Agent skill
Requirements Definition
This skill should be used when the user asks to "define requirements", "create specification", "clarify requirements", "write requirements document", or mentions requirement analysis. Provides comprehensive requirements definition methodology.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/requirements-definition
SKILL.md
Security:
- All data encrypted at rest using AES-256
- JWT tokens for authentication
Maintainability:
- Test coverage >= 80%
- Documentation for all public APIs
</example>
Impact Scope:
- All components making API calls
- Testing utilities need to mock React Query
</example>
Objectivity (0-100): Evidence-based vs. assumption-based
- 90-100: All requirements verified through investigation
- 70-89: Most requirements verified, some assumptions documented
- 50-69: Mix of verification and assumptions
- Below 50: Mostly assumptions, needs more investigation
</example>
<best_practices> Always investigate current state before defining requirements using Serena's symbol-level operations Score questions using the 4-criteria scoring system and prioritize high-score questions (>= 15) Clearly distinguish mandatory from optional requirements with explicit rationale Document all assumptions when requirements are unclear or incomplete Map each requirement to specific test scenarios for verification Include rationale for key design decisions in technical specifications Use Context7 to verify latest library documentation and best practices Create dependency graphs showing task execution order </best_practices>
<error_escalation> Minor ambiguity in non-critical detail Note in report, proceed Unclear requirement affecting scope Document issue, use AskUserQuestion for clarification Technically infeasible requirement STOP, present options to user Requirement violates security or ethics BLOCK operation, require explicit user acknowledgment </error_escalation>
<related_agents> Primary agent for requirements definition and specification design Use for investigating current system state before requirements definition Delegate to after requirements are fully defined and approved </related_agents>
<related_skills> Use to understand current system state before requirements definition Use after requirements approval to delegate implementation Use to define test requirements and acceptance criteria </related_skills>
<anti_patterns> Requirements that are unclear or unmeasurable Write specific, testable requirements with clear acceptance criteria Specifying implementation details instead of requirements Describe what needs to be achieved, not how to implement it Writing requirements without investigating existing code Always investigate current state before defining requirements Not identifying technical or operational constraints Explicitly document all constraints that affect implementation Treating all requirements as equally important Clearly mark requirements as mandatory or optional with rationale </anti_patterns>
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?