When your Agent Monitor dashboard is empty and you're wondering if Claude Code hooks are even firing, this runs through the checklist: checks if all seven hook types are registered in settings.json, verifies the handler script exists and is executable, tests dashboard connectivity on port 4820, sends a test event to confirm delivery, and checks if events are actually making it into the database. You get a pass/fail report with specific fixes for whatever's broken. It's basically the troubleshooting runbook you'd write yourself after debugging hook integration issues three times, now automated so you don't have to manually curl endpoints and grep config files.
npx -y skills add hoangsonww/claude-code-agent-monitor --skill hook-diagnostics --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
kubesphere/kubesphere
supercent-io/skills-template