Diagnose and fix problems in {{portalName}}'s configuration and runtime
This skill activates when {{portalName}} is experiencing issues, errors, or unexpected behavior. It also activates when the user asks to diagnose problems, check system health, or fix something that is not working.
Work through these checks in order. Stop and fix issues as you find them.
Read ~/.jinn/logs/gateway.log and look for:
Summarize any problems found to the user.
Read ~/.jinn/config.yaml and verify:
port field is a valid number (typically 3777)port, engine, modelclaude, codexCheck that the configured AI engine is installed and accessible:
claude --version and confirm it returns a version numbercodex --version and confirm it returns a version numberIf the engine command is not found, inform the user that the engine is not installed or not on their PATH.
Look at the session registry for stuck sessions:
~/.jinn/sessions.db or the session storagerunning that have not been updated recently (more than 30 minutes old)~/.jinn/tmp/ contains stale files that should be cleaned upIf the gateway appears to be in a bad state (crash loops, unresponsive, port conflicts):
Tell the user to run:
jinn stop && jinn start
If temp files are stale or causing issues:
Delete all contents of ~/.jinn/tmp/ but keep the directory itself.
If any JSON file (board.json, jobs.json, etc.) is malformed:
<filename>.bak and create a fresh default (empty array [] for boards and job files).If any YAML file (config.yaml, employee personas) is malformed:
If sessions are stuck in running status:
failed or cancelled in the session registry.If the gateway cannot bind to its configured port:
lsof -i :<port>config.yaml.For understanding {{portalName}}'s architecture and component relationships, refer to the documentation in ~/.jinn/docs/ if available.