Skip to content

Part of Interview Your Code Requirements Like a Senior Architect

Engineering Blueprint

Safety checked

Interview Your Code Requirements Like a Senior Architect

0June 2026

Conducts a rigorous pre-code interview using interactive questioning and codebase analysis.

What problem does this solve?

This skill takes your requirement and conducts a one-question-at-a-time interview, pushing back on gaps, contradictions, and security risks before you write code. It fixes the problem of vague requirements and unaddressed edge cases by forcing hard decisions upfront.

How does it work?

Invoke it with a requirement or file path. It forks an analysis of your codebase (architecture patterns, tech stack, dependencies, team conventions), then asks questions one at a time using a coverage tracker (Problem, Users, Technical Approach, Risks, Security, etc.). When you answer, it probes deeper or challenges assumptions if it spots contradictions or over-engineering. On security concerns, it hard-blocks until resolved. When coverage is complete, it generates a production spec with a decisions log, implementation order, and optional interactive HTML preview for annotation before finalizing. Output: comprehensive spec with audit trail of every debate and resolution.

Included Skills

No skills in this group

What's required to run this?

Requires Claude Code environment (Cursor, Claude.app, or compatible client) and access to the skill configuration files (SKILL.md and STYLE_PRESETS.md). Uses the Task tool with subagent_type: Explore to fork codebase analysis in parallel, and AskUserQuestion for all interview prompts, so it needs multi-turn agent capabilities. Security hard blocks will pause the interview until explicitly addressed, which may extend the interview duration if significant security gaps are detected.

Key Features

One-at-a-Time Questioning

Interactive prompts with custom answer options, not a form. Shows real-time coverage tracker so you know which areas are complete.

Codebase Context

Analyzes existing patterns, tech stack, and team conventions in parallel, so every question respects your actual codebase instead of asking about things you already have.

Active Pushback

Challenges contradictions, flags over-engineering, exposes edge cases, and refuses to proceed past unaddressed security gaps.

Decisions Log with Rationale

Tracks every pushback, disagreement, and resolution with full reasoning, creating an audit trail of architectural decisions.

HTML Preview & Annotation

Optionally generates an interactive HTML spec that lets you click any section to add inline comments, then revises the markdown spec based on feedback.

About This Blueprint

Industry
Technology
Sales

ICP-Filtered Outreach Lists from G2 Buyer Intent

Stop wasting rep time on weak intent signals and mismatched accounts. The workflow ranks ICP-fit buyers by readiness, finds the right contact, and supplies tailored outreach angles for the strongest opportunities.

ID

Ishani D.

Account Manager

Customer Experience

Answer pre-purchase questions to convert hesitant shoppers with AI

Shoppers get accurate answers about fit, compatibility, ingredients, and delivery even when your team is offline, so fewer leave before checkout. Conversation insights also reveal which product-page details could prevent the next unanswered question.

UB

Urska B.

GTM Lead

Customer Experience

Find the root cause behind repeat support tickets with AI

Catch a few unusual tickets before a product or fulfillment issue turns into hundreds of refunds, chargebacks, and bad reviews. Cluster transcript evidence by SKU, order date, location, and carrier so operations can trace the cause and support can reach affected customers early.

UB

Urska B.

GTM Lead