๐Ÿง
QualityJavaScript

Doubt-Driven Development

by addyosmani

Doubt-Driven Development is a Quality skill for Claude Code, published by addyosmani in agent-skills.

86.7K stars9.3K forkson addyosmani/agent-skillsAdded 2026/08/13Repository updated 2026/08/11
agent-skillsantigravityclaude-codecodexcursorskills
Install in seconds
Install Doubt-Driven Development
Copy Doubt-Driven Development into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/addyosmani/agent-skills/tree/main/skills/doubt-driven-development ~/.claude/skills/doubt-driven-development

Requires Node.js. Downloads this skill only โ€” not the rest of the repository โ€” into your Claude Code skills folder.

Without Node.js

git clone https://github.com/addyosmani/agent-skills.git

Clones the whole repository, then copy the skillโ€™s own directory into your skills folder yourself.

In this catalog

Source file
skills/doubt-driven-development/SKILL.md in addyosmani/agent-skills
Installs to
~/.claude/skills/doubt-driven-development
Collection
One of 24 skills cataloged from this repository
Category
Quality โ€” 1354 skills

What Doubt-Driven Development does

Doubt-Driven Development subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, in unfamiliar code, or when stakes are high.

Doubt-Driven Development is cataloged under Quality on DirSkills. Doubt-Driven Development comes from a repository tagged agent-skills, antigravity, claude-code, codex and cursor.

Documentation

README

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 โ€” biased to disprove, not approve โ€” 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:

This is the opening of the README. Read the full README on GitHub.

Commands Doubt-Driven Development provides

Slash commands named in this skillโ€™s SKILL.md, listed in the order they first appear.

  • /review
  • /loop

Frequently asked about Doubt-Driven Development

  • What else does addyosmani publish alongside Doubt-Driven Development?

    Doubt-Driven Development is one of 24 skills that DirSkills catalogs from addyosmani/agent-skills, the repository it ships in. Its siblings there include API and Interface Design, Agent Skill Discovery and Browser Testing. Each one is a separate skill with its own page in this directory, installs the same way Doubt-Driven Development does, and is maintained by addyosmani in that same repository. The rest of the collection is listed on the addyosmani/agent-skills page.

  • How does Doubt-Driven Development compare to other Quality skills?

    Doubt-Driven Development ranks #21 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Doubt-Driven Development against them. Open each page to compare what they document and how they install.

More from addyosmani/agent-skills

Doubt-Driven Development is one of 24 skills cataloged on DirSkills from addyosmani/agent-skills.

See all 24 skills โ†’
๐Ÿ”Œ
3w ago

API and Interface Design

API and Interface Design guides the creation of stable, well-documented interfaces including REST APIs, GraphQL schemas, module boundaries, and component props. Use it when designing new endpoints, defining contracts between teams, or changing existing public interfaces.
Quality
86.7K9.3K
๐Ÿงญ
3w ago

Agent Skill Discovery

Agent Skill Discovery discovers and invokes agent skills, helping an agent identify the right engineering workflow for a task. Use it when starting a session or when unsure which skill applies.
AI Engineering
86.7K9.3K
๐Ÿงช
3w ago

Browser Testing

Browser Testing runs tests and inspections in a real browser via Chrome DevTools MCP. Use it when building or debugging browser UI to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output.
Quality
86.7K9.3K
๐Ÿš€
3w ago

CI/CD and Automation

CI/CD and Automation sets up and modifies build and deployment pipelines, automating quality gates like lint, type check, tests, build, and security audits so no change reaches production without passing checks.
DevOps
86.7K9.3K
๐Ÿ”
3w ago

Code Review and Quality

Code Review and Quality conducts multi-axis code review across correctness, readability, architecture, security, and performance before merging changes. Use it to assess code quality before code enters the main branch.
Quality
86.7K9.3K
๐Ÿงน
3w ago

Code Simplification

Code Simplification simplifies code by reducing complexity while preserving exact behavior. Use it when refactoring for clarity, improving readability, or reviewing code that has accumulated unnecessary complexity.
Quality
86.7K9.3K