npx claudepluginhub seajhawk/cc-marketplace --plugin auto-devWant just this agent?
Then install: npx claudepluginhub u/[userId]/[slug]
Deep-dive technical discovery and requirement gathering before coding. Use when a task is broad, ambiguous, or requires architectural decisions.
Interview Mode
Overview
This skill forces a "slow down to speed up" workflow. Before writing implementation code, conduct a thorough technical interview to uncover hidden requirements and trade-offs.
When to Use
- Task description is vague or broad ("add auth to my app")
- Multiple valid approaches exist
- Architectural decisions are needed
- User requirements may have hidden complexity
- The task could be interpreted multiple ways
Instructions
-
Stop and Think - Do not start coding yet.
-
Interview Phase - Use the
AskUserQuestiontool to gather requirements:- UI/UX requirements and preferences
- State management approach
- Security considerations
- Error handling expectations
- Edge cases and boundary conditions
- Integration points with existing code
- Performance requirements
- Testing expectations
-
Ask Deep Questions - Challenge assumptions:
- "What happens if...?"
- "How should the system behave when...?"
- "Do you need to support...?"
- "What's the expected scale...?"
-
Iterate - If an answer reveals complexity, ask follow-up questions.
-
Spec Creation - Summarize findings into a specification document.
-
Confirmation - Get user approval before proceeding to implementation.
Example Interview
User: "I want to add auth to my app."
Interview Questions:
- Authentication method: JWT tokens, session-based, or OAuth?
- Do you need social login (Google, GitHub, etc.)?
- What's the password policy (length, complexity)?
- Password reset flow - email or SMS?
- Session duration and refresh token handling?
- Protected routes - which pages require auth?
- Role-based access control needed?
- Rate limiting for login attempts?
- Two-factor authentication requirement?
- Where will user data be stored?
Output Format
After the interview, create a spec document:
# Feature Specification: [Feature Name]
## Requirements
- Requirement 1
- Requirement 2
## Technical Approach
- Approach details
## Edge Cases
- Edge case 1
- Edge case 2
## Out of Scope
- Items explicitly excluded
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
Similar Agents
Agent for managing AI Agent Skills on prompts.chat - search, create, and manage multi-file skills for Claude Code.
Agent for managing AI prompts on prompts.chat - search, save, improve, and organize your prompt library.
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: <example>Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Great work! Now let me use the code-reviewer agent to review the implementation against our plan and coding standards" <commentary>Since a major project step has been completed, use the code-reviewer agent to validate the work against the plan and identify any issues.</commentary></example> <example>Context: User has completed a significant feature implementation. user: "The API endpoints for the task management system are now complete - that covers step 2 from our architecture document" assistant: "Excellent! Let me have the code-reviewer agent examine this implementation to ensure it aligns with our plan and follows best practices" <commentary>A numbered step from the planning document has been completed, so the code-reviewer agent should review the work.</commentary></example>