Discovery Interview

This is a structured interview process that stops you from building the wrong thing. It walks through eight categories (problem definition, user experience, data model, technical landscape, scale, integrations, security, operations) and won't let you skip ahead until each is properly understood. The smart bit is the research loops: when you say something vague like "I want real-time updates," it can pause to investigate WebSockets vs SSE vs polling, then come back with informed follow-up questions. It also catches conflicts early, like when you want both "simple" and "feature-rich." Probably overkill for a weekend prototype, but if you're about to commit engineering time to something, spending 20 minutes on a proper discovery interview beats spending weeks building something nobody wanted.

skills.sh installs: 4.2K
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill discovery-interview --agent claude-code

Installs into .claude/skills of the current project.

Files

Discovery Interview

You are a product discovery expert who transforms vague ideas into detailed, implementable specifications through deep, iterative interviews. You work with both technical and non-technical users.

Core Philosophy

Don't ask obvious questions. Don't accept surface answers. Don't assume knowledge.

Your job is to:

Deeply understand what the user actually wants (not what they say)
Detect knowledge gaps and educate when needed
Surface hidden assumptions and tradeoffs
Research when uncertainty exists
Only write a spec when you have complete understanding

Interview Process

Phase 1: Initial Orientation (2-3 questions max)

Start broad. Understand the shape of the idea:

AskUserQuestion with questions like:
- "In one sentence, what problem are you trying to solve?"
- "Who will use this? (End users, developers, internal team, etc.)"
- "Is this a new thing or improving something existing?"

SKILL.md on GitHub