← ClaudeAtlas

interviewlisted

This skill conducts discovery conversations to understand user intent and agree on approach before taking action. It should be used when the user explicitly calls /interview, asks for recommendations, needs brainstorming, wants to clarify, or when the request could be misunderstood. Prevents building the wrong thing by uncovering WHY behind WHAT.
sheikh-mohammad/agent-factory-claude-skills · ★ 6 · AI & Automation · score 63
Install: claude install-skill sheikh-mohammad/agent-factory-claude-skills
# Interview Skill Prevent building the wrong thing. Discover user's intent (WHY), validate assumptions, and agree on approach (WHAT) before taking action. ## What This Skill Does - Discovers INTENT behind surface requests (WHY they want it) - Surfaces and validates AI's assumptions before acting - Explores solution options informed by intent - Reaches mutual agreement on both problem and solution - Works for any context: software, documents, brainstorming, automation ## What This Skill Does NOT Do - Follow rigid scripts - Skip to implementation without understanding - Accept surface requests without exploring intent - Make assumptions without validating them --- ## Core Problem This Skill Solves **AI builds the wrong thing because it:** 1. Takes surface requests literally without understanding intent 2. Makes hidden assumptions it never validates 3. Proceeds without confirming alignment **This skill ensures:** 1. Intent (WHY) is discovered, not just request (WHAT) 2. Assumptions are surfaced and validated 3. Both problem and solution are agreed before proceeding --- ## The WHY + WHAT Model ``` Surface WHAT → Discover WHY → Surface Assumptions → Informed WHAT → Agree on Both → Proceed ``` | Phase | Purpose | Example | |-------|---------|---------| | **Surface WHAT** | Capture initial request | "Add dark mode" | | **Discover WHY** | Uncover intent/problem | "Eye strain for night workers" | | **Surface Assumptions** | Expose AI's hidden assumptions | "Assuming web a