agentsclimarketplace

Run retrospective

Skill alexe-ev/product-plugins/product-planning/skills/run-retrospective

Structure and facilitate a product or delivery retrospective to extract learning and improve team practices. Use this skill when a team needs to reflect on a completed cycle, launch, or experiment and turn observations into action.From its SKILL.md

Install
npx -y skills add alexe-ev/product-plugins --skill run-retrospective

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.6 KB, 514 tokens by cl100k_base, as published. Nobody here has run it

Run Retrospective

Purpose

Help teams run structured retrospectives that produce honest reflection, shared learning, and concrete improvement actions — not just feel-good discussions.

Skill type

Conceptual skill

Use this skill when

  • A sprint, quarter, launch, or experiment has completed and a retro is needed
  • A team retro produces low-value conversations and no follow-through
  • A post-mortem is needed after a failure or near-miss
  • A structured review is needed before starting the next planning cycle

Do not use this skill when

  • The goal is ongoing performance monitoring (use detect-performance-signals)
  • The goal is stakeholder communication about results (use communicate-decisions-tradeoffs)

Required inputs

  • Event or period being reflected on (sprint, launch, quarter, experiment)
  • Team involved

Optional inputs

  • Prior retro actions and their status
  • Relevant metrics or outcome data
  • Stakeholder feedback
  • Known issues going in

Upstream context

Works best when:

  • The period has a clear end point
  • Some outcome data or observations are available

Downstream handoff

Output can feed:

  • design-operating-cadence (retro findings → process improvements)
  • build-roadmap-prioritization (learning feeds next cycle)

Instructions

  1. Define the scope: what period or event is being reviewed?
  2. Gather data before the session: metrics, events, feedback.
  3. Select a retro format appropriate to the context:
    • What went well / what didn't / what to change (simple cycles)
    • Start / Stop / Continue (behavior-focused)
    • Timeline retro (complex launches or long cycles)
    • Post-mortem format (failures or incidents)
  4. Generate observations across all dimensions.
  5. Prioritize themes that most deserve action.
  6. Define specific, owned action items (owner + due date).
  7. Review prior retro actions before closing.

Output

Provide:

  • Scope and context summary
  • Format selected with rationale
  • Key observations organized by theme
  • Prioritized themes
  • Action items with owner and due date
  • Prior action item status (if applicable)
  • One "learning statement" capturing the most important takeaway

Risks / caveats

  • Retros without action items are venting sessions — always close with owned actions
  • Psychological safety is a prerequisite for honest retros — do not skip it
  • Review prior retro actions at the start, not the end

What ships with it: 4 files

6.4 KB alongside SKILL.md

Keep looking

Skills are one crate of 326,512. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.