Output format, templates, and examples for structuring feature requirements. Auto-invoke when normalizing feature requirements, structuring input, or analyzing GitHub issues for feature workflows. Do NOT load for implementation, code review, or planning tasks.
Normalizes feature requirements into a structured 4-section format (FEATURE, EXAMPLES, DOCUMENTATION, OTHER CONSIDERATIONS). Auto-invokes when analyzing GitHub issues or processing feature requests to ensure completeness for planning.
/plugin marketplace add L-Sypniewski/claude-code-toolkit/plugin install development-workflow@claude-code-toolkitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Standard format and patterns for structuring feature requirements from any input source.
All inputs normalized to this structure:
## FEATURE
[Clear, concise description of what needs to be built. Be specific about:
- Core functionality
- User-visible behavior
- Expected outcomes
- Success criteria]
## EXAMPLES
[Concrete examples of the feature in action:
- Usage scenarios
- Input/output examples
- User interaction flows
- Edge cases to consider]
## DOCUMENTATION
[Technical implementation guidance:
- Relevant existing code/patterns
- Technology choices and constraints
- Integration points with existing systems
- Architectural considerations
- Links to relevant documentation]
## OTHER CONSIDERATIONS
[Additional factors that influence implementation:
- Performance requirements
- Security implications
- Backwards compatibility
- Migration needs
- Testing strategy
- Deployment considerations]
Append status indicator at end of output:
---
**COMPLETENESS**: COMPLETE | INCOMPLETE
**CRITICAL GAPS**: [List if incomplete]
**RECOMMENDATION**: [Next step]
COMPLETE: All sections have sufficient detail for complexity scoring and planning.
INCOMPLETE: Critical gaps exist that affect scope/architecture:
feature-requirements-clarifier agentBad (vague):
Add authentication to the app
Good (specific):
Implement JWT-based authentication with:
- User registration and login endpoints (Express.js)
- Password hashing using bcrypt (12 rounds)
- JWT access tokens (15min expiry) and refresh tokens (7 days)
- Protected route middleware
- Session management in Redis
Bad (vague):
Users can log in
Good (concrete):
1. New user registration:
POST /api/auth/register
Body: { email: "user@example.com", password: "secure123" }
Response: { token: "jwt...", user: { id, email } }
2. Login flow:
POST /api/auth/login
Body: { email: "user@example.com", password: "secure123" }
Response: { token: "jwt...", refreshToken: "..." }
Bad (generic):
Use standard authentication patterns
Good (specific):
- Express.js middleware: https://expressjs.com/en/guide/using-middleware.html
- Existing auth pattern: src/middleware/auth.ts
- JWT spec: https://tools.ietf.org/html/rfc7519
- Similar implementation: examples/auth-flow/
Bad (generic):
Make it secure
Good (specific):
- Security: Rate limiting on auth endpoints (10 attempts/15min)
- Performance: Cache JWT validation in Redis (5min TTL)
- Compatibility: Must work with existing session-based admin panel
- Migration: Script to migrate existing user passwords
- Testing: Unit tests for middleware, integration for full flow
When input is vague (e.g., "implement dark mode"):
## FEATURE
Implement dark mode functionality for the application.
## EXAMPLES
_No examples provided in input._
## DOCUMENTATION
**General Resources**:
- React Context API: https://react.dev/learn/passing-data-deeply-with-context
- CSS custom properties: https://developer.mozilla.org/...
_Specific technical approach requires clarification._
## OTHER CONSIDERATIONS
_Requires clarification on scope and constraints._
---
**COMPLETENESS**: INCOMPLETE
**CRITICAL GAPS**:
- Placement: Where should the toggle be located?
- Persistence: How should preference be stored?
- Scope: Which pages/components need dark mode?
- System preference: Detect prefers-color-scheme?
**RECOMMENDATION**: Invoke `feature-requirements-clarifier` agent.
Before returning, verify:
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.