agentleFS
Sign inStart free
kronus-techkronus-tech/kronus/.claude/skills/kronus-troubleshoot/SKILL.md

kronus-troubleshoot

Skill4 starsChanged 7 months agoMITView on GitHub

Diagnose and fix common Kronus issues — daemon, brain, dashboard, Telegram. Auto-invoked when user says "troubleshoot", "fix kronus", "kronus not working", "diagnose".

  • Reads credentials

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 10 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run a full Kronus health check and fix any issues found.

    line 9
  2. Distinctive:

    If not running: offer to start it

    line 17
  3. Distinctive:

    If running: report PID and uptime

    line 18
  4. Distinctive:

    Should return JSON with version and status

    line 24
  5. Distinctive:

    If down: daemon may need restart

    line 25
  6. Distinctive:

    Should return JSON with node counts

    line 31
  7. Very specific:

    If down: start with cd ~/.claude/daemon && bun run brain/src/index.ts & or check if brain-mcp is configured

    line 32
  8. Distinctive:

    Should have 10+ agents and 20+ skills

    line 56
  9. Very specific:

    If missing: re-run install.sh

    line 57
  10. Distinctive:

    Should exist and be non-zero size

    line 63
  11. Distinctive:

    If missing or corrupted: delete and re-scan

    line 64
  12. Distinctive:

    Ask: "Should I fix this? (y/n)" — use AskUserQuestion

    line 71
  13. Distinctive:

    Ask to proceed with AskUserQuestion

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Run a full Kronus health check and fix any issues found.

Diagnostics (run ALL of these)

1. Daemon Status

~/.claude/daemon/scripts/kronus-daemon.sh status
  • If not running: offer to start it
  • If running: report PID and uptime

2. Dashboard API

curl -s http://localhost:8420/api/status
  • Should return JSON with version and status
  • If down: daemon may need restart

3. Knowledge Graph (Brain)

curl -s http://localhost:4242/api/map
  • Should return JSON with node counts
  • If down: start with cd ~/.claude/daemon && bun run brain/src/index.ts & or check if brain-mcp is configured

4. Hub Server

curl -s http://localhost:3100/health
  • Optional — may not be running
  • If down: cd hub && bun run dev &

5. Telegram Config

cat ~/.claude/channels/telegram/.env
cat ~/.claude/channels/telegram/access.json
cat ~/.claude/channels/telegram/projects.json
  • .env must have TELEGRAM_BOT_TOKEN
  • access.json must have user IDs in allowFrom
  • projects.json maps groups to project paths

6. Agents & Skills

ls ~/.claude/agents/*.md | wc -l
ls -d ~/.claude/skills/*/ | wc -l
  • Should have 10+ agents and 20+ skills
  • If missing: re-run install.sh

7. Brain Database

ls -la ~/.kronus/brain.sqlite
  • Should exist and be non-zero size
  • If missing or corrupted: delete and re-scan

Fix Protocol

For each issue found:

  1. Explain what's wrong in plain language
  2. Show the fix command
  3. Ask: "Should I fix this? (y/n)" — use AskUserQuestion
  4. Apply the fix

If Daemon Restart Needed

  1. Tell the user: "The daemon needs to restart. Active Telegram sessions will reconnect automatically."
  2. Ask to proceed with AskUserQuestion
  3. Run: ~/.claude/daemon/scripts/kronus-daemon.sh restart
  4. Wait 3 seconds
  5. Verify: curl -s http://localhost:8420/api/status
  6. Report: "Kronus is back online. Dashboard: http://localhost:8420"

Output Format

KRONUS HEALTH CHECK
═══════════════════

✓ Daemon: running (PID XXXX, uptime Xh)
✓ Dashboard: http://localhost:8420 (v5.5)
✗ Brain: not running
  → Fix: cd brain && bun run src/index.ts &
✓ Hub: http://localhost:3100 (v5.3.0)
✓ Telegram: configured (X projects mapped)
✓ Agents: XX installed
✓ Skills: XX installed

Issues found: 1

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free