Agent skill
requirements-gathering-skill
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/requirements-gathering-skill
SKILL.md
Requirements Gathering Skill
=== PURPOSE ===
This skill provides procedures for gathering, documenting, and managing requirements. Used by the Product Manager agent for all requirements-related work.
=== USED BY ===
| Agent | Purpose |
|---|---|
| @agent(product-manager) @ref(CB-AGENT-PM-001) | Primary skill for requirements work |
=== PREREQUISITES ===
Before using this skill:
- Access to stakeholders or their documented feedback
- Understanding of project goals (@ref(CB-BIZ-GOALS-001))
- Familiarity with user story format
=== PROCEDURE: User Story Creation ===
Purpose: Create well-formed user stories with acceptance criteria
Steps:
- Identify the user persona (who)
- Identify the action/goal (what)
- Identify the benefit (why)
- Write in format: "As a [persona], I want [goal], so that [benefit]"
- Define acceptance criteria (Given/When/Then format)
- Add priority and size estimates
- Link to related requirements
Output Format:
## User Story: [Title]
**As a** [user persona]
**I want** [goal/action]
**So that** [benefit/value]
### Acceptance Criteria
- [ ] Given [context], when [action], then [outcome]
- [ ] Given [context], when [action], then [outcome]
### Priority: [High/Medium/Low]
### Size: [S/M/L/XL]
### Related: [links to requirements or issues]
=== PROCEDURE: Requirements Document ===
Purpose: Create comprehensive requirements documentation
Steps:
- Define document scope and context
- List stakeholders and their interests
- Document functional requirements
- Document non-functional requirements
- Define constraints and assumptions
- Create traceability matrix
- Get stakeholder sign-off
Location: devdocs/business/requirements/[feature-name].md
=== PROCEDURE: Stakeholder Interview ===
Purpose: Extract requirements from stakeholder conversations
Steps:
- Prepare interview questions
- Document current pain points
- Identify desired outcomes
- Clarify priorities
- Document assumptions
- Summarize and validate understanding
- Follow up on unclear points
Questions to Ask:
- What problem are you trying to solve?
- Who are the primary users?
- What does success look like?
- What are the must-haves vs nice-to-haves?
- What are the constraints (time, budget, technical)?
=== PROCEDURE: Requirements Prioritization ===
Purpose: Prioritize requirements using MoSCoW method
Categories:
- Must Have: Critical, non-negotiable
- Should Have: Important but not critical
- Could Have: Desirable but not necessary
- Won't Have: Out of scope for this release
Steps:
- List all requirements
- Categorize each using MoSCoW
- Validate with stakeholders
- Document rationale for each priority
- Review and adjust as needed
=== ANTI-PATTERNS ===
Vague Requirements
Problem: Requirements like "make it faster" or "improve UX" Solution: Always quantify: "reduce load time to under 2 seconds"
Assumed Context
Problem: Not documenting assumptions Solution: Explicitly state all assumptions
Missing Acceptance Criteria
Problem: User stories without clear done criteria Solution: Every story must have Given/When/Then criteria
Scope Creep
Problem: Requirements expanding without documentation Solution: Document all changes with rationale
=== RELATED SKILLS ===
| Skill | Relationship |
|---|---|
| @skill(issue-management) | Requirements become issues |
| @skill(roadmap-planning) | Requirements feed roadmap |
| @skill(user-flows) | UX informs requirements |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?