diagnose
SolidUse when an AI Brain vault needs a health check or something feels off: Claude ignores CLAUDE.md, journal entries missing from /weekly, hooks not firing, something broke after a git pull, a friend's install misbehaves, Obsidian crashes or pegs the CPU, a .claude/worktrees folder appeared, Granola/WhatsApp/Slack/Gmail notes stopped arriving, or Windows .ps1 scripts error. Also after major /setup-brain upgrades. Not for debugging code; audits the vault install only.
Install
Quality Score: 81/100
Skill Content
Details
- Author
- mycelium-hq
- Repository
- mycelium-hq/ai-brain-starter
- Created
- 5 months ago
- Last Updated
- yesterday
- Language
- Python
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
skilldoctor
Diagnose the Claude Code skills installed on this machine — why one never triggers, and whether Claude can see it at all. Use when the user says a skill isn't firing, isn't triggering, or is being ignored; asks to check, audit, or debug their skills; mentions the skill description budget, truncated skills, or duplicate skills; or asks whether a skill they installed is safe to trust. Runs a deterministic CLI over every installed skill at once, so it catches whole-system problems no single-file check can see.
diagnose
Self-diagnosis skill for 5dive agents. Trigger this skill whenever the user says something is broken, not working, or behaving unexpectedly — or when any tool or command exits with an error. Runs a structured health check covering auth state, service health, disk, memory, recent CLI errors, and skill integrity. Surfaces a root-cause summary so the agent can fix the problem itself instead of asking the user. Also exposes a security audit sub-command for SSH keys, open ports, auth failures, and risky file permissions.
diagnose
When something feels off, type /diagnose and describe the symptom. The skill walks the seven-layer stack (kernel, skills, hooks, daemons, vault, doctrine, principal config) and reports which layer is most likely responsible. Caddy pattern applied to debugging.