AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Sprint Review

skill-abrahamferga-scrum-skills-sprint-review · by abrahamFerga

Facilitates the Sprint Review by presenting the increment, inspecting progress toward the Product Goal, and capturing Product Backlog adaptations. Use when anyone says things like "sprint review", "demo prep", "what did we complete this sprint", "review the increment", "what's the Product Backlog looking like after this sprint", or "stakeholder demo". Don't use for the Retrospective, Daily Scrum,…

No reviews yet
0 installs
42 views
0.0% view→install

Install

$ agentstack add skill-abrahamferga-scrum-skills-sprint-review

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-abrahamferga-scrum-skills-sprint-review)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Sprint Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Sprint Review

Scrum Guide grounding

The Sprint Review is a working session, not a presentation. The Scrum Team and stakeholders inspect what was accomplished and how the environment has changed. The output is an adapted Product Backlog that reflects the current best opportunity going forward.

Key rules:

  • Time-boxed to four hours for a one-month Sprint (proportionally shorter for shorter Sprints).
  • The increment is inspected — not just described. Stakeholders ask questions and give input.
  • The Product Backlog may be adjusted based on what was learned.
  • Velocity and burn-down metrics are inputs, not the focus.

Tool detection

Identify which project management tool is available:

  1. Check for active mcp__azure-devops__* tools → set $PM_TOOL to ado
  2. Otherwise check for active mcp__jira__* tools → set $PM_TOOL to jira
  3. If both → ask: "I see both ADO and Jira connected — which should I use?"
  4. If neither → set $PM_TOOL to manual

Step 1 — Fetch Sprint data

Retrieve the completed Sprint's items:

  • ADO: use wit_get_work_items_for_iteration for the sprint just completed; filter for Done/Closed state
  • Jira: use the sprint report or issue listing tool for the closed sprint
  • Manual: ask the team to share what was completed, what wasn't, and the Sprint Goal

Identify:

  • $SPRINT_GOAL — the goal set at Sprint Planning
  • $DONE_ITEMS — work items that meet the Definition of Done
  • $NOT_DONE_ITEMS — work items that were planned but not completed
  • $PRODUCT_GOAL — the longer-horizon objective the team is working toward (if known)

Step 2 — Assess the Sprint Goal

State clearly whether the Sprint Goal was met, partially met, or not met — and why.

  • Met: The increment delivered the intended outcome.
  • Partially met: Some committed scope was not done, but the core outcome was achieved.
  • Not met: The team did not deliver the outcome. Name the cause without assigning blame.

A missing Sprint Goal is a team health signal worth naming: "The team didn't have a Sprint Goal this Sprint — that makes it hard to assess whether the Sprint was successful. Worth raising in the Retrospective."


Step 3 — Present the increment

Structure the review of $DONE_ITEMS:

For each completed item, prepare a one-line summary suitable for a stakeholder audience:

  • What it does (user-facing language, not technical)
  • Which part of the Product Goal it advances

Example:

#1234 — Export transactions as CSV
  Customers can now download their full transaction history for any date range.
  Contributes to: "Make it easy for customers to manage their own finances."

Flag items in $NOT_DONE_ITEMS briefly — not as failures, but as context for the backlog discussion.


Step 4 — Capture stakeholder input

Prompt the team to note the key inputs received during the review:

"What feedback or new information came from stakeholders that should influence the backlog?"

Accept free-form input. Group into:

  • New opportunities — things to add or prioritize
  • Changes in direction — items to deprioritize or remove
  • Risks or concerns — items that need a closer look

Step 5 — Adapt the Product Backlog

Based on what was done, what wasn't, and stakeholder input, produce a set of recommended backlog actions:

| Action | Item | Reason | |---|---|---| | Reprioritize | [#ID Title] | [why it moves up/down] | | Add | [new item description] | [stakeholder request or new insight] | | Remove | [#ID Title] | [no longer relevant] | | Carry over | [#ID Title] | [not done, still valuable] |

Ask: "Do these backlog changes reflect the team's intent? Confirm to apply, or tell me what to adjust."

After confirmation, apply changes via the PM tool or output them for manual action.


Step 6 — Output the review summary

Sprint Review — [SPRINT NAME / NUMBER] — [DATE]

Sprint Goal: [SPRINT_GOAL] — [Met / Partially Met / Not Met]

Increment (Done)
- [#ID] [Title]: [one-line stakeholder description]

Not completed this Sprint
- [#ID] [Title]: [brief note — carry over / deprioritized / blocked]

Stakeholder input
- [Key feedback or decision]

Product Backlog adaptations
- [Action]: [#ID / description]

Next Sprint outlook
- [Any relevant context: upcoming events, team changes, Product Goal milestone]

Guardrails

  • Never present undone items as done. The Definition of Done is the team's standard.
  • Never make backlog changes without explicit Product Owner confirmation.
  • Never frame incomplete work as a team failure — focus on learning and adaptation.
  • If no stakeholders attended, note it: the Sprint Review without external input reduces its value.
  • Keep the tone collaborative and forward-looking — this is an inspection event, not a performance review.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.