From feature-dev
Automates 7-phase feature development workflow using specialized agents for codebase exploration, architecture design, and quality review. Invoke via /feature-dev for multi-file features or ambiguous requirements.
How this skill is triggered — by the user, by Claude, or both
Slash command
/feature-dev:feature-devThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A comprehensive, structured workflow for feature development with specialized agents for codebase exploration, architecture design, and quality review.
A comprehensive, structured workflow for feature development with specialized agents for codebase exploration, architecture design, and quality review.
Launch the guided feature development workflow:
/feature-dev Add user authentication with OAuth
Or interactively:
/feature-dev
The workflow will guide you through 7 distinct phases automatically.
Building features requires more than just writing code. This skill provides a systematic approach that:
Goal: Understand what needs to be built
Example:
User: /feature-dev Add caching
Agent: Let me understand what you need...
- What should be cached? (API responses, computed values, etc.)
- What are your performance requirements?
- Do you have a preferred caching solution?
Goal: Understand relevant existing code and patterns
code-explorer agents in parallelAgents launched:
Example output:
Found similar features:
- User authentication (src/auth/): Uses JWT tokens, middleware pattern
- Session management (src/session/): Redis-backed, 24hr expiry
Key files:
- src/auth/AuthService.ts:45 - Core authentication logic
- src/middleware/authMiddleware.ts:12 - Request authentication
Goal: Fill in gaps and resolve all ambiguities
Example:
Before designing, I need to clarify:
1. OAuth provider: Which providers? (Google, GitHub, custom?)
2. User data: Store OAuth tokens or just profile?
3. Existing auth: Replace or add alongside current auth?
4. Sessions: Integrate with existing session management?
5. Error handling: How to handle OAuth failures?
Critical: Ensures nothing is ambiguous before design begins.
Goal: Design multiple implementation approaches
code-architect agents with different focuses:
Example output:
Approach 1: Minimal Changes
- Extend existing AuthService with OAuth methods
Pros: Fast, low risk
Cons: Couples OAuth to existing auth
Approach 2: Clean Architecture
- New OAuthService with dedicated interface
Pros: Clean separation, testable
Cons: More files, more refactoring
Approach 3: Pragmatic Balance
- New OAuthProvider abstraction
Pros: Balanced complexity and cleanliness
Cons: Some coupling remains
Recommendation: Approach 3 - clean boundaries without excessive refactoring
Goal: Build the feature
Goal: Ensure code is simple, DRY, elegant, and functionally correct
code-reviewer agents in parallel:
Example output:
High Priority Issues:
1. Missing error handling in OAuth callback (src/auth/oauth.ts:67)
2. Memory leak: OAuth state not cleaned up (src/auth/oauth.ts:89)
Medium Priority:
1. Could simplify token refresh logic (src/auth/oauth.ts:120)
What would you like to do?
Goal: Document what was accomplished
Purpose: Deeply analyzes existing codebase features by tracing execution paths
Focus:
Output:
Triggered: Automatically in Phase 2, or manually
Purpose: Designs feature architectures and implementation blueprints
Focus:
Output:
Triggered: Automatically in Phase 4, or manually
Purpose: Reviews code for bugs, quality issues, and project conventions
Focus:
Output:
Triggered: Automatically in Phase 6, or manually
/feature-dev Add rate limiting to API endpoints
Explore a feature:
"Launch code-explorer to trace how authentication works"
Design architecture:
"Launch code-architect to design the caching layer"
Review code:
"Launch code-reviewer to check my recent changes"
Use for:
Don't use for:
Cause: Normal for large codebases Solution: Agents run in parallel when possible. Thoroughness pays off in better understanding.
Cause: Feature request too vague Solution: Be more specific in initial request. Provide context about constraints upfront.
Cause: Multiple valid approaches presented Solution: Trust the recommendation (based on codebase analysis). Pick pragmatic option when in doubt.
After using the workflow:
For detailed workflow documentation, see README.md
For agent specifications, see:
agents/code-explorer.mdagents/code-architect.mdagents/code-reviewer.mdFor slash command implementation, see commands/feature-dev.md
npx claudepluginhub secondsky/claude-skills --plugin feature-devGuides multi-phase feature development with research, planning, implementation, and review phases. Use for complex features touching >5 files or requiring architecture decisions.
Guides end-to-end feature development through 8 phases: discover requirements, explore codebase, clarify ambiguities, design architecture, TDD implementation, multi-agent review, quality validation, and blog post. Use for adding new features.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.