Log Triage
SkillMonitoring & opsParse bot logs and Langfuse traces into a short incident digest — what broke, how often, and the likely cause. Use when the user asks why the bot errored, wants a summary of recent failures, is debugging a crash, or after heartbeat-monitor reports a red check.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Log Triage skill
What this skill tells your AI
The instructions your AI receives, as published by thesmokedev/taskchad-os in optional-skills/devops/log-triage/SKILL.md and read by ahel’s review.
Turn noisy logs into a ranked, human-readable incident digest.
Sources
- Bot log — the chat process log (e.g.
bot.log/ whereverrun_chat.shwrites). Start here. - Langfuse — if
LANGFUSE_*is configured, traces give per-request timing, model calls, and errors. See.claude/sections/08_*(observability).
Triage method
- Scope — last N hours, or since the last known-good marker.
- Extract errors — grep for
ERROR/CRITICAL/Traceback/Unhandled. - Cluster — group by normalized message (strip timestamps, IDs, paths) so "the same error 200 times" reads as one cluster with a count.
- Rank — by frequency × severity. The top 1–3 clusters are the headline.
- Diagnose — for each headline cluster: first seen, last seen, count, the representative stack frame, and a one-line hypothesis.
Output
🔧 Log triage — last <window>
1. <normalized error> ×<count>
first <ts> · last <ts>
at <file:line>
likely: <hypothesis>
2. ...
Quiet otherwise: <count> warnings, no other errors.
Keep it to the signal. Do not paste raw log spans — cite file:line and counts.
This skill is read-only; it diagnoses, it does not restart or patch.
Signals
- GitHub stars
- 24
- Forks
- 5
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
log-triage- Source
- github.com/thesmokedev/taskchad-os