wave-postmortem

Generate structured wave postmortem reports from milestone execution artifacts.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/ahlerjam/mmp --skill wave-postmortem
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wave-postmortem
Source: https://github.com/ahlerjam/mmp/tree/main/skills/wave-postmortem
Command: npx skills add https://github.com/ahlerjam/mmp --skill wave-postmortem

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It turns messy, multi-phase milestone execution artifacts into a consistent, decision-ready wave postmortem with drift classification and actionable follow-ups.

Core Features & Use Cases

  • Wave report generation: Reads orchestrator status, an audit event stream, and optional per-agent reflexion history to produce a structured markdown report.
  • MAST drift classification: Maps audit events to canonical MAST clusters using the repository’s failure-mode vocabulary to keep terminology consistent.
  • Issue-recommendation gating: Optionally creates GitHub follow-up issues (if gh is available) based on the recommendations contained in the generated report.

Quick Start

Run /mmp:wave-postmortem to generate the wave postmortem report from the orchestrator wave state.

Frequently Asked Questions about wave-postmortem

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a structured postmortem report from milestone execution artifacts?

You can generate a wave retro report by running the wave-postmortem command on your milestone execution artifacts. It reads orchestrator status, audit event streams, and optional agent reflexion history to produce a structured markdown report.

What is MAST classification for drift classification in retrospection workflows?

MAST classification maps audit events to canonical failure-mode vocabulary clusters during retrospection workflows. It ensures consistent terminology across wave postmortem reports by standardizing how milestone execution drift and failures are categorized.

How do I create follow-up GitHub issues from wave postmortem recommendations?

To create follow-up GitHub issues from postmortem recommendations, the gh command-line tool must be available and explicitly enabled. The skill gates issue creation, automatically generating GitHub issues based on recommendations contained in the generated report when configured.

Can I run retrospection on archived milestone waves instead of live ones?

Yes, you can run retrospection on archived milestone waves. The skill selects the correct state input by using specific wave IDs or live/archive flags, allowing you to generate deterministic postmortem reports from either live or archived wave data.

What's the best way to classify audit events for milestone management reports?

The best way to classify audit events for milestone management reports is using canonical MAST vocabulary. Mapping events to these predefined failure-mode clusters keeps terminology consistent and turns messy execution artifacts into decision-ready postmortem data.

Do I need the gh CLI installed to generate wave postmortem reports?

No, you do not need the gh CLI installed to generate wave postmortem reports. The gh command-line tool is only required optionally for creating follow-up GitHub issues, and this feature must be explicitly enabled in your configuration.