` or say “process new sources”; also when validating research during Idea if you already maintain the wiki and want material incorporated before you commit to a build direction.
Is second-brain-ingest safe to install?
It expects Bash plus read/write access to your repo; review the Security Audits panel on this Prism page and only run it on knowledge bases you control.
SKILL.md
READMESKILL.md - Second Brain Ingest
# Second Brain — Ingest Process raw source documents into structured, interlinked wiki pages. ## Identify Sources to Process Determine which files need ingestion: 1. If the user specifies a file or files, use those 2. 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 3. 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. ### 3. Create source summary page Create a new file in `wiki/sources/` named after the source (slugified). Include: --- tags: [relevant, tags] sources: [original-filename.md] created: YYYY-MM-DD updated: YYYY-MM-DD --- # Source Title **Source:** original-filename.md **Date ingested:** YYYY-MM-DD **Type:** article | paper | transcript | notes | etc. ## Summary Structured summary of the source content. ## Key Claims - Claim 1 - Claim 2 - ... ## Entities Mentioned - [[Entity Name]] — brief context - ... ## Concepts Covered - [[Concept Name]] — brief context - ... ### 4. Update entity and concept pages For each entity (person, organization, product, tool) and concept (idea, framework, theory, pattern) mentioned in the source: **If a wiki page already exists:** - Read the existing page - Add new information from this source - Add the source to the `sources:` frontmatter list - Update the `updated:` date - Note any contradictions with existing content, citing both sources **If no wiki page exists:** - Create a new page in the appropriate subdirectory: - `wiki/entities/` for people, organizations, products, tools - `wiki/concepts/` for ideas, frameworks, theories, patterns - Include YAML frontmatter with tags, sources, created, and updated fields - Write a focused summary based on what this source says about the topic ### 5. Add wikilinks Ensure all related pages link to each other using `[[wikilink]]` syntax. Every mention of an entity or concept that has its own page should be linked. ### 6. Update wiki/index.md For each new page created, add an entry under the appropriate category header: - [[Page Name]] — one-line summary (under 120 characters) ### 7. Update wiki/log.md Append: ## [YYYY-MM-DD] ingest | Source Title Processed source-filename.md. Created N new pages, updated M existing pages. New entities: [[Entity1]], [[Entity2]]. New concepts: [[Concept1]]. ### 8. Report results Tell the user what was done: - Pages created (with links) - Pages updated (with what changed) - New entities and concepts identified - Any contradictions found with existing content ## Conventions - Source summary pages are **factual only**. Save interpretation and synthesis for concept and synthesis pages. - A single source typically touches **10-15 wiki pages**. This is normal and expected. - When new information contradicts existing wiki content, **update the wiki page and note the contradiction** with both sources cited. - **Pre