agentleFS
itmbastawiitmbastawi/product-skill-pack/scrum-master/SKILL.md

scrum-master

Skill7 starsChanged 4 months agoMITView on GitHub

Break down the product into epics, sprints, tasks, and estimates. Use as step 6 of the product pipeline, after architecture is complete. Requires `05-architecture.md` and all prior outputs. Produces a sprint plan with epics, stories, tasks, and time estimates ready for development.

14 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

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a realistic, actionable development plan with clear epics, sprints, and estimates.

    line 16
  2. Very specific:

    Read all prior outputs from @output_dir@/, especially 03-product-requirements.md and 05-architecture.md

    line 19
  3. Distinctive:

    Keep sprints realistic — don't cram too much in

    line 109
  4. Distinctive:

    Consider parallel workstreams where possible

    line 113

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “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

Scrum Master — Step 6 of Product Pipeline

Goal

Create a realistic, actionable development plan with clear epics, sprints, and estimates.

Input

Read all prior outputs from @output_dir@/, especially 03-product-requirements.md and 05-architecture.md

Output

Save to @output_dir@/06-sprint-plan.md

Deliverables

1. Epics

Group user stories into epics:

Epic IDEpic NameDescriptionStoriesPriority

2. Sprint Plan

Assume 2-week sprints. For each sprint:

  • Sprint goal
  • Stories included
  • Story points (Fibonacci: 1, 2, 3, 5, 8, 13)
  • Dependencies
  • Risks

3. Task Breakdown

For each story, break into technical tasks:

Task IDTask NameAssignee RoleEstimate (hours)Dependencies

4. Definition of Done

  • Code complete
  • Unit tests passing
  • Code reviewed
  • Acceptance criteria met
  • Documentation updated
  • Deployed to staging

5. Velocity Projection

  • Estimated team velocity (story points/sprint)
  • Total story points
  • Projected completion date
  • Buffer for unknowns (20%)

6. Risk Register

RiskImpactProbabilityMitigation

Output Template

# Sprint Plan: [Project Name]

## Epics
### Epic 1: [Name]
[Description and included stories]

### Epic 2: [Name]
...

## Sprint Plan
### Sprint 1: [Goal]
[Stories and points]

### Sprint 2: [Goal]
...

## Task Breakdown
### Tasks for Sprint 1
| ID | Task | Role | Hours | Depends On |
|----|------|------|-------|------------|

## Definition of Done
[Checklist]

## Velocity Projection
- Estimated velocity: X points/sprint
- Total scope: Y points
- Projected completion: Z sprints (with 20% buffer)

## Risk Register
| Risk | Impact | Probability | Mitigation |
|------|--------|-------------|------------|

## Dependencies
[External dependencies and blockers]

## Notes
[Assumptions about team size and availability]

Rules

  • Base estimates on the architecture, not guesses
  • Assume a standard team: 1 PM, 1 Designer, 2-3 Devs, 1 QA (adjust if interview brief specifies)
  • Keep sprints realistic — don't cram too much in
  • Identify dependencies between stories to avoid blockers
  • Flag stories with high uncertainty (spike tasks)
  • Include setup/infrastructure sprints if needed
  • Consider parallel workstreams where possible
  • Be conservative with estimates — under-promise, over-deliver

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.