obsidian-second-brain
obsidian-second-brain is a Personal knowledge & notes skill for AI agents, published by akillness in the jeo-skills repository on GitHub. Skillspace rates obsidian-second-brain F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.
Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.
Routing-first front door for the obsidian-second-brain skill — a self-rewriting Obsidian vault that evolves Karpathy's LLM-Wiki pattern. Instead of appending new notes, every source REWRITES existing pages: people get updated, claims revised, contradictions reconciled, and cross-source patterns synthesized automatically. Ships 45 slash commands across 4 layers (Operations, Thinking Tools, Context Engine, Research Toolkit), a background agent + 4 scheduled agents, 4 role presets, and a write-time AI-first validator. Runs cross-CLI on Claude Code, Codex CLI, Gemini CLI, and OpenCode. Use when the user wants a knowledge vault that maintains itself, to save/ingest meetings/voice/screenshots/URLs into Obsidian, to reconcile contradictions, to challenge a decision against their own history, to run vault-first or open-web research (X / Perplexity / NotebookLM / YouTube / podcasts), or to install the second-brain skill on any of the four CLIs. Triggers on: obsidian second brain, second brain,…
- Grade
- F
- Quality
- 15 / 100
- Safety
- Unsafe
- GitHub stars
- 37
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 78 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Critical-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- pipe remote script to shell
- mentions secrets in text
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.