---
title: "retro"
description: "LLM-driven session retrospection. Detects friction in agent sessions and materializes learnings into correct destinations (personal rules, project rules, skill PRs, checkpoints, harness artefacts)."
canonical: https://agentpluginsdirectory.com/plugins/retro
last-updated: 2026-09-22
---

# retro
LLM-driven session retrospection. Detects friction in agent sessions and materializes learnings into correct destinations (personal rules, project rules, skill PRs, checkpoints, harness artefacts).
- Slug: retro
- Publisher: Netresearch DTT GmbH
- Repository: https://github.com/netresearch/retro-skill
- Manifest: plugin.json
- Version: 1.9.1
- License: (MIT AND CC-BY-SA-4.0)
- Category (editorial): agent-tooling
- Skills: 1 (retro)
- MCP servers: 0
- Stars: 6
- Repository created: 2026-05-12
- Repository last pushed: 2026-09-22
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/retro
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What retro does, in the publisher's words

LLM-driven session retrospection for Claude Code agents. After a session, /retro reads the conversation transcript, detects friction, and routes each finding to one of seven homes, with per-proposal approval and no silent writes.

> Where continuous friction-detection hooks pile up write-only noise nobody triages, /retro reads what actually happened and hands you a short list of approved, durable learnings, a global rule, project rules, or skill PRs.

- What it does
- Why
- Requirements
- Install
- A worked example
- The seven destinations

/retro analyzes the current Claude Code session directly from the conversation transcript, no continuous background hooks. It detects friction (tool errors, repeated mistakes, skills that should have triggered but didn't, convention violations), classifies each finding into exactly one of seven destinations, asking first who should own this truth, and materializes the approved learnings. Every write is gated behind explicit per-proposal approval.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/netresearch/retro-skill/HEAD/README.md

## Skills

- retro: Use when a Claude Code session ends or is declared finished, a friction needs fixing, a reusable learning needs capturing, local memory needs promoting upward, or for cross-session audits, detect friction AND learnings, route each to the right destination, and gate 'done'. Triggers: /retro, /retro…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.