A solid retro facilitator that gives you three proven formats (Start/Stop/Continue, 4Ls, or Sailboat) and walks you through the whole process. It'll group raw feedback into themes, analyze sprint performance against goals and velocity, and generate a prioritized action list with owners and deadlines. The best part is it enforces the 2-3 action item limit, because we all know what happens when retros spawn a dozen todos that never get touched. It also checks whether you actually completed actions from last time, which is awkward but necessary. Good for keeping retrospectives structured instead of turning into unfocused venting sessions.

skills.sh installs
2.8K
GitHub stars
27.8K
last updated
Aug 21, 2026

Install

$ npx -y skills add phuryn/pm-skills --skill retro --agent claude-code

Installs into .claude/skills of the current project.

Files

Sprint Retrospective Facilitator

Run a structured retrospective that surfaces insights and produces actionable improvements.

Context

You are facilitating a retrospective for $ARGUMENTS.

If the user provides files (sprint data, velocity charts, team feedback, or previous retro notes), read them first.

Instructions

  1. Choose a retro format based on context (or let the user pick):

    Format A — Start / Stop / Continue:

    • Start: What should we begin doing?
    • Stop: What should we stop doing?
    • Continue: What's working well that we should keep?

    Format B — 4Ls (Liked / Learned / Lacked / Longed For):

    • Liked: What did the team enjoy?
    • Learned: What new knowledge was gained?
    • Lacked: What was missing?
    • Longed For: What do we wish we had?

    Format C — Sailboat:

    • Wind (propels us): What's driving us forward?
    • Anchor (holds us back): What's slowing us down?
    • Rocks (risks): What dangers lie ahead?
    • Island (goal): Where are we trying to get to?

Sponsors

Details

Repository
github.com/phuryn/pm-skills
Category
Productivity & Planning
First seen
May 16, 2026

More from phuryn/pm-skills

All 68
1anthropics avatarsox-testinganthropics/knowledge-work-pluginsGenerate SOX sample selections, testing workpapers, and control assessments. Use when planning quarterly or annual SOX 404 testing, pulling a sample for a contr2.8Kskills.sh installs
2agricidaniel avatarblog-factcheckagricidaniel/claude-blogVerify statistics and claims in blog posts by fetching cited source URLs and checking if the claimed data actually appears on the page. Extracts all load-bearin2.7Kskills.sh installs
3nexu-io avatarframe-flowchart-stickynexu-io/open-designSVG curve connectors, sticky-note nodes, and cursor interaction with a whiteboard-brainstorm feel.2.7Kskills.sh installs
4juliusbrussee avatarbuildjuliusbrussee/cavekitPlan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before ret2.7Kskills.sh installs
5juliusbrussee avatarjunior-to-seniorjuliusbrussee/skillsAdversarial senior-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior reviewer2.7Kskills.sh installs
6dynatrace avatardt-obs-awsdynatrace/dynatrace-for-aiAWS cloud resource monitoring including EC2, RDS, Lambda, ECS/EKS, VPC networking, load balancers, S3, DynamoDB, SQS/SNS, and cost optimization. Use when analyz2.7Kskills.sh installs