agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/skills/retro-facilitation/SKILL.md

retro-facilitation

Skill0 starsChanged 18 days agoMITView on GitHub

Plan and run a retrospective after a launch, project, sprint, or incident, then turn what came out of it into a short list of changes with owners. Use when someone asks to run a retro, post-mortem, post-launch review, lessons learned session, or after-action review, wants retro questions or an agenda, or pastes retro notes and wants them made into actions.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If notes come in raw, group them into clusters before writing.

    line 51
  2. Distinctive:

    Every change is a specific behavior or process, not a value ("communicate better" is not a change.

    line 72
  3. Distinctive:

    No names attached to problems.

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Retro facilitation

A retro is worth the hour only if something changes afterward. Most retros produce a long list of feelings and no owners. This one ends with two or three changes someone has agreed to make.

Before you start

If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.

Step 1: Set it up

Confirm:

  • What we're looking back on: the project, launch, sprint, or incident, with dates
  • Who's in the room: everyone who did the work; leaders only if they won't stifle honesty
  • The goal: usually "decide what to keep doing and what to change next time"

Send a pre-read with the timeline of what happened (key dates, decisions, and outcomes), so the session doesn't spend 20 minutes reconstructing it.

Step 2: Run the session (60 minutes)

0:00  Set the tone (2 min)
      "We're here to improve how we work, not to find who's at fault."
0:02  Timeline check (8 min)
      Walk the pre-read. Fill in what's missing.
0:10  Silent writing (10 min)
      Everyone writes on their own:
      - What went well that we should keep
      - What got in the way
      - What surprised us
0:20  Share and group (15 min)
      Read out, cluster similar notes, name each cluster.
0:35  Pick what matters (10 min)
      Everyone votes for the 2 or 3 clusters most worth fixing.
0:45  Decide changes (13 min)
      For each top cluster: what will we do differently, who owns it, by when.
0:58  Close (2 min)
      Read back the changes and owners.

For incidents, replace "What surprised us" with "Where did we first see a sign, and what stopped us from acting on it?"

Step 3: Write it up

If notes come in raw, group them into clusters before writing. Keep people's exact words for the notes; don't soften them.

# Retro: [What] — [Date]
**Attendees:** [names]

## Keep doing
- [Cluster] — [one line]

## Changes we're making
| Change | Owner | By when | How we'll know it worked |

## Also came up (not acting on now)
- [Cluster] — [why parked]

## Timeline
[Short version from the pre-read]

Rules:

  • Two or three changes, maximum. Ten changes means none happen.
  • Every change is a specific behavior or process, not a value ("communicate better" is not a change; "post launch status in the launch channel every Monday" is).
  • No names attached to problems. Name owners only on changes.
  • At the next retro, start by checking whether last time's changes happened.

Related skills

  • meeting-to-action-converter — turn retro notes into owned changes
  • process-documentation — write the change into the process
  • decision-log — look back at what was decided

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.