How do I install the Second Brain Review skill?

Run npx skillmds@latest add undefined-ui/second-brain-review in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Second Brain Review safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Second Brain Review?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Second Brain Review free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Second Brain Review?

undefined-ui (@undefined-ui) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Second Brain Review by undefined-ui

Name: Second Brain Review
Author: undefined-ui

Second Brain Review

Produce a periodic review of a second-brain vault: what was added, which topics are growing, what contradicts what, which questions are still open, and what is worth reading next. Use this skill whenever the user asks for a weekly or monthly review, asks what changed in their vault, what they have been learning about lately, or what they should look at next, and when a scheduled review task fires. Do NOT use for structural linting, for ingesting sources, or for answering a specific factual question.

undefined-ui 50938ee 2.1 KB Updated Sep 17, 2026

File contents

Review the vault

Capture systems fail at the point where nothing comes back out. A review is the loop that closes: it turns a week of ingestion into something the owner reads and acts on, and it is what makes the vault feel alive rather than archival.

Core rule

A review reports on the vault, not on the agent's activity. Nobody needs to know how many tool calls ran; they need to know what they now know.

Workflow

Diff the period. New and updated pages since the last review, from log.md and frontmatter dates.
Find the clusters. Which concepts gained the most links. That is where the owner's attention actually went, which is often not where they think it went.
Surface contradictions recorded during the period and still unresolved.
List open questions from concept and synthesis pages.
Find the neglected. Pages linked often but thin, or gaps in index.md that keep getting referenced.
Recommend three things to read or write next, each tied to a specific page.

Output format

## Week of <date>

Added: <n> pages, <n> sources ingested

### Where your attention went
<two or three sentences on the clusters>

### Unresolved
<contradictions and open questions, each linked>

### Thin spots
<pages that are referenced more than they deserve given their content>

### Next
1. <specific action tied to a page>
2.
3.

Calibration

Reviews that list everything get skimmed and then ignored. Keep it under a page. Three recommendations, not ten. If a week produced nothing worth reporting, say that in one line instead of manufacturing insight.

---name: second-brain-reviewdescription: Produce a periodic review of a second-brain vault: what was added, which topics are growing, what contradicts what, which questions are still open, and what is worth reading next. Use this skill whenever the user asks for a weekly or monthly review, asks what changed in their vault, what they have been learning about lately, or what they should look at next, and when a scheduled review task fires. Do NOT use for structural linting, for ingesting sources, or for answering a specific factual question.---# Review the vaultCapture systems fail at the point where nothing comes back out. A review is theloop that closes: it turns a week of ingestion into something the owner readsand acts on, and it is what makes the vault feel alive rather than archival.## Core ruleA review reports on the vault, not on the agent's activity. Nobody needs toknow how many tool calls ran; they need to know what they now know.## Workflow1. **Diff the period.** New and updated pages since the last review, from `log.md` and frontmatter dates.2. **Find the clusters.** Which concepts gained the most links. That is where the owner's attention actually went, which is often not where they think it went.3. **Surface contradictions** recorded during the period and still unresolved.4. **List open questions** from concept and synthesis pages.5. **Find the neglected.** Pages linked often but thin, or gaps in `index.md` that keep getting referenced.6. **Recommend three things to read or write next**, each tied to a specific page.## Output format```## Week of <date>Added: <n> pages, <n> sources ingested### Where your attention went<two or three sentences on the clusters>### Unresolved<contradictions and open questions, each linked>### Thin spots<pages that are referenced more than they deserve given their content>### Next1. <specific action tied to a page>2.3.```## CalibrationReviews that list everything get skimmed and then ignored. Keep it under apage. Three recommendations, not ten. If a week produced nothing worthreporting, say that in one line instead of manufacturing insight.

Frequently asked questions