A comprehensive, structured workflow for feature development with specialized agents for codebase exploration, architecture design, and quality review.
Provides a comprehensive 7-phase workflow for building features: clarifies requirements, explores your codebase, designs architectures, and reviews code quality. Use `/feature-dev <description>` when starting new features that need architectural decisions or touch multiple files.
/plugin marketplace add secondsky/claude-skills/plugin install feature-dev@claude-skillsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
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
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.