Name: incident-debug
Author: xmindlab-heicode

Imported from xmindlab-heicode/heicode-sk-hub (skills/incident-debug/SKILL.md). Install upstream with npx skills add xmindlab-heicode/heicode-sk-hub --skill incident-debug. Copyright stays with the author.

Incident Debug

Run evidence-based investigation. Do not guess or stack random fixes.

Workflow

State the incident symptom and impact.
Establish timeline: when it started, what changed, who is affected.
Reproduce or capture logs from the failing path.
Trace request/data flow across component boundaries.
Form one hypothesis at a time.
Test the hypothesis with the smallest safe check.
Apply a minimal fix only after root cause is identified.
Verify externally and internally.
Write a concise incident note.

Output

Status:
Impact:
Timeline:
Evidence:
Root Cause:
Fix:
Verification:
Follow-ups:

Rules

Separate facts from hypotheses.
Record commands and exact timestamps when possible.
Avoid restarts or destructive actions until the likely impact is clear.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Install incident-debug and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "xmindlab-heicode-heicode-sk-hub-incident-debug", "kind": "skill", "name": "incident-debug", "description": "Use when investigating production incidents, regressions, outages, failed integrations, or unexpected behavior.", "publisher": "xmindlab-heicode", "version": "1.0.0", "capabilities": { "domains": [ "coding" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Use when investigating production incidents, regressions, outages, failed integrations, or unexpected behavior." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/xmindlab-heicode/heicode-sk-hub", "path": "skills/incident-debug/SKILL.md", "ref": "656d232db3050b73e4d4cedca70bfd5005ad1303", "url": "https://github.com/xmindlab-heicode/heicode-sk-hub/blob/656d232db3050b73e4d4cedca70bfd5005ad1303/skills/incident-debug/SKILL.md", "key": "xmindlab-heicode/heicode-sk-hub/skills/incident-debug/SKILL.md" } }, "instructions": "# Incident Debug\n\nRun evidence-based investigation. Do not guess or stack random fixes.\n\n## Workflow\n\n1. State the incident symptom and impact.\n2. Establish timeline: when it started, what changed, who is affected.\n3. Reproduce or capture logs from the failing path.\n4. Trace request/data flow across component boundaries.\n5. Form one hypothesis at a time.\n6. Test the hypothesis with the smallest safe check.\n7. Apply a minimal fix only after root cause is identified.\n8. Verify externally and internally.\n9. Write a concise incident note.\n\n## Output\n\n```text\nStatus:\nImpact:\nTimeline:\nEvidence:\nRoo", "cost": { "context_tokens": 204 } }

incident-debug

About

Incident Debug

Workflow

Output

Rules

Use it

Install incident-debug and it becomes one more candidate the router can pick - when it fits.

Manifest

Reviews