Review a finished coding session for what slowed the agent down or let a mistake through, and turn one lesson into a test, check or doc in the project so the next session does not repeat it. Use when the user asks for a retro or retrospective, a post-mortem of a session, or "what should we change so this doesn't happen again". To carry unfinished work into a new session, use `handoff`; to prove a fix before claiming it, use `regression-proof`.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Retro
A retro improves the agent's **environment**: the checks, docs and pointers that the next session in this project will run into. It ends with one change made in the project, which the user reviews and commits. Credit and license: `LICENSE.md` in this folder.
## Steps
1. **Load the style guide.** Call the Skill tool with `writing-for-agents`. Every doc or rule this retro writes is read by an agent, and that skill says how to write one so it is followed the same way every run.
2. **Read the session.** Use the session the user names; with none named, use the current one. For an earlier session, read its transcript rather than working from memory: Claude Code keeps them as `.jsonl` files under `~/.claude/projects/<project slug>/`. Note each place the agent searched for a long time, made a mistake, retried, or lacked a fact it needed.
3. **Find candidates** in the categories below. Each candidate names the moment in the session (the tool call, the error, the retry) and the change that would have prevented it.
…
The line at the top of this page pins the label git:20261020.3008de9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_ibzh3ipfp4foccye
GET https://markdownregistry.com/api/v1/resolve?ref=ehnruiz/claude-skills/retro
GET https://markdownregistry.com/api/v1/blob/232315cd041c1eac9ec2f73ef41fc27f96b6e62f5c073134af003fa0508ead51
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
ehnruiz/claude-skills · skills/confluence-jira-links/SKILL.md · Link a Confluence page and the Jira tickets it is about, both ways, without duplicates - each ticket shown on the page…
ehnruiz/claude-skills · skills/diagnosing-bugs/SKILL.md · A disciplined loop for hard bugs, flaky tests and performance regressions - build a red-capable feedback loop first…
ehnruiz/claude-skills · skills/epic-review/SKILL.md · Review a Jira epic (or the Jira Product Discovery idea it implements) against its own In Scope list - which items are…
ehnruiz/claude-skills · skills/explain-the-number/SKILL.md · Like-for-like before a measured number is reported or credited to a change. Use before saying a change moved a score, a…
ehnruiz/claude-skills · skills/grilling/SKILL.md · Grill the user relentlessly about a plan, decision, or idea until every branch of it is settled. Use when the user…
ehnruiz/claude-skills · skills/handoff/SKILL.md · Write a handoff note so a fresh session can continue this one's work. Use when the user says to hand off, wrap up, or…
ehnruiz/claude-skills · skills/leader-1-1-prep/SKILL.md · Build a prep brief for a recurring 1:1 with a skip-level or senior leader. Pulls the last meeting's notes, the tickets…
ehnruiz/claude-skills · skills/llm-integration/SKILL.md · Checklist for code that calls a language model or exposes a system to one. Use when writing or reviewing code that…
ehnruiz/claude-skills · skills/no-ai-attribution/SKILL.md · Keep AI-assistant credit lines out of anything published on the user's behalf. Use before writing a commit message…
ehnruiz/claude-skills · skills/open-in-my-browser/SKILL.md · Open a link the user shares in their own Chrome through the Claude in Chrome extension, where their sign-ins and VPN…
ehnruiz/claude-skills · skills/pick-up/SKILL.md · Continue work from a handoff note an earlier session wrote. Use when the user says to pick up, continue or carry on…
ehnruiz/claude-skills · skills/plain-writing/SKILL.md · Draft text a person will send or post under their own name, in plain language that does not read as machine-written…
apmantza/pi-lens · .claude/skills/retro/SKILL.md · Run the pi-lens retrospective — turn a session, an incident, or a merged bug fix into environment changes (checks…
serejaris/personal-corp-os · templates/department/skills/retro/SKILL.md · Use when the user asks for "ретро", "обзор недели", or "что было за неделю" and the department needs a fact-based…
