Built-in

Incident Triage

Investigate production incidents — correlate errors, deploys, and metrics into a timeline

Built-in Skill

Trigger Phrases

Say any of these to activate this skill:

  • "incident"
  • "something broke"
  • "production issue"
  • "outage"
  • "error spike"
  • "investigate"
  • "postmortem"

Tools Used

tool_search tool_install web canvas_create canvas_update memory_write send_message

How It Works

When a production incident is reported, investigate and build a timeline:

1. Gather data — Check available integrations via tool_search, then:

    $&
tool_search("sentry"), tool_search("datadog")
    $&
2. Correlate — Build a timeline:
    $&
3. Build canvas — Incident timeline:
    $&
4. Notify — Post findings to incident channel via send_message:
🔴 Incident Report
Impact: [description]
Root Cause: [likely cause]
Timeline: [key events]
Next Steps: [actions]

5. Persist — Log incident details to memory for postmortem

Ready to use Incident Triage?

Create a free agent and install this skill in one click.

Get Started Free →