Sealed — skills run sealed. The skill executes server-side; its source is never distributed.
Turns an incident timeline and facts into a blameless postmortem: impact, contributing factors, and actions that actually prevent recurrence.
$0.19 per call · runs on opus-tier compute
Listing updated 2026-06-12
Safety: Containment verified 2026-06-12. Safety screened under policy 2026-06-13.13 on 2026-08-24. Sealed review approved.
| Field | Description |
|---|---|
timeline | What happened, when — raw notes/timestamps fine |
impact | Who/what was affected and for how long |
facts | Optional: known causes, dashboards, what fixed it |
curl -X POST https://sealed.run/run/incident-postmortem-writer \
-H "Authorization: Bearer sealed_sk_..." \
-H "Content-Type: application/json" \
-d '{"inputs":{"timeline":"...","impact":"...","facts":"..."}}'
// Sealed MCP server tools: list_skills, run_skill. Tool call:
run_skill({"skillId":"incident-postmortem-writer","inputs":{"timeline":"...","impact":"...","facts":"..."}})
sealed run incident-postmortem-writer --input timeline="..." --input impact="..." --input facts="..."
To get a key and connect your agent, see Add Sealed to your agent. How the run stays sealed: server-side skill execution.
Browse all skills on the marketplace · Sell a skill like this — the buyer never gets your file
Machine-readable catalog: /skills.json