create-delivery-postmortem

Post-Mortem Create Skill

Facilitate writing a structured post-mortem document for release delays and delivery incidents. The skill gathers context from the user, synthesizes narrative sections, facilitates an interactive Five Whys root cause analysis, and produces an executive-ready document.

Arguments

• title (required): Short incident name (e.g., "ROCm RPM Delay")
• release (optional): Target release milestone (e.g., "3.5 EA2", "4.0 GA")
• priority (optional): critical / high / medium / low
• format (optional, default: html): Output format — html or markdown

Example: /create-delivery-postmortem title="ROCm RPM Delay" release="3.5 EA2" priority="high"

Steps

When invoked:

Phase 1: Context Gathering

1. Prompt for context. Tell the user what input is most valuable, in this order of usefulness:

   1. Slack threads or conversations — paste directly. These are the richest source for building timelines and identifying who knew what and when.
   2. JIRA ticket IDs — look these up for context (committed dates, status changes, comments).
   3. Committed delivery dates — when was something promised, and by whom?
   4. Key people involved — who owned the deliverable, who raised the risk, who responded.
   5. Meeting notes or email excerpts — especially anything documenting commitments or escalations.
   6. Free-form narrative — the user's own understanding of what happened.

   Say: "Paste whatever you have — Slack threads, JIRA ticket IDs, notes, narrative. The most useful things are conversations that show when risks were raised and committed delivery dates. Send as many messages as you need. Say 'done' when you've shared everything."

   Accept input across multiple messages until the user signals completion.

2. Synthesize narrative sections. From the gathered context, draft:

   • Postmortem Summary: Incident name, author (from git config user.name, confirm with user), priority, target release.
   • Executive Summary: One paragraph — what happened, what the impact was, what was learned. Written for a Director-level audience who needs the picture in 30 seconds.
   • Leadup: Sequence of events leading to the incident. Use specific dates and actors.
   • Impact: Potential or observed delivery impact. Be specific about what was delayed, by how long, and what downstream was affected.
   • Detection and Timeline: When the team detected or raised the risk. Name people, communication channels (Slack, email, meeting), and timestamps.
   • Response: Who responded and what was done at each stage. Include delays or obstacles to responding. Be specific about handoffs.
   • Recovery: When the incident was resolved. Describe how time-to-mitigation could have been improved.