---
title: "Adversarial Decision Review: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/addyosmani-doubt-driven-development/
description: "Submit a bounded artifact and its contract to an independent reviewer before accepting a consequential decision."
---

# Adversarial Decision Review: review, setup & limitations · Undominated.ai

> Submit a bounded artifact and its contract to an independent reviewer before accepting a consequential decision.

[← Explore all skills](/skills/)

DEVELOPMENT WORKFLOW / addyosmani

# Adversarial Decision Review

Submit a bounded artifact and its contract to an independent reviewer before accepting a consequential decision.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/addyosmani/agent-skills/tree/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/doubt-driven-development)

SOURCE REVIEW

 Reviewed 2026-10-15
 Evidence 5 linked sources
 Publisher addyosmani
 Licence [MIT ↗](https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/LICENSE)
 Revision aeac41d4d005
 [Read what was—and wasn’t—checked ↓](#review)

“Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.”

 [addyosmani · upstream description ↗](https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/doubt-driven-development/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The definition separates CLAIM from reviewer input, requires artifact-plus-contract only and warns against recursive persona orchestration.
- Check a migration invariant without priming the reviewer with the implementer conclusion.

### A good fit for

 - Check a migration invariant without priming the reviewer with the implementer conclusion.

### Weigh up before choosing

 - An adversarial prompt does not establish independence or expertise. The skill requires host delegation; self-questioning is explicitly a degraded fallback.
- Source inspection only; no installation, authenticated operation, runtime benchmark or security certification was performed.
- The review loop is bounded at three cycles before escalation; an oversized artifact must be decomposed instead of extending the loop.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - skills/doubt-driven-development/SKILL.md
- LICENSE
- README.md

### Our findings

 - The definition separates CLAIM from reviewer input, requires artifact-plus-contract only and warns against recursive persona orchestration.

### Not established by this review

 - Third-party instructions and helpers were not executed; service access, host compatibility and outcomes remain untested.
- Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/README.md)

DOCUMENTED COMMAND

 npx skills add addyosmani/agent-skills/skills/doubt-driven-development Copy command ↗

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

 Optional: install the reviewed revision

Keeps the original source and installer version where recorded, while leaving your AI tools and installation scope for you to choose.

 npx skills add https://github.com/addyosmani/agent-skills/tree/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/doubt-driven-development Copy reviewed-revision command ↗ - Install the pinned directory interactively and retain its referenced files; inspect the source before granting tool access.
- Extract the smallest reviewable artifact and contract, omit the proposed verdict, then adjudicate concrete counterexamples with evidence.

### Before you start

 - Host support for an isolated reviewer plus repository/source access

### Compatibility

Agents supporting directory-based SKILL.md instructions

### Local instructions with workflow-dependent access

 - Spawns workers that inherit host access and reads implementation evidence; review itself does not authorize commits or deployment.

### Cost model

Skill source is freely available under its stated licence; host, infrastructure and service usage may incur charges.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Pinned skills/doubt-driven-development/SKILL.md ↗](https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/doubt-driven-development/SKILL.md) Checked 2026-10-14 https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/doubt-driven-development/SKILL.md Supports: summary, review, install, access, limitations
- [Pinned LICENSE ↗](https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/LICENSE) Checked 2026-10-14 https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/LICENSE Supports: license
- [Pinned README.md ↗](https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/README.md) Checked 2026-10-14 https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/README.md Supports: summary, review, install, access, limitations
- [Definition excerpt rechecked at the existing revision ↗](https://raw.githubusercontent.com/addyosmani/agent-skills/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/doubt-driven-development/SKILL.md) Checked 2026-10-15 https://raw.githubusercontent.com/addyosmani/agent-skills/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/doubt-driven-development/SKILL.md Supports: limitations, review
- [Installation-source command audit at the existing revision ↗](https://raw.githubusercontent.com/addyosmani/agent-skills/aeac41d4d005999432bb7312f7ff06383a91d59d/README.md) Checked 2026-10-15 https://raw.githubusercontent.com/addyosmani/agent-skills/aeac41d4d005999432bb7312f7ff06383a91d59d/README.md Supports: review

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Source-Driven Implementation ↗ Ground version-sensitive code changes in official documentation and explicit source citations.](/skills/addyosmani-source-driven-development/)[### Bug Reproduction Brief ↗ Reduce an uncertain bug report to an evidence-backed failing fixture before repair.](/skills/github-bug-reproduction-brief/)[### C# / TypeScript API Contract Drift ↗ Compare C# controller and DTO contracts with TypeScript or JavaScript consumers in both directions.](/skills/github-api-breaking-change-detector/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
