doubt-driven-development

Subjects non-trivial decisions to fresh-context adversarial review before they stand.

Updated Sep 15, 2026
One-click install
npx skills add https://github.com/Qiuyi-Hong/addyosmani-skills --skill doubt-driven-development-qiuyi-hong
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doubt-driven-development
Source: https://github.com/Qiuyi-Hong/addyosmani-skills/tree/main/skills/doubt-driven-development
Command: npx skills add https://github.com/Qiuyi-Hong/addyosmani-skills --skill doubt-driven-development-qiuyi-hong

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long coding sessions accumulate context that quietly turns assumptions into facts, and confident answers are not always correct ones. This Skill catches wrong directions early by cross-examining every non-trivial decision with a fresh-context adversarial reviewer while course-correction is still cheap. ## Core Features & Use Cases - Five-step doubt cycle: CLAIM the decision, EXTRACT the smallest reviewable artifact plus contract, DOUBT it with an adversarial fresh-context reviewer, RECONCILE findings by precedence, and STOP at a bounded limit of three cycles. - Cross-model escalation: Optionally routes the artifact and contract to external CLI reviewers such as Gemini CLI or Codex CLI through read-only sandboxed invocations, with explicit user authorization for every run. - Use Case: Before committing a new caching layer claimed to be thread-safe, the Skill extracts the diff and its contract, spawns an adversarial reviewer instructed to find issues rather than validate, classifies each finding as actionable, trade-off, or noise, and loops until findings are trivial. ## Quick Start Ask the agent to apply doubt-driven development to stress-test the architectural decision or code change you are about to commit.

Frequently Asked Questions about doubt-driven-development

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

FAQPage Schema
How do I stress-test a code decision before committing it?

Apply the five-step doubt cycle: write the claim, extract the smallest reviewable artifact plus its contract, invoke a fresh-context reviewer with an adversarial find-issues prompt, classify each finding against the artifact text, and stop after trivial findings or three cycles.

What is the difference between doubt-driven development and code review?

Doubt-driven development is an in-flight posture that cross-examines individual non-trivial decisions while course-correction is cheap. Code review is a post-hoc verdict on a finished artifact such as a pull request, and the two are complementary.

When should I not use adversarial review on my changes?

Skip it for mechanical operations like renaming or formatting, one-line changes with obvious correctness, reading or summarizing code, pure tooling operations, and when the user explicitly prioritizes speed over verification.

Can I get a second opinion from a different AI model during review?

Yes. In interactive sessions the Skill offers cross-model escalation through external CLIs such as Gemini CLI or Codex CLI, invoked in read-only sandbox mode via stdin. Each invocation requires explicit user authorization and is skipped with an announcement in non-interactive contexts.

Why does the reviewer only receive the artifact and contract?

Passing the original claim or reasoning biases the reviewer toward agreement. Supplying only the artifact and contract forces the reviewer to independently determine whether the work satisfies its requirements, producing genuine disproof attempts rather than validation.