postmortem

Convert merged pull request review comments into lessons and skillbase updates.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you capture what reviewers actually caught in a merged PR and convert that signal into concrete improvements, so the same issues don’t repeat in future changes.

Core Features & Use Cases

  • PR review-to-lessons analysis: Detects the merged PR, fetches metadata, review comments, and review summaries, then extracts actionable lessons that indicate missing skills, specialists, or checklist coverage.
  • Pattern-to-routing diagnosis: Classifies findings into pattern-violation vs correctness-bug tracks, then directs the postmortem into the appropriate diagnosis path (specialist vs logic reviewer).
  • Self-improving skillbase: Cross-references existing skills/specialists, edits the relevant skill/specialist files to close gaps, and produces a structured report with patterns found, changes made, and judgment-needed items.

Quick Start

Run the postmortem after a PR merges by asking it to run a postmortem for that PR, e.g., “Run a postmortem for PR 1234.”

Frequently Asked Questions about postmortem

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

FAQPage Schema
How do I turn merged GitHub pull request review feedback into actionable lessons?

To turn merged GitHub PR review feedback into actionable lessons, run a postmortem that fetches PR metadata and comments, extracts missing skills or checklist gaps, and updates your skillbase with concrete fixes.

What is the best way to audit pull request review comments after a merge?

The best way to audit PR review comments after merge is to run a postmortem that fetches review signals, classifies findings into pattern-violation or correctness-bug tracks, and routes the diagnosis to the correct specialist or logic reviewer.

Can I extract human vs bot review signals from GitHub PR comments?

Yes, you can extract human vs bot review signals from GitHub PR comments. The postmortem process uses gh to discover the PR, fetches metadata and review summaries, then separates human feedback from bot signals for gap identification.

How do I detect recurring patterns in GitHub PR review feedback across multiple merges?

You can detect recurring patterns in GitHub PR review feedback by running a postmortem that classifies findings into pattern-violation versus correctness-bug tracks, then cross-references existing skills and specialists to identify structural gaps.

How do I route GitHub PR postmortem findings to the correct specialist?

To route GitHub PR postmortem findings to the correct specialist, the process classifies each finding into a pattern-violation or correctness-bug track, directing pattern issues to specialists and logic issues to logic reviewers for targeted fixes.

Do I need the gh CLI to run a postmortem on a merged pull request?

Yes, you need the gh CLI to run a postmortem on a merged pull request. The postmortem requires GitHub PR discovery via gh to fetch metadata, review comments, and review summaries before extracting actionable lessons.