agentleFS
ShiningPlagueShiningPlague/shiningplague-studio/skills/retrospective/SKILL.md

retrospective

Skill0 starsChanged 4 months agoMITView on GitHub

Use at sprint end, after completing a major milestone, or when designer says 'retro', 'retrospective', 'sprint review', 'what worked / what didn't'. ShiningPlague-adopted: full implementation that routes retrospective output to docs/devlog.md (single change-log + retro record), updates sprint-status.yaml to closed, sprint-type aware.

69 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use soak-test and team-live-ops.

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

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 58 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add a new section to docs/devlog.md:

    line 54
  2. Very specific:

    After retro lands, propose firing /sprint-plan for next sprint OR /gate-check if a phase transition is the natural next step.

    line 93
  3. Distinctive:

    After major milestone (phase transition, release)

    line 98
  4. Very specific:

    After firing, if sprint closed → propose /sprint-plan new for next sprint

    line 104
  5. Very specific:

    If phase transition opportunity → propose /gate-check <phase>

    line 105

“Common” is measured: kept by at least 6 in 10 of the 58 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

🌱 ShiningPlague-adopted. Originally Donchitos (barebones stub); battle-tested on a shipped Godot project. Upstream was a pointer-only file; the studio version is the full implementation that routes retrospective output INTO docs/devlog.md rather than creating separate files.

If an artifact named here is absent: say so plainly in one line, skip that step, and continue. Never invent the file to satisfy a checklist, and never fail a close because an optional artifact was never created.

Devlog routing (studio rule)

Retrospective output gets appended to docs/devlog.md under a dated section, not to a separate retrospectives folder.

Why: hard-won rule — docs/devlog.md is the single canonical change log. Retrospectives route INTO devlog so the doc stack stays consolidated: one canonical change-log + retro record per file. Avoids parallel docs.

Procedure

Step 1: Read sprint state

  • production/sprint-status.yaml — current sprint metadata + story states
  • production/sprints/sprint-<N>-*.md — sprint plan + acceptance criteria
  • Git log since sprint start — commits, what shipped
  • docs/open-flags.md — flags raised during sprint
  • production/qa/bugs/ — bugs found during sprint

Step 2: Synthesize retro themes

For each prompt, gather observations from the sprint:

  • What worked — 3-5 things that went smoothly + reasons
  • What didn't work — 3-5 things that struggled + root causes
  • Surprises — what came up that wasn't planned
  • Action items — concrete changes for next sprint
  • Velocity / metrics — stories closed, blocked, deferred

Step 3: Append to devlog.md

Add a new section to docs/devlog.md:

## YYYY-MM-DD — Sprint <N> Retrospective: <Sprint Focus>

**Sprint:** <N> · **Type:** Foundation/Adoption | Production | Polish · **Duration:** YYYY-MM-DD → YYYY-MM-DD

### What worked
- ...
- ...

### What didn't work
- ...
- ...

### Surprises
- ...

### Action items for next sprint
- [ ] <action>
- [ ] <action>

### Velocity
- Stories planned: N · Closed: N · Blocked: N · Deferred: N
- Major commits: <list>
- Bugs found: N · Resolved: N

### Open carry-overs
- Stories that didn't close: <list with reasons>

Step 4: Update sprint-status.yaml

  • Mark current sprint as status: closed
  • Add retrospective_logged: docs/devlog.md#<anchor>
  • Note any stories carrying to next sprint

Step 5: Propose next sprint

After retro lands, propose firing /sprint-plan for next sprint OR /gate-check if a phase transition is the natural next step.

When to fire

  • End of any sprint (story status: all closed or carried)
  • After major milestone (phase transition, release)
  • Designer says "let's reflect", "what worked", "retro"
  • Auto-fire opportunity: as part of /session-close if a sprint closed that session

Cross-skill awareness

  • After firing, if sprint closed → propose /sprint-plan new for next sprint
  • If phase transition opportunity → propose /gate-check <phase>
  • Chain into /update if devlog needs broader project sync

Failure modes

  • ❌ Creating retrospective in separate file when devlog.md exists — violates the consolidation rule
  • ❌ Skipping sprint-status.yaml update — leaves sprint state stale, /help misreports
  • ❌ Vague retros ("things were OK") — concrete items only, or skip
  • ❌ Firing too early (mid-sprint) — wait until natural sprint end OR designer explicitly invokes early

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.