
Skillpack Health Check
Lets an agent report whether a gbrain install is healthy and list suggested repairs without running them
- Repository
- garrytan/gbrain
- Stars
- 31,447
- Licence
- MIT
- Files
- 1 file
What it does
This skill teaches an AI agent to run the gbrain command-line tool's health check and read back a structured report saying whether the gbrain setup is working. When something is wrong, the agent lists the suggested fixes for you to review, and it is designed not to carry them out on its own. It is meant to be used by a scheduled daily check or when you ask whether gbrain is healthy.
Great for
- Developers running gbrain who want a daily or CI health signal
- Users of an OpenClaw-style agent who want a one-line status in a morning briefing
- Operators debugging jobs that stopped running or a brain that stopped updating
Skip it if
- Anyone without gbrain installed, since the skill only wraps the gbrain command and does nothing useful otherwise (the skill itself does not make repairs)
- Situations where you want the agent to automatically fix problems, because the skill explicitly requires separate approval before any repair runs and may not fit fully hands-off operation
- Non-technical users who do not have a command line set up, since it depends on a shell and the gbrain binary
Try asking
- “Is gbrain healthy?”
- “Run a skillpack check and tell me if anything needs attention.”
- “The brain has not been updating; check the brain and list any suggested repairs without running them.”
- “Run the gbrain health check in quiet mode for my morning briefing.”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
skillpack-check.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip skillpack-check.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip skillpack-check.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
- Use the quiet flag in scheduled jobs so the full JSON report does not appear in every email or briefing.
- Review the listed actions before approving any of them, since some change the brain, host files or service installation, and some may spend money on embeddings.
- If the command exits with code 2, treat it as urgent and first confirm gbrain is installed and on PATH.
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.