
gbrain Advisor
Coaches you on getting more from your gbrain setup, with read-only checks and asks before any fix
- Repository
- garrytan/gbrain
- Stars
- 31,447
- Licence
- MIT
- Files
- 1 file
What it does
This skill teaches an AI agent to run the gbrain advisor command, which reads the state of a personal knowledge brain and ranks suggested actions such as version updates, pending migrations, stalled jobs, low embedding coverage and missing skills. The agent then summarizes the most important items in plain language, shows the exact fix command, and asks before doing anything. It can also run on a weekly schedule to give a checkup, reporting only new or critical items.
Great for
- Developers and power users who run a gbrain instance and want a periodic health check
- Teams maintaining a shared gbrain setup who want the most important maintenance items surfaced
- Users who want a weekly reminder to review their brain's configuration
Skip it if
- People who do not use gbrain, since the advisor only reads gbrain state
- Situations where an agent should fix issues automatically: the skill is designed to require explicit user approval, and an automated --apply path would bypass that intent if misconfigured
- Brains that cannot be reached: the skill defers to a separate db-repair skill in that case rather than reporting a clean result
Try asking
- “Is my brain set up right?”
- “What should I do to get more out of gbrain?”
- “Run my weekly brain checkup and tell me only what's new”
- “Advise me on my brain and show the fix commands”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
gbrain-advisor.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip gbrain-advisor.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip gbrain-advisor.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 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
- Ask the agent to show the fix command first and approve each one individually rather than approving in bulk
- Set up the weekly cron recipe only if you want proactive pings, and check the schedule and prompt it creates
- Review the local run history if you want to see what changed between checkups
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.