agentleFS
teodstrteodstr/workbench/skills/retrospective/SKILL.md

retrospective

Skill0 starsChanged yesterdayMITView on GitHub

Learn from a project or a phase without blaming anyone: gather the facts and a timeline, find what went well and what did not, dig into the causes, and turn them into a few concrete changes with owners, then close the project properly (handover, documents, thanks). Use at the end of a project, after a milestone, after a failure or an incident, or when the same problems keep coming back. Triggers: "retrospective", "lessons learned", "post-mortem", "what went wrong", "project closure", "retour d'expérience", "bilan de projet", "leçons apprises", "clôture du projet", "retrospectiva", "lecciones aprendidas", "cierre del proyecto".

73 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use dev-story, team-level and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    dev-story

    Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), routes to the right programmer agent for the system and engine, implements the code and test, and confirms each acceptance criterion. The core implementation skill — run after /story-readiness, before /code-review and /story-done.

    Also in 12 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 12 projects that use this

  • CoralGameSkill

    team-narrative

    Orchestrate the narrative team: coordinates narrative-director, writer, world-builder, and level-designer to create cohesive story content, world lore, and narrative-driven level design.

    Also in 12 projects that use this

  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 11 projects that use this

  • +7 more from lilangMax
  • +1 more from CoralGame

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 62 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the same problems come back from one project to the next.

    line 22
  2. Very specific:

    Not to rescue a project that is still running late: use project-recovery.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 62 edited versions of this file we could read. “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

Retrospective

A retrospective is only useful if it changes how the next project runs. This skill follows the structure Derby and Larsen describe (set the stage, gather data, generate insights, decide what to do, close) and ends with a few changes that someone owns.

When to use

  • At the end of a project, after each phase of a long one, or after an incident.
  • When the same problems come back from one project to the next.
  • Not to rescue a project that is still running late: use project-recovery.

Inputs

  1. The plan, the final dates and costs, the status updates.
  2. The people involved, and their perspectives.
  3. What was promised to clients, partners or family.

Method

  1. Set the stage: the goal is to learn, not to blame. Assume that everyone did their best with what they knew at the time.
  2. Gather the facts: a timeline of key events, planned versus actual (dates, budget, scope), and what each person noticed.
  3. Find what worked and what did not, then dig into the causes of the main problems by asking "why" several times until the cause is something that can be changed.
  4. Decide on a few changes: two or three, each with an owner and a date, and the way to check next time that it helped.
  5. Close the project: confirm the deliverables are accepted, hand over to whoever maintains the result, archive the documents and the decision log, settle the last invoices, thank the people involved.
  6. Share the lessons where the next project will find them.

Output

### Retrospective: <project or phase> (<date>)
Planned vs actual: dates … | budget … | scope …
Timeline: …
Worked well: … | Did not work: …
Causes: …
| Change | Owner | By | How we check |
|---|---|---|---|

### Closure checklist
Deliverables accepted | Handover done | Documents archived | Invoices settled | Thanks sent

Quality bar

  • Facts and the timeline come before opinions.
  • Causes are dug into, and nobody is blamed.
  • Two or three changes with owners and dates, not a long wish list.
  • The project is formally closed: handover, documents, invoices, thanks.
  • Written in the user's language, with the terms below.

Terminology

EnglishFrançaisEspañol
RetrospectiveRétrospectiveRetrospectiva
Lessons learnedRetour d'expérience, leçons apprisesLecciones aprendidas
Root causeCause racineCausa raíz
BlamelessSans recherche de coupableSin culpables
Project closureClôture du projetCierre del proyecto
HandoverPassationTraspaso

Sources

  • Derby, E., & Larsen, D. (2006). Agile Retrospectives: Making Good Teams Great. Pragmatic Bookshelf.
  • Kerth, N. L. (2001). Project Retrospectives: A Handbook for Team Reviews. Dorset House.

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.