# Second Brain Report

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-undefined-ui-second-brain-os-second-brain-report`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [undefined-ui](https://agentstack.voostack.com/s/undefined-ui)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [undefined-ui](https://github.com/undefined-ui)
- **Source:** https://github.com/undefined-ui/second-brain-os/tree/main/skills/second-brain-report
- **Website:** https://x.com/undefinedKi/status/2068306794116501544

## Install

```sh
agentstack add skill-undefined-ui-second-brain-os-second-brain-report
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Write a research report

A report that presents only findings looks stronger and is less useful, because
the reader cannot tell where it is load-bearing and where it is thin.

## Core rule

Scope against the vault first. Most of the work in a good report is knowing what
you do not need to look up.

## Workflow

1. **Inventory what exists.** Which pages cover this, what is thin, what is
   missing entirely. That answer is the research plan.
2. **Report the gaps before writing,** so the user can decide whether to ingest
   more first.
3. **Write from pages, citing pages.** Every claim traces to a source page with
   a URL behind it.
4. **Record disagreement** where sources conflict, with dates and who says what.
5. **State what could not be established** and what evidence would change the
   conclusion.
6. **Save to `output/`** and offer to ingest it back as a source.

## Output format

```
## Question
## What the vault covers    (with [[page]] citations)
## Where sources disagree
## What I could not establish
## What would change this
## Pages read: 
```

## Calibration

If the vault covers less than half the question, say so at the top rather than
producing a report that reads as complete.

Never fill a gap from general knowledge without labelling it as outside the
vault. A report whose sources cannot be checked is worth less than a short one
that can.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [undefined-ui](https://github.com/undefined-ui)
- **Source:** [undefined-ui/second-brain-os](https://github.com/undefined-ui/second-brain-os)
- **License:** MIT
- **Homepage:** https://x.com/undefinedKi/status/2068306794116501544

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-undefined-ui-second-brain-os-second-brain-report
- Seller: https://agentstack.voostack.com/s/undefined-ui
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.