retro

Analyzes a work session to extract retention insights and durable learnings.

Updated Feb 20, 2026
One-click install
npx skills add https://github.com/supertyrelle/pelley --skill retro-supertyrelle
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: retro
Source: https://github.com/supertyrelle/pelley/tree/main/skills/retro
Command: npx skills add https://github.com/supertyrelle/pelley --skill retro-supertyrelle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns the end of a work session into a structured retrospective, helping you understand what went well, what slowed progress, and what should change next time. It also persists durable learnings so future sessions benefit from accumulated experience instead of repeating the same mistakes.

Core Features & Use Cases

  • Session analysis: Reviews recent git activity, backlog status, and conversation context to reconstruct what happened during the session.
  • Actionable reflection: Extracts keep, stop, and try-next-time learnings across velocity, quality, process, blockers, and discoveries.
  • Memory upkeep: Updates MEMORY.md with durable insights and captures concrete follow-up actions when they are ready to implement.
  • Use cases: Ideal for end-of-day wrapups, epic completion reviews, team process checks, and any moment when you want to turn recent work into reusable guidance.

Quick Start

Ask the retro skill to review this session and update project memory with the most important durable learnings.

Frequently Asked Questions about retro

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

FAQPage Schema
How do I run a retrospective on a git work session?

Run a session retrospective by analyzing recent git activity, backlog status, and conversation context to extract actionable keep, stop, and try-next-time learnings. This reconstructs the session to identify what slowed progress and what went well.

What is the best way to capture durable engineering learnings after a milestone?

Capturing durable engineering learnings after a milestone requires structured reflection on session velocity, quality, and blockers. Update project memory files to persist these insights so future sessions benefit from accumulated experience instead of repeating mistakes.

Can I analyze git activity and conversation context together for session review?

Yes, you can analyze git activity and conversation context together for session review. Reviewing both data sources alongside backlog status reconstructs what happened during the session, enabling actionable reflection on process blockers and discoveries.

Do I need a memory file to extract retrospective insights from an engineering session?

You need a memory file to persist durable insights extracted from an engineering session. Updating memory with keep, stop, and try-next-time learnings captures concrete follow-up actions and ensures future work benefits from accumulated experience.

What are the limitations of automated engineering session analysis?

Automated engineering session analysis relies on inspecting git activity, backlog status, and conversation context. Limitations include dependency on the accuracy of these inputs and the requirement for manual learning lifecycle checks for optional follow-up actions.