← ClaudeAtlas

jarvis-deep-interviewlisted

Convergent Socratic interview that turns vague requirements into a production-grade specification via 8-15 narrowing rounds with mathematical ambiguity gating. Inspired by Sorbh/interview-me, adds Contrarian/Simplifier Challenge Mode and JSONL decision log. Use when an idea exists but implementation decisions are still undefined.
Ramsbaby/jarvis · ★ 6 · AI & Automation · score 74
Install: claude install-skill Ramsbaby/jarvis
# /deep-interview — Convergent Requirements Interview Acts as a senior architect. 8-15 rounds of Socratic questions narrow a vague idea into a production-grade spec. Blocks contradictions, edge-case gaps, and security gaps before any code is written. ## How it differs from /brainstorm - **/brainstorm** (divergent): expand possibilities. 15-20 questions + UI mockup variants. Exits when ideation feels saturated. - **/deep-interview** (convergent): spec gating. 8-15 narrowing rounds + decision log. Exits when ambiguity score ≤ threshold. When to use which: - Idea itself is undefined → `/brainstorm` - Idea exists, implementation decisions are undefined → `/deep-interview` ## Mechanism (4 stages) ### 1. Mathematical ambiguity gating After each round, score across: - Undefined behavior areas - Contradiction risk (conflicting requirements) - Uncovered edge cases - Security gaps (secrets, PII, permissions) - Unidentified irreversible decisions Refuse autonomous implementation until score ≤ 0.2 (default threshold). ### 2. Socratic question patterns Examples the agent will ask: - "What happens when X scenario triggers Y?" - "What evidence would prove this decision wrong (falsifiability condition)?" - "What assumptions are you carrying that aren't yet stated?" - "What technical debt will this create one year out?" ### 3. Contrarian / Simplifier Challenge Mode For each major decision, automatically run two checks: - **Contrarian**: deliberately raise the counter-hypothesis (d