Troubleshooting
Unified skill for when things break — in development or in production.
Workflow Routing
| Request Pattern |
Route To |
| Debugging, fix bug, error recovery, troubleshooting, reproduce bug, root cause, stack trace, test failing, build broken |
Debugging/SKILL.md |
| Incident, outage, SEV1, SEV2, postmortem, blameless review, incident response, war room, 5 whys, incident timeline |
Incident/SKILL.md |
Examples
Example 1: Debug a failing test
User: "This test is failing intermittently"
→ Routes to Debugging
→ Non-reproducible bug playbook: isolate, instrument, competing hypotheses
Example 2: Production incident
User: "The API is returning 500s in production"
→ Routes to Incident
→ New incident workflow: triage, mitigate, communicate, resolve
Example 3: Post-incident review
User: "Write a postmortem for yesterday's outage"
→ Routes to Incident/Postmortem
→ Blameless review: timeline, contributing factors, action items
1---2name: troubleshooting3description: Debugging and incident management — 6-step triage, Stop-the-Line, competing hypotheses for dev-time bugs plus incident detection, response, and blameless postmortems for production issues. USE WHEN debugging, fix bug, error recovery, troubleshooting, reproduce bug, root cause, stack trace, test failing, build broken, incident, outage, SEV1, SEV2, postmortem, blameless review, incident response, 5 whys.4---56# Troubleshooting78Unified skill for when things break — in development or in production.910## Workflow Routing1112| Request Pattern | Route To |13|---|---|14| Debugging, fix bug, error recovery, troubleshooting, reproduce bug, root cause, stack trace, test failing, build broken | `Debugging/SKILL.md` |15| Incident, outage, SEV1, SEV2, postmortem, blameless review, incident response, war room, 5 whys, incident timeline | `Incident/SKILL.md` |1617## Examples1819**Example 1: Debug a failing test**20```21User: "This test is failing intermittently"22→ Routes to Debugging23→ Non-reproducible bug playbook: isolate, instrument, competing hypotheses24```2526**Example 2: Production incident**27```28User: "The API is returning 500s in production"29→ Routes to Incident30→ New incident workflow: triage, mitigate, communicate, resolve31```3233**Example 3: Post-incident review**34```35User: "Write a postmortem for yesterday's outage"36→ Routes to Incident/Postmortem37→ Blameless review: timeline, contributing factors, action items38```
mj-deving