Skills for Real Engineers. Straight from my .agents directory.
second-brain-privacy
Agent skill fromundefined-ui/second-brain-os
Audit the vault for material that should not be in it: credentials, other people's private information, confidential work, and anything the user would not want synced or backed up. Use this skill when the user asks about privacy, is about to share or sync the vault, has just imported chat history or meeting notes, or asks what is sensitive in their notes. Do NOT use to delete anything on your own, or as a substitute for the publishing check.
How to install second-brain-privacy
npx skills add undefined-ui/second-brain-os# or add only this skill to Claude Code: copy the folder
skills/second-brain-privacy/
# into
~/.claude/skills/second-brain-privacy/ (all projects)
.claude/skills/second-brain-privacy/ (one project)
1# Audit privacy23A mature vault is one of the highest-signal documents about a person that4exists, and it lives in a folder that gets synced, committed, backed up and5occasionally shared. Every copy is another place the content exists.67## Core rule89Find and report. Delete nothing without an explicit instruction naming what to10remove.1112## Workflow13141. **Scan for credentials:** API keys, tokens, passwords, connection strings.15 Check `.obsidian/plugins/` too, where plugin data lives.162. **Find other people's information:** meeting transcripts, personal messages,17 anything told in confidence, health or financial detail about someone else.183. **Find confidential work:** material under NDA or employer restriction.194. **Check the git remote.** Private material in a public repo is the most20 expensive version of this problem.215. **Report by severity,** with the specific file and why.2223## Output format2425```26Critical: <credentials, must be removed and rotated>27High: <other people's private information>28Review: <material the user should decide about>29Repo visibility: <public | private> - <verdict>30```3132## Calibration3334Never quote the credential itself in the report. Name the file and the type.3536Redaction after ingest is unreliable, because material has already propagated37into concept pages and links. When something should not be there, say what else38would need removing with it.
Excerpt shown under the repository's MIT license.
More skills in second-brain-os
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
