Skip to content
Back to search

second-brain

LLM-maintained personal knowledge base for Obsidian. Based on Andrej Karpathy's LLM Wiki pattern.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nicholasspisak--second-brain/badge.svg)](/listings/nicholasspisak--second-brain)

HTML

<a href="/listings/nicholasspisak--second-brain"><img src="/api/listings/nicholasspisak--second-brain/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npx skills add NicholasSpisak/second-brain

This installs four skills into your AI agent (Claude Code, Codex, Cursor, Gemini CLI, and 40+ others):

| Skill | What it does | |---|---| | `/second-brain` | Set up a new vault (guided wizard) | | `/second-brain-ingest` | Process raw sources into wiki pages | | `/second-brain-query` | Ask questions against your wiki | | `/second-brain-lint` | Health-check the wiki |

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 103 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Second Brain
  2. An LLM-maintained personal knowledge base built on the [LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f). Drop raw sources into a folder, let the LLM compile them into a structured wiki, and browse it all in Obsidian.
  3. ![Second Brain Overview](docs/assets/second-brain-overview.png)
  4. ## How It Works
  5. You feed raw material (articles, papers, notes, transcripts) into a `raw/` folder. The LLM reads everything, writes structured wiki pages, creates cross-references, and maintains an index. You browse the results in Obsidian — following links, exploring the graph view, and asking questions.
  6. The LLM is the librarian. You're the curator.
  7. ## Prerequisites
  8. - **[Obsidian](https://obsidian.md)** — the markdown editor you'll browse your wiki in
  9. - **An AI coding agent** — [Claude Code](https://claude.ai/code), [Codex](https://openai.com/codex), [Cursor](https://cursor.com), [Gemini CLI](https://github.com/google-gemini/gemini-cli), or any agent that supports [Agent Skills](https://agentskills.io)
  10. - **[Node.js](https://nodejs.org)** — required for installing the skills via npm
  11. ## Install
  12. ```bash
  13. npx skills add NicholasSpisak/second-brain
  14. ```
  15. This installs four skills into your AI agent (Claude Code, Codex, Cursor, Gemini CLI, and 40+ others):
  16. | Skill | What it does |
  17. |---|---|
  18. | `/second-brain` | Set up a new vault (guided wizard) |
  19. | `/second-brain-ingest` | Process raw sources into wiki pages |
  20. | `/second-brain-query` | Ask questions against your wiki |
  21. | `/second-brain-lint` | Health-check the wiki |
  22. ## Quick Start
  23. 1. **Install the skills** (see above)
  24. 2. **Run the wizard:** type `/second-brain` in your AI agent — it walks you through naming, location, domain, and tooling
  25. 3. **Install Web Clipper:** [Obsidian Web Clipper](https://chromewebstore.google.com/detail/obsidian-web-clipper/cnjifjpddelmedmihgijeibhnjfabmlf) — configure it to save to your vault's `raw/` folder
  26. 4. **Open in Obsidian** — launch Obsidian, choose "Open folder as vault", select your vault folder
  27. 5. **Clip your first article** to `raw/`, then run `/second-brain-ingest` — the LLM will discuss key takeaways and build wiki pages
  28. 6. **Browse your wiki** in Obsidian — follow `[[wikilinks]]`, explore the graph view, check `wiki/index.md`
  29. 7. **Keep going** — `/second-brain-query` to ask questions, `/second-brain-lint` to health-check
  30. ## What You Get
  31. ```
  32. your-vault/
  33. ├── raw/ # Your inbox — drop sources here
  34. │ └── assets/ # Images and attachments
  35. ├── wiki/ # LLM-maintained wiki
  36. │ ├── sources/ # One summary per ingested source
  37. │ ├── entities/ # People, orgs, products, tools
  38. │ ├── concepts/ # Ideas, frameworks, theories
  39. │ ├── synthesis/ # Comparisons, analyses, themes
  40. │ ├── index.md # Master catalog of all pages
  41. │ └── log.md # Chronological operation record
  42. ├── output/ # Reports and generated artifacts
  43. └── CLAUDE.md # Agent config (varies by agent)
  44. ```
  45. ## Optional Tools
  46. The wizard offers to install these. All optional but recommended:
  47. - **[summarize](https://github.com/steipete/summarize)** — summarize links, files, and media from the CLI
  48. - **[qmd](https://github.com/tobi/qmd)** — local search engine for markdown files (useful as wiki grows)
  49. - **[agent-browser](https://github.com/vercel-labs/agent-browser)** — browser automation for web research
  50. ## FAQ
  51. **The wizard failed or I need to re-run setup.**
  52. Run `/second-brain` again — the onboarding script is idempotent. It won't overwrite existing files, so your data is safe. If you need a fresh start, delete the vault folder and re-run.
  53. **I accidentally modified a file in `raw/`.**
  54. That's OK. The wiki was built from the original content. If you need the original back, check your git history (if the vault is a git repo) or re-clip the source. The wiki pages are unaffected.
  55. **`wiki/index.md` is out of sync with actual pages.**
  56. Run `/second-brain-lint` — it checks index consistency and offers to fix mismatches.
  57. **Wikilinks are broken after renaming a page.**
  58. Run `/second-brain-lint` — it scans for broken `[[wikilinks]]` and reports which files need updating.
  59. **The wiki is getting large and queries are slow.**
  60. Install `qmd` (`npm i -g @tobilu/qmd`). The query skill uses it automatically when available. It provides fast hybrid search across your wiki files.
  61. **Can I use this with multiple AI agents?**
  62. Yes. The wizard generates config files for each agent you select. They all follow the same wiki schema, so multiple agents can work on the same vault.
  63. **How do I handle images in clipped articles?**
  64. In Obsidian, set Settings → Files and links → Attachment folder path to `raw/assets/`. After clipping an article, use "Download attachments for current file" to save images locally.
  65. **How often should I lint?**
  66. After every 10 ingests or monthly — whichever comes first. Also run it before any major query or synthesis work.
  67. ## Based On
  68. - [Andrej Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f)
  69. - [Agent Skills open standard](https://agentskills.io)
  70. - [Blueprint & origin story](docs/REQUIREMENTS.md) — the founding document for this project
  71. ---
  72. <p align="center">Want to learn how to build projects like this with AI? Join the <a href="https://www.skool.com/buildwithai/about">Build With AI</a> community.</p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.