Doubt Driven Development

Most code review happens after you've already committed to an approach. This flips that: before any non-trivial decision stands (architectural choices, production deploys, cross-boundary logic), you spawn a fresh-context reviewer with an explicit adversarial prompt to disprove it. Not validate, disprove. The skill defines what counts as non-trivial, gives you a five-step checklist (CLAIM, EXTRACT, DOUBT, RECONCILE, STOP), and includes cross-model escalation hooks so you can throw the same artifact at Gemini or another model to catch blind spots your first reviewer shared with you. Use it when correctness matters more than speed, when working in unfamiliar code, or any time debugging later would cost more than verification now.

skills.sh installs: 65.8K
GitHub stars: 114.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add addyosmani/agent-skills --skill doubt-driven-development --agent claude-code

Installs into .claude/skills of the current project.

Files

Doubt-Driven Development

Overview

A confident answer is not a correct one. Long sessions accumulate context that quietly turns assumptions into "facts" without anyone noticing. Doubt-driven development is the discipline of materializing a fresh-context reviewer — biased to disprove, not approve — before any non-trivial output stands.

This is not /review. /review is a verdict on a finished artifact. This is an in-flight posture: non-trivial decisions get cross-examined while course-correction is still cheap.

When to Use

A decision is non-trivial when at least one of these is true:

It introduces or modifies branching logic
It crosses a module or service boundary
It asserts a property the type system or compiler cannot verify (thread safety, idempotence, ordering, invariants)
Its correctness depends on context the future reader cannot see
Its blast radius is irreversible (production deploy, data migration, public API change)

Apply the skill when:

SKILL.md on GitHub