agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/skills/sprint-review-summary/SKILL.md

sprint-review-summary

Skill0 starsChanged 19 days agoMITView on GitHub

Translate what engineering shipped in a sprint or cycle into a short summary of what it means for customers and the business — what's done, what slipped, and what other teams need to know. Use when someone pastes a sprint board, completed tickets, a cycle report, or demo notes and wants a sprint recap, a stakeholder update, an engineering update for leadership, or "what did we ship?

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the status in the source.

    line 28
  2. Distinctive:

    No ticket IDs, story points, or velocity unless the reader is engineering.

    line 41
  3. Distinctive:

    No codenames or internal team names.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Sprint review summary

Engineering reports progress in tickets and points. Everyone else wants to know what changed, what didn't, and whether it affects them. This summary is the translation.

Before you start

If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.

Step 1: Sort the work

From the source, place every item in one bucket:

BucketWhat goes here
Shipped to customersLive and usable now
Done, not yet releasedComplete but behind a flag, waiting on a release, or in beta
Carried overPlanned for this sprint and not finished
DroppedRemoved from the sprint on purpose
InternalTech debt, tooling, infrastructure, tests

Use the status in the source. Don't count an item as shipped unless the source says it's live.

Step 2: Translate

For shipped and done items, write one plain sentence each:

  • What changed, for whom
  • Where it shows up, if the source says

For carried-over and dropped items, say what it was and the reason, if given. Don't add reasons that aren't in the source.

Group internal work into one or two lines ("Reliability work on the reporting service"). Name it only if it has a visible effect, like faster load times, and the source says so.

Rules:

  • No ticket IDs, story points, or velocity unless the reader is engineering.
  • No codenames or internal team names.
  • Plain verbs: "you can now," "fixed," "faster," not "implemented," "refactored," "enhanced."

Step 3: Flag who needs to know

List anything another team should act on: support needs a new help article, sales can now say yes to something, a carried-over item affects a launch date.

Output

# Sprint [N] summary — [Dates]

**In one line:** [the most important outcome]

## Shipped
- [Plain sentence]

## Done, releasing soon
- [Plain sentence] — releasing [when, if known]

## Carried over
- [Item] — [reason, if given]

## Who needs to know
- **Support:** [what]
- **Sales:** [what]
- **[Team]:** [what]

## Behind the scenes
- [One or two lines on internal work]

Drop any empty section. Keep the whole summary readable in under a minute.

Related skills

  • release-notes-drafting — turn the summary into customer-facing notes
  • roadmap-hygiene — update the roadmap for what slipped
  • cross-team-dependency-map — flag what other teams need next

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.