Skip to main content
ClaudeWave
ES, Spanish
Skill755 estrellas del repoactualizado 8d ago

iterate-retrospective

# iterate-retrospective This Claude Code skill facilitates and documents structured team retrospectives by capturing what went well, identifying improvement areas, and converting insights into concrete action items with owners and due dates. Use it at sprint ends, after project milestones, following incidents, or at regular intervals to build organizational learning and accountability for continuous improvement.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/product-on-purpose/pm-skills /tmp/iterate-retrospective && cp -r /tmp/iterate-retrospective/skills/iterate-retrospective ~/.claude/skills/iterate-retrospective
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
# Retrospective

A retrospective is a structured reflection that helps teams learn from their experiences and continuously improve. By regularly examining what went well, what didn't, and what to change, teams build a culture of learning and adaptation. The value isn't just in the discussion.it's in the documented actions and follow-through.

## When to Use

- At the end of every sprint (for agile teams)
- After completing a significant project or milestone
- Following a major incident or outage
- When team dynamics feel off and need addressing
- At regular intervals (monthly, quarterly) even without specific triggers
- When onboarding new team members to establish improvement culture

## When NOT to Use

- You want one durable learning banked for the organization -> use `iterate-lessons-log`; the retro is the ceremony, the log entry outlives it
- You are scoring an OKR cycle at close -> use `measure-okr-grader`
- The reflection must end in a pivot-or-persevere call -> use `iterate-pivot-decision`
- You need a recap of a general (non-retro) meeting -> use `foundation-meeting-recap`

## Instructions

When asked to facilitate or document a retrospective, follow these steps:

1. **Set the Context**
   Define what period or project this retrospective covers, who attended, and any significant events that occurred. This frames the discussion and helps future readers understand the context.

2. **Choose a Format**
   Select a retrospective format that fits the team's needs. Common options include:
   - **Start/Stop/Continue:** Simple and direct
   - **4Ls:** Liked, Learned, Lacked, Longed for
   - **Mad/Sad/Glad:** Emotion-focused
   - **Sailboat:** Visual metaphor (wind=helps, anchor=holds back)

3. **Gather Input**
   Collect observations from all team members. Ensure everyone contributes.quiet voices often have important insights. Group similar items to identify themes.

4. **Discuss and Prioritize**
   Don't try to address everything. Focus the discussion on the most impactful items. Vote or discuss to identify the top 2-3 issues to address.

5. **Define Action Items**
   Convert insights into specific, assignable actions. Every action needs an owner and a due date. Avoid vague improvements like "communicate better."

6. **Review Previous Actions**
   Check the status of action items from the last retrospective. Celebrate completions and discuss blockers for incomplete items. This builds accountability.

7. **Document for Future Reference**
   Capture the key points so they're available for future team members and for tracking patterns over time.

## Project Memory Contract

Active only when `.claude/pm-skills.local.md` exists. With no file, ignore this section entirely
and behave exactly as described above.

- **Reads:** the recent `artifacts[]` entries, so the retrospective can look at what the cycle actually produced instead of relying on recall.
- **Writes:** the lessons as an `interpretation` artifact.
- **Posture:** propose the entry and wait for confirmation before writing, unless
  `memory_auto_append: true` is set, in which case append and echo what was written.
- **Write discipline:** re-read the file immediately before writing, never from the copy that
  produced the proposal. If it changed in between, merge your entry into the current state and
  re-propose rather than overwriting; add only your own entry and leave every other field and
  section byte-identical. Nothing enforces this at runtime and the file is gitignored, so a
  careless whole-file write loses another session's work with no way to recover it.

A retrospective surfaces raw observations, patterns, and commitments at once. Record the durable half, the lessons, under a single tag; a downstream reader needs to know how firmly to weight the entry, and a mixed tag tells it nothing.
## Output Format

Use the template in `references/TEMPLATE.md` to structure the output. A complete retrospective fills every template section: Overview; Previous Retrospective Review; What Went Well; What to Improve; Discussion Notes; Action Items; Parking Lot; Metrics and Trends; Facilitator Notes; and Next Retrospective.

## Quality Checklist

Before finalizing, verify:

- [ ] All attendees had opportunity to contribute
- [ ] Both positives and improvements are captured
- [ ] Action items have owners and due dates
- [ ] Previous retrospective actions are reviewed
- [ ] A reader who missed the retro can tell what was decided and who owns each action from this document alone

## Examples

See `references/EXAMPLE.md` for a completed example.
chainSlash Command

Run an ad-hoc ordered chain of pm-skills with shared context (ephemeral; routes to the pm-workflow-orchestrator)

define-hypothesisSkill

Defines a testable hypothesis with clear success metrics and a validation approach. Use when forming assumptions to test or aligning a team on what success looks like, before any experiment is designed. To design the A/B test or experiment that will validate the hypothesis, use measure-experiment-design.

define-jtbd-canvasSkill

Creates a Jobs to be Done canvas capturing the functional, emotional, and social dimensions of a customer job. Use when deeply understanding customer motivations, designing for jobs, or reframing product positioning.

define-opportunity-treeSkill

Creates an opportunity solution tree connecting a desired outcome to customer opportunities and candidate solutions, preventing solution-first jumps in continuous discovery. Use when structuring scattered feature ideas or communicating how the roadmap traces to outcomes. For ranking an existing flat list of candidates, use define-prioritization-framework instead; this skill discovers the list, it does not score one.

define-prioritization-frameworkSkill

Run applicable prioritization frameworks (RICE, ICE, MoSCoW, Weighted Scoring, Kano) against a list of features or initiatives. Produces a comparison table showing where rankings agree and diverge across frameworks, and an executive summary with recommendation. Framework applicability is filtered by data availability; Kano requires customer research. Refuses to fabricate scores; produces an estimation scaffold when input data is missing.

define-problem-statementSkill

Creates a clear problem framing document with user impact, business context, and success criteria. Use when starting a new initiative, realigning a drifted project, or communicating up to leadership.

deliver-acceptance-criteriaSkill

Generates structured Given/When/Then acceptance criteria for a user story or feature slice, covering the happy path, key failure scenarios, and non-functional expectations in testable form. Use when turning requirements into verifiable scenarios for engineering handoff and QA sign-off. For a dedicated catalog of boundary conditions, error states, and recovery paths across a feature, use deliver-edge-cases; to write the stories themselves, use deliver-user-stories.

deliver-edge-casesSkill

Documents edge cases, error states, boundary conditions, race conditions, and recovery paths for a feature - the systematic catalog of what can go wrong and the failure modes to design for. Use during specification to map the failure surface and ensure comprehensive coverage, or during QA planning to identify boundary and limit scenarios to test. Distinct from deliver-acceptance-criteria, which writes story-level Given/When/Then checks; this skill produces the whole-feature edge-case catalog.