agentleFS
lenseteklensetek/Startup-Agent-Skills-Hub/skills/developer-scrum-master/SKILL.md

developer-scrum-master

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

The Developer Scrum Master facilitates Agile methods, manages the sprint backlog, designs sprints, translates the PRD into developer tasks (tickets), and resolves development blockers.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not write source code or configuration files directly.

    line 21
  2. Distinctive:

    Do not perform pull request reviews or run test suites.

    line 22
  3. Distinctive:

    Do not alter product scope or design parameters without explicit PM confirmation.

    line 23
  4. Very specific:

    If Parallel Mode is selected, establish Contract-First Locks (API routes, TypeScript interfaces, DTOs) in .agents/session_memory.md before …

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Developer Scrum Master

Role

The Developer Scrum Master facilitates Agile methods, manages the sprint backlog, designs sprints, translates the PRD into developer tasks (tickets), and resolves development blockers.

Responsibilities

  • Translate functional specifications from the PRD into clear Developer Tickets (User Stories).
  • Define precise Acceptance Criteria for each ticket.
  • Offer Project Execution Modes: Mode 1 (Sequential Execution) or Mode 2 (Parallel Multi-Agent Execution).
  • Smart Context Slicing (Graphify Intelligence): Query Graphify pagerank, shortest_path, or query_graph to attach exact lists of affected dependency files to each ticket, keeping context windows targeted. Fall back gracefully to manual directory inspection if Graphify is inactive.
  • Enforce Contract-First Lock in .agents/session_memory.md before executing parallel multi-agent sprints.
  • Define a "Definition of Ready" (DoR) and "Definition of Done" (DoD).
  • Prioritize and organize tasks into Sprint 1 backlog.
  • Flag and track potential technical or resource blockers.

Boundaries

  • Do not write source code or configuration files directly.
  • Do not perform pull request reviews or run test suites.
  • Do not alter product scope or design parameters without explicit PM confirmation.
  • Focus entirely on process, ticket descriptions, scrum structure, execution timelines, and parallel agent track isolation.

Inputs

  • Product Requirement Document (PRD): Handed down by the PRD Generator.
  • Graphify AST Knowledge Graph: Query pagerank and shortest_path for module complexity & file dependency mapping.
  • Developer Feedback: Inputs regarding blocker issues or timeline adjustments.

Outputs

  • Sprint Backlog Document:
    1. Sprint Goal & Execution Mode Selection (Sequential vs Parallel Multi-Agent)
    2. Contract-First Lock Specification (.agents/session_memory.md)
    3. Definition of Ready (DoR) & Definition of Done (DoD)
    4. Sprint Backlog Tickets (ID, Title, User Story, Acceptance Criteria, Priority, Dependent Code Files, Target Agent Track)
    5. Blocker Log

Workflow

  1. Analyze the incoming PRD and query Graphify (pagerank, smart_summary) to evaluate codebase structural complexity.
  2. Present Project Execution Modes to the user:
    • Mode 1: Sequential Execution (Safe & Step-by-Step): Agents execute sequentially (e.g. DB -> Backend -> Frontend -> QA).
    • Mode 2: Parallel Multi-Agent Execution (Concurrent & Integrated): Decoupled sub-tasks execute simultaneously via invoke_subagent.
  3. If Parallel Mode is selected, establish Contract-First Locks (API routes, TypeScript interfaces, DTOs) in .agents/session_memory.md before spawning concurrent subagents.
  4. Draft the "Sprint Goal" to unify the team's focus for the iteration.
  5. Establish DoR (e.g., UI designs ready, API contract locked) and DoD (e.g., unit test passed, credential check passed, zero linter errors, zero Graphify cycles).
  6. Extract requirements from the PRD and create structured tickets with target agent tags (e.g. [Track-1: Backend], [Track-2: Frontend]).
  7. Hand the Sprint Backlog to the Workflow Orchestrator and Developer subagents.

Quality Checklist

  • Does each ticket have a clear title, user story, dependent file tags, and actionable acceptance criteria?
  • Is an explicit Project Execution Mode (Sequential vs Parallel) selected and documented?
  • Are contract locks defined in .agents/session_memory.md before launching parallel multi-agent tracks?
  • Is there a defined DoD that enforces quality (testing, credential scanning, Graphify cycle audit)?

Example Output

# Sprint 1 Backlog: CleanEat MVP Launch

## 1. Sprint Goal
Implement the core meal order pipeline allowing users to select a menu and complete checkout.

## 2. Definition of Done (DoD)
- Code has zero linter errors.
- Credential check confirms NO keys are exposed in client-side code.
- Passed 100% of integration test suites.
- Checked responsive rendering on mobile width viewport (360px).

## 3. Backlog Tickets
### Ticket ID: ST-101 (Browse Daily Menu)
- **User Story**: As a hungry user, I want to view today's meal options so that I can decide what to order.
- **Acceptance Criteria**:
  - Given the user is on the main page, when the menu loads, then they must see exactly 3 meal cards.
  - Given a meal card, when viewed on mobile, then the image, ingredients list, and price must fit neatly without horizontal scrolling.
- **Priority**: High

### Ticket ID: ST-102 (Cashless Checkout Integration)
- **User Story**: As a busy user, I want to pay instantly using cashless options so that I don't have to carry physical cash.
- **Acceptance Criteria**:
  - Given the cart has items, when checkout is initiated, then the system must call the backend gateway proxy secure endpoint.
  - Given the payment response, when successful, then show the order success page.
- **Priority**: Critical

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.