Incident
Curated, sanitized export of 21 agent-skill packages for Claude Code and Codex, gated by an automated publication audit (no secrets, no local paths).
npx -y skills add mj-deving/pai-skills --skill IncidentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Incident management from detection through postmortem. USE WHEN incident, outage, SEV1, SEV2, production down, postmortem, blameless review, incident response, war room, incident update, status page, root cause analysis, 5 whys, incident timeline, on-call.
SKILL.md
2.5 KB, as published. Nobody here has run it
Incident
Manage incidents across 4 phases: Triage → Communicate → Mitigate → Postmortem.
Customization
Before executing, check for user customizations at:
${PAI_USER_DIR}/SKILLCUSTOMIZATIONS/Incident/
If this directory exists, load and apply:
PREFERENCES.md- Severity thresholds, escalation contacts, communication templates- Additional files specific to the skill
These define user-specific preferences. If the directory does not exist, proceed with skill defaults.
Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| New | "new incident", "production down", "SEV1" | Workflows/New.md |
| Update | "incident update", "status update" | Workflows/Update.md |
| Postmortem | "postmortem", "blameless review", "root cause" | Workflows/Postmortem.md |
Examples
Example 1: Start a new incident
User: "Production API is returning 500s for all users"
→ Invokes New workflow
→ Assesses severity, identifies affected systems
→ Produces triage summary + status update + communication draft
Example 2: Post a status update
User: "Update the incident — we identified the cause, it's a bad deploy"
→ Invokes Update workflow
→ Structures update with current status, actions taken, next steps
→ Outputs formatted status update ready to post
Example 3: Write postmortem
User: "Write the postmortem for yesterday's outage"
→ Invokes Postmortem workflow
→ Reconstructs timeline, runs 5 Whys analysis
→ Produces blameless postmortem with action items
Quick Reference
Severity Levels:
| Level | Criteria | Response Time |
|---|---|---|
| SEV1 | Total outage, all users affected | Immediate, all-hands |
| SEV2 | Major degradation, many users affected | < 15 min, on-call team |
| SEV3 | Partial degradation, some users affected | < 1 hour, assigned team |
| SEV4 | Minor issue, workaround available | Next business day |
Phases:
- Triage — Severity, impact, roles (IC, comms, responders)
- Communicate — Internal update, customer comms, war room cadence
- Mitigate — Steps taken, timeline tracking, resolution confirmation
- Postmortem — Blameless review, 5 Whys, action items with owners