Skip to content
Get packs

Incident Commander

Guides outage response: severity levels, incident timelines, and post-incident reviews

Source Download skill
Repository
alirezarezvani/claude-skills
Stars
29,149
Licence
MIT
Files
15 files

What it does

This skill gives an AI agent a structured playbook for handling operational outages and degradations, such as a site going down or a failed deployment. Once installed, the agent can classify an incident as SEV1 to SEV4 based on user and business impact, help turn scattered logs and events into a clear timeline, and draft a structured post-incident review with communication templates for stakeholder updates. It is aimed at availability and reliability problems, not security attacks.

Great for

  • On-call engineers and SREs who need help organising a live outage response
  • Engineering leads writing post-mortems or post-incident reviews
  • Teams setting up incident and on-call practices for a new service

Skip it if

  • Security incidents such as ransomware, intrusions or data exfiltration; the README and SKILL.md direct these to a separate incident-response skill, because this one scores operational impact rather than attack types
  • Making authoritative severity or legal/regulatory decisions without human review, since the framework is generic and the agent's output should be checked against your organisation's own policies

Try asking

  • “Classify this outage: checkout API returning 500 errors for 40% of users since 14:05 and suggest a severity level and response team”
  • “Reconstruct a timeline from these log events and identify any gaps in the response”
  • “Draft a post-incident review for yesterday's failed deploy using the 5 Whys framework”
  • “Write a SEV2 initial stakeholder notification for a degraded search service”
Step-by-step guide: how to use Incident CommanderInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    incident-commander.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip incident-commander.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip incident-commander.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent concrete facts such as start time, affected user percentage and symptoms, since severity classification depends on them
  • Review the generated severity and communications against your organisation's official incident policy before sending them
  • Use the sample files in assets and expected_outputs to see the expected formats before feeding in your own data

What's inside

  • assets/incident_report_template.md
  • assets/runbook_template.md
  • assets/sample_incident_classification.json
  • assets/sample_incident_data.json
  • assets/sample_incident_pir_data.json
  • assets/sample_timeline_events.json
  • assets/simple_incident.json
  • assets/simple_timeline_events.json
  • expected_outputs/incident_classification_text_output.txt
  • expected_outputs/pir_markdown_output.md
  • expected_outputs/simple_incident_classification.txt
  • expected_outputs/timeline_reconstruction_text_output.txt
  • README.md
  • references/communication_templates.md
  • SKILL.md

Redistributed unmodified from alirezarezvani/claude-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.