Sign inGet started
Skills / Project-management

Scrum

The way most teams work today is fundamentally broken. Scrum doesn't hide that — it reveals it. And once you can see the waste, you can eliminate it.

Scrum is the world's most adopted agile framework, built on three pillars of empiricism: Transparency, Inspection, and Adaptation. Developed by Jeff Sutherland and Ken Schwaber in 1993, it structures work into short, timeboxed Sprints with rigidly defined roles, events, and artifacts that force teams to surface problems fast and course-correct before they compound. Where traditional project management hides waste, Scrum exposes it — sprint by sprint.

By Jeff Sutherland · Free
Specimen 01 · Live diagnosisScrum
Input

“I'm a Scrum Master. We've been doing Scrum for six months and our velocity is completely flat. We hold all the ceremonies but nothing ever improves.…”

Diagnosis
I'm Jeff Sutherland's Scrum methodology — built on three decades of what separates hyperproductive teams from teams that just go through the motions.
Full transcript ↓
Calibrated referenceagent-skills.ai
The gap

Do twice the work in half the time — one sprint at a time

Scrum organizes all product development work into a repeating cycle called a Sprint (1–4 weeks), governed by three roles (Product Owner, Scrum Master, Development Team), five events (Sprint Planning, Daily Scrum, Sprint Review, Sprint Retrospective, and the Sprint itself), and three artifacts (Product Backlog, Sprint Backlog, Increment). Sutherland's unique extensions go beyond the baseline Scrum Guide: Yesterday's Weather uses actual past velocity as the single best predictor for sprint capacity; the Happiness Metric treats team morale as a leading performance indicator; the Impediment Backlog makes blockers visible and forces the Scrum Master to systematically remove them. Every Sprint ends with a Definition of Done — a formal quality checklist — and a shippable Increment, making progress concrete and undeniable. Sutherland's Scrum@Scale framework extends these same principles across entire organizations with multiple interdependent teams.

The problem

Most teams that adopt Scrum end up practicing what Sutherland calls 'Zombie Scrum' or 'Scrumfall' — they run the ceremonies but ignore the empirical principles underneath. Daily standups become status reports. Retrospectives produce no changes. Sprint goals get abandoned mid-sprint. The result is all the overhead of Scrum with none of the acceleration — and no diagnostic framework for why velocity is flat, team morale is dropping, or the same impediments keep reappearing sprint after sprint.

The solution

Stop going through the Scrum motions and start getting the results — properly structured sprints, user stories with real acceptance criteria, retrospectives that actually change behavior, and a velocity trend that compounds upward instead of stalling.

You bring
  • Your current backlog or list of work items (even rough or informal)
  • Team context: size, roles filled, how you work today
  • The specific sprint, ceremony, or artifact you're struggling with
  • Any blockers, dysfunctions, or anti-patterns you've observed
You get
  • A prioritized Sprint Backlog with user stories in proper format and acceptance criteria
  • A team-specific Definition of Done checklist
  • A structured Start/Stop/Continue retrospective with concrete action items
  • A Yesterday's Weather velocity forecast for your next sprint
  • An Impediment Backlog with escalation paths for your Scrum Master
In action

Watch the methodology work.

Three specimens from a single real session: the same situation, unaided and calibrated, the full transcript, and the skill answering live in the channel where the work happens.

Fig.01The same situation, two ways
Specimens A · B
Specimen AVague
Unaided

“Your team has been running Scrum for four months. Velocity oscillates between 18 and 22 points with no trend. The retrospective last Friday produced a whiteboard full of sticky notes that no one photographed. The same impediment — unclear acceptance criteria from the Product Owner — has been mentioned in standup 11 times across three sprints and is still unresolved. Sprint Planning takes three hours because stories aren't groomed. The Scrum Master is spending most of their time scheduling meetings rather than removing blockers.”

×Vague — nothing concrete to act on.
Specimen BCalibrated
With Scrum

“Sprint Planning now takes 90 minutes because the top 10 backlog items meet a written Definition of Ready before the meeting starts. The Impediment Backlog has 4 items, 2 of which were resolved in the last sprint. Last retrospective produced one action item — owned, dated, and reviewed at the start of this retrospective — and the team closed it. Velocity has risen from 20 to 31 points over eight sprints, and the Happiness Metric survey shows team morale at its highest since the project started.”

Specific, grounded, and ends with one clear next step.
Fig.02A real session, unedited
In-app · assistant
ScrumClaude
Scrum
I'm Jeff Sutherland's Scrum methodology — built on three decades of what separates hyperproductive teams from teams that just go through the motions. Before we dive in: are you working as a Scrum Master, Product Owner, or developer? And what's the specific problem you're trying to solve — ceremony design, backlog health, team dysfunction, or something else?
I'm a Scrum Master. We've been doing Scrum for six months and our velocity is completely flat. We hold all the ceremonies but nothing ever improves. Our retrospectives feel like venting sessions with no real action.
Flat velocity for six months with ceremonies that produce no change — that's a classic Zombie Scrum pattern. You have the skeleton of Scrum but not the empirical engine. Two questions to diagnose this: First, do your retrospectives end with a written list of specific action items with named owners and a target sprint? Not 'we should communicate better' — but 'Maria will set up a shared Slack channel for design handoffs by Sprint 14, success = zero missed design handoffs in Sprint 15.' Second, are you tracking an Impediment Backlog — a written, prioritized list of blockers you're actively working to remove?
Honestly, no to both. We talk about problems in the retro but no one writes anything down. And impediments just get mentioned in the daily standup and then forgotten.
There's your velocity ceiling. Sutherland's research is unambiguous: hyperproductive teams — the ones achieving 300–400% velocity gains — universally have two things you're missing: retrospectives that produce durable behavioral change with accountable owners, and an Impediment Backlog that makes blockers visible until they're resolved. The untracked impediment mentioned in standup and forgotten is killing your throughput, sprint after sprint. Let's fix both. For the retrospective, I want to run a Start/Stop/Continue session with you right now and build a proper action board. For the impediments, I'll help you build your first Impediment Backlog. Which one is the bigger pain point this sprint?
The retrospectives. Every sprint we identify the same problems but nothing changes. I feel like I'm failing as a Scrum Master.
You're not failing — you're running the ceremony without the mechanism. The ceremony is the meeting. The mechanism is: one improvement per sprint, one owner, one measurable success criterion, reviewed at the top of the next retrospective before any new problems are raised. Here's the rule I want you to implement immediately: No retrospective can add new items until last sprint's action item is reviewed. Did it happen? What was the outcome? This single change breaks the 'venting cycle.' Now — tell me the one problem your team has raised in at least two consecutive retrospectives. Let's write the first real action item together.
We keep saying that stories aren't ready when sprint planning starts. We end up spending the first day of every sprint just clarifying requirements.
Perfect — that's a Definition of Ready problem. Here's your action item: 'Before Sprint 15 Planning, Product Owner will conduct a Backlog Refinement session with the team to verify the top 10 backlog items meet our Definition of Ready: written acceptance criteria, no blocking dependencies, story points estimated. Owner: [Product Owner's name]. Success criterion: Sprint 15 Planning starts on time with zero stories requiring same-day clarification.' I'll also help you draft a Definition of Ready checklist you can use going forward. This is one sprint. If velocity doesn't tick up after implementing this, we look at the next constraint. That's Inspect and Adapt — not venting, not hoping.
Reply to Scrum
What the skill is doing
01Sprint Planning Facilitator
02User Story Architect
03Retrospective Catalyst
Fig.03The same skill, in the channel you already use
WhatsApp · live
9:41
SScrumtyping…
Messages are end-to-end encrypted. No one outside of this chat can read them.
Today
I'm a Scrum Master. We've been doing Scrum for six months and our velocity is completely flat. We hold all the ceremonies but nothing ever improves. O…9:14✓✓
I'm Jeff Sutherland's Scrum methodology — built on three decades of what separates hyperproductive teams from teams that just go t…9:14
Before we dive in: are you working as a Scrum Master, Product Owner, or developer?9:15
And what's the specific problem you're trying to solve — ceremony design, backlog health, team dysfunction, or something else?9:15
Message

The same skill, where the work happens.

No new app to learn. The methodology runs over the WhatsApp Business API, so the answer lands as a reply in the thread you’re already in — same rigour, zero context-switch.

Reads the situation, names the pattern, returns one concrete next move.
Delivered in seconds, inside a conversation that already exists.
Specimen · WhatsApp Business API · live
Capabilities

What it does, specifically.

Each capability is a distinct move drawn straight from the source methodology — not a generic assistant guessing.

CapabilityC-01

Sprint Planning Facilitator

Walk through a complete Sprint Planning session: select backlog items based on team velocity, establish a clear Sprint Goal, break stories into tasks, and produce a committed Sprint Backlog. Prevents over-commitment and under-commitment — the two most common sprint planning failure modes.

Based on Sutherland's Yesterday's Weather principle — using last sprint's actual velocity as the primary capacity input — combined with the Scrum Guide's Sprint Goal requirement that gives the team a single north-star for the iteration.
CapabilityC-02

User Story Architect

Write, refine, and evaluate user stories in the canonical 'As a [user], I want [goal], so that [benefit]' format with explicit Acceptance Criteria. Diagnoses story-splitting problems, epic decomposition, and Definition of Ready gaps that cause stories to fail in-sprint.

Grounded in Sutherland's Product Backlog refinement practices and the INVEST criteria (Independent, Negotiable, Valuable, Estimable, Small, Testable) — the quality standard for backlog items before they enter Sprint Planning.
CapabilityC-03

Retrospective Catalyst

Facilitate a complete Sprint Retrospective using Start/Stop/Continue or other proven formats, producing a prioritized list of concrete process improvements with owners and timelines. Identifies when a team is running fake retrospectives — meetings that generate ideas but never produce sustained behavioral change.

Built on the Inspect-and-Adapt pillar of Scrum's empirical model. Sutherland treats the Retrospective as the team's primary mechanism for continuous improvement — his research shows hyperproductive teams (400%+ velocity) universally have high-functioning retrospective practices.
CapabilityC-04

Impediment Radar

Identify, categorize, and prioritize team impediments — distinguishing between blockers the Development Team can self-resolve, those requiring Scrum Master intervention, and systemic organizational issues requiring escalation. Builds and maintains an Impediment Backlog so nothing gets lost.

Derives from Sutherland's Impediment Backlog pattern and his emphasis that the Scrum Master's primary job is impediment removal — not meeting scheduling. Teams that don't track impediments formally routinely re-encounter the same blockers sprint after sprint.
CapabilityC-05

Happiness Metric Designer

Design and interpret a team happiness survey calibrated to your team's context — including prompt questions, measurement cadence, and threshold triggers for Scrum Master action. Connects morale data to velocity trends to catch performance problems before they show up in the burndown chart.

Sutherland's proprietary extension to standard Scrum: his research documents that team happiness is a leading indicator of productivity — drops in morale predict velocity decline by 1–2 sprints. This is one of the features that distinguishes ScrumInc's approach from the baseline Scrum Guide.
Tested

Graded before it shipped.

Every skill is scored against independent scenarios for methodology fidelity before it goes live — not vibes, a rubric.

What it produces
OutputD-01

Sprint Backlog

A committed list of user stories for the current sprint, each in proper format with acceptance criteria, story point estimates, and task breakdowns — derived from the Product Backlog using the team's Yesterday's Weather velocity.

OutputD-02

Definition of Done Checklist

A team-specific, negotiated quality checklist that every Increment must pass before it is considered shippable. Covers code review, testing, documentation, and deployment readiness thresholds specific to your team's context.

OutputD-03

Retrospective Action Board

A structured Start/Stop/Continue output with each action item assigned an owner, a target sprint, and a success criterion — so the retrospective produces durable change rather than a list of good intentions.

OutputD-04

Impediment Backlog

A tracked, prioritized list of team blockers with categorization by resolution path (self-resolved / Scrum Master / executive escalation) and age — making impediment removal visible and accountable.

OutputD-05

Yesterday's Weather Forecast

A sprint capacity calculation using actual previous velocity, accounting for team availability, planned absences, and scope risk — giving Sprint Planning a reality-grounded commitment baseline instead of optimistic guesswork.

The source

Grounded in the original work.

Every answer traces back to a real source and the practitioner who wrote it — not a secondhand summary. Here is the source of record.

Source authorA-01

Jeff Sutherland

Jeff Sutherland co-created Scrum in 1993 alongside Ken Schwaber and has spent three decades documenting hyperproductive teams achieving 400%+ velocity gains. A decorated Vietnam War fighter pilot who flew over 100 combat missions, Sutherland holds a PhD in Statistics and applied systems thinking from aerospace to software. He is the founder of ScrumInc, co-author of the canonical Scrum Guide (used by millions globally), and author of the bestselling 'Scrum: The Art of Doing Twice the Work in Half the Time' (Crown Business, 2014).

Status · Inspired by Jeff Sutherland’s work — not yet claimed. Are you Jeff Sutherland?
Primary sourceS-01

Scrum: The Art of Doing Twice the Work in Half the Time

by Jeff Sutherland

Co-creator of Scrum, founder of ScrumInc, co-author of the Scrum Guide, PhD in Statistics, decorated Vietnam War combat pilot turned software methodology pioneer.

Read the original ↗
Citationscruminc.com
In the build queue

Be first to run it.

Scrum is being built right now. Leave your email and we’ll tell you the moment it goes live.

Notify meEmail
At launchMy team's velocity is flat and our retrospectives never produce real change. Can you help me figure out what's broken and run a proper retrospective with me?