retro helps run a sprint retrospective that ends in specific improvements. It offers three formats: Start / Stop / Continue, the 4Ls (Liked, Learned, Lacked, Longed For) and Sailboat (wind, anchor, rocks, island).
Raw feedback such as sticky notes, survey answers or Slack messages is grouped into themes and checked for sentiment patterns, and the output is a summary with two or three action items that each have an owner, a deadline and a success metric.
What You Get
- A chosen retro format with its prompts
- Key themes grouped from the team’s feedback
- A sprint performance block with goal status and committed versus completed points
- A table of two or three action items with owner, deadline and success metric
- A carry-over section with the status of last retro’s actions
- A markdown summary
Common Use Cases
- Running a retro from raw team feedback
- Turning sprint data and velocity into discussion topics
- Checking whether last sprint’s actions were completed
What Makes It Unique
It caps action items at two or three because more will not get done, and it requires each to be specific, assignable and measurable. For teams without input yet it suggests collecting feedback anonymously first and points to the live-polls and live-qa skills.
Under The Hood
The skill is one SKILL.md of instructions with no scripts. The agent reads any sprint data, velocity charts, feedback or earlier retro notes you provide, and saves the summary as a markdown file. It does not call external services.