skills.rest
garrytan
garrytanCOMMUNITY
Explore all skills by this author →
Website𝕏@garrytanGitHub

company-brainify

Sanitize a personal knowledge brain into a shareable team brain by stripping sensitive content.

29.4k|4.4k|Updated Apr 5, 2026
Search Tags:#sanitization#data privacy#content audit#Knowledge Base#GBrain#git history purge#team brain
One-click install
npx skills add https://github.com/garrytan/gbrain --skill company-brainify
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: company-brainify
Source: https://github.com/garrytan/gbrain/tree/main/plugin/skills/company-brainify
Command: npx skills add https://github.com/garrytan/gbrain --skill company-brainify

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Personal knowledge bases accumulate sensitive material — compensation details, performance assessments, retention conversations, and candid opinions — that must be removed before the brain can be shared with a team. Clean working files alone are insufficient because git history and extracted facts still carry the sensitive versions.

Core Features & Use Cases

  • Full-scope sanitization: Scans people, meetings, dailies, companies, projects, and analysis directories plus takes, facts, and back-links, removing ratings, compensation, performance assessments, and political dynamics while preserving professional identity and work history.
  • Gated destructive operations: Fires data-loss-gate confirmation cards before bulk content stripping and before git history rewriting with force-push, requiring explicit typed consent.
  • Verification and re-audit: Verifies sanitization with grep passes and retrieval queries against the shipped tree, and supports report-only periodic re-audits of an existing shared brain.
  • Use Case: A founder wants to stand up a shared company brain from their personal brain. The skill copies the scanned scope into a staging directory, strips sensitive content, verifies the result, and exports it as a fresh repo with clean history — leaving the personal brain untouched.

Quick Start

Ask the agent to sanitize my personal brain into a team-safe company brain, stripping compensation and performance data before sharing it with the team.

Frequently Asked Questions about company-brainify

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I sanitize a personal knowledge base before sharing it with my team?▼

Run a full-scope scan across people, meetings, dailies, companies, projects, and analysis directories, then strip ratings, compensation, performance assessments, and political dynamics per file. Sanitize a staging copy rather than the personal brain, verify with grep and retrieval checks, and export as a fresh repo.

What content should be removed when creating a shared company brain?▼

Remove internal scores and ratings, compensation details, performance assessments, departure and retention notes, management strategy, internal political dynamics, and personal PII. Keep professional identity, current projects, career arc, professional beliefs, work timelines, and skills.

Why is cleaning working files not enough when sharing a git-based knowledge repo?▼

Git history retains every pre-sanitization version of cleaned files, so anyone with repo access can read the sensitive content from old commits. The skill purges history with git filter-repo after a mirror-clone backup, or exports a fresh repo with no prior history.

Does deleting sensitive facts with gbrain forget remove them from the brain?▼

No. gbrain forget only expires a fact — the row stays on the page struck through and remains served via --include-expired. Sensitive fact rows must be deleted from the page's Facts fence, re-synced, and the facts index reconciled, then verified with gbrain recall --grep.

Can I audit an existing shared brain for sensitive content without editing it?▼

Yes. The skill supports a report-only re-audit mode that re-runs the discovery and triage phases without edits, flagging new sensitive hits for human review. This suits periodic hygiene passes since sensitive data re-accumulates through meeting ingestion and enrichment pipelines.

Related Skills

Explore More Software Engineering Skills→
weipingweiping
1

webhook-transforms

Transform raw webhook payloads into sanitized markdown pages with citations.

Community
Intermediate
gaiastudio-aigaiastudio-ai
2

gaia-knowledge-refresh

Re-fetch ingested sources and apply hash-gated three-way reconciliation to update changed content.

Official
Advanced
ltdrewltdrew
1

maintain

Run automated health checks for stale pages, orphan pages, and dead links.

Community
Advanced
starlink-awakenstarlink-awaken

publish

Generate password-protected HTML documents from Markdown brain pages using AES-256-GCM encryption.

Community
Intermediate