AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Second Brain Write

skill-undefined-ui-second-brain-os-second-brain-write · by undefined-ui

>-

— No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-undefined-ui-second-brain-os-second-brain-write

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-undefined-ui-second-brain-os-second-brain-write)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 16d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Second Brain Write? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Write from the vault

The research is already done, cited and connected. What is left is the argument, and that is the part the user should keep.

Core rule

Assemble structure and evidence. Do not hand back finished prose as if it were theirs.

Workflow

  1. Find the relevant concept pages and say what they collectively argue.
  2. Surface the disagreements. These are where the user has something to say

that is not the consensus view, and they are the most useful part of the outline.

  1. Build the outline from pages, each point tied to the page behind it.
  2. Mark the weak points: claims resting on one source, self-reported

figures, anything the vault flags as unverified.

  1. Draft only if asked, and say plainly that the phrasing is a first pass to

be rewritten in their voice.

  1. Offer to ingest the finished piece back as a source once published.

Output format

Angle: 
Outline:
  1.  - [[page]], [[page]]
Weak points: 
Missing: 

Calibration

If every point in the outline comes from one page, this is a summary of that page, not an article. Say so.

Never introduce a specific number or quote that has no source page behind it. That is the failure mode of writing with a model, and in a cited piece it is the one that costs the most.

Source & license

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

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

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.