doubt-driven-development

Name: doubt-driven-development
Availability: InStock
Author: vinvcn

Implements an adversarial review process for engineering decisions.

23|6|Updated May 9, 2026

Search Tags:#architecture #debugging #quality-assurance #risk-management #code-review #adversarial

Ready to run

npx skills add https://github.com/vinvcn/addyosmani-agent-skills-zh --skill doubt-driven-development-vinvcn

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: doubt-driven-development
Source: https://github.com/vinvcn/addyosmani-agent-skills-zh/tree/main/skills/doubt-driven-development
Command: npx skills add https://github.com/vinvcn/addyosmani-agent-skills-zh --skill doubt-driven-development-vinvcn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill prevents the accumulation of unverified assumptions in long-running AI sessions by forcing a rigorous, adversarial review of non-trivial decisions before they are finalized.

Core Features & Use Cases

Adversarial Review: Spawns a fresh-context reviewer to actively find flaws, edge cases, and hidden coupling in your proposed logic.
Structured Reconciliation: Provides a disciplined framework to classify findings into actionable fixes, trade-offs, or noise.
Use Case: Use this when implementing complex thread-safe caching logic or high-risk production changes where correctness is more critical than speed.

Quick Start

Apply the doubt-driven-development skill to the current architectural proposal to identify potential failure modes and unstated assumptions.

Frequently Asked Questions about doubt-driven-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

What is adversarial code review for architectural changes?▼

Adversarial code review is a structured process that spawns a fresh-context reviewer to actively identify flaws, edge cases, and hidden coupling in high-risk architectural changes before finalization.

How do I find hidden assumptions in complex thread-safe caching logic?▼

To find hidden assumptions in caching logic, apply an adversarial review process that forces rigorous questioning of non-trivial decisions through a structured cycle of claim presentation and systematic reconciliation.

When should I use an adversarial review process for engineering decisions?▼

Use an adversarial review process for high-stakes engineering decisions like security-sensitive code, high-risk production changes, and architectural modifications where correctness is more critical than development speed.

How do I systematically classify findings from an adversarial code review?▼

Systematically classify adversarial code review findings using a structured reconciliation framework that categorizes identified flaws and edge cases into actionable fixes, acceptable trade-offs, or disregarded noise.

Can I use adversarial review to prevent unverified assumptions in long-running AI sessions?▼

Yes, adversarial review prevents the accumulation of unverified assumptions in long-running AI sessions by forcing rigorous, fresh-context questioning of non-trivial decisions before they are finalized.

What are the limitations of using adversarial review for software engineering?▼

The primary limitation of adversarial review is its overhead; it is designed for high-risk logic and architectural changes where correctness is paramount, making it less suitable for rapid development where speed outweighs strict verification.