Skip to content

Company Brain Sanitizer

Strips sensitive HR and personal data from a personal brain to make a safe shared team brain.

Repository
garrytan/gbrain
Stars
31,447
Licence
MIT
Files
1 file

What it does

This skill teaches an AI agent to turn a personal knowledge base (a 'brain' of notes, people pages, meeting notes and daily logs) into a version safe to share with a team. It searches the brain for internal ratings, compensation, performance assessments, departure or retention talk, management strategy, political dynamics and personal details, then removes or edits them while keeping professional identity, projects, career history and expertise. It also checks git history for old sensitive versions and can run as a report-only audit of an existing shared brain.

Great for

  • Founders or executives who want to share a personal brain with their team without leaking HR-sensitive notes
  • Teams auditing an existing shared brain for content that should not be there
  • Maintainers of the gbrain project who need a repeatable sanitization workflow

Skip it if

  • Simply connecting or importing an existing company repository: the skill says that is a different workflow and that stripping metadata is not needed for that; using this skill there could delete useful content
  • Anyone expecting a guaranteed, fully automatic redaction: the skill itself says judgment calls are made per file and bulk passes can look finished while still leaking, so manual review is required
  • Purging git history on a repository others depend on: history rewriting is destructive and can break collaborators' copies

Try asking

  • “Audit the shared team brain and report any pages that still mention compensation or performance concerns”
  • “Sanitize my personal brain so I can share it with my new team, starting with 3-5 files for review”
  • “Scrub employee data from meeting notes and daily logs in the brain repo”
  • “Check that no page still links to sections that were removed”
Step-by-step guide: how to use Company Brain SanitizerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    company-brainify.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip company-brainify.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip company-brainify.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run it first as a report-only audit to see what would be removed before any edits are made
  • Review the first 3-5 sanitized files yourself before allowing bulk changes
  • Keep a backup of the brain repo before any git history purge, since that step is destructive and needs explicit confirmation

What's inside

  • SKILL.md

Redistributed unmodified from garrytan/gbrain under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.