Skip to content
SkillModel-led706 tokens in use

retro

Facilitate a sprint retrospective in a format you pick, group feedback into themes and finish with owned action items.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-execution/skills/retro
claude plugin install pm-execution@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing retro costs

55tokens idle
706tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples6/15
  • Output12/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers