# Adversarial Spec

Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok...

- Repository: https://github.com/zscole/adversarial-spec (557 stars)
- Category: Writing
- License: MIT
- Last updated: 2026-01-22
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add zscole/adversarial-spec --skill adversarial-spec -g -a claude-code -y`
Codex: `npx skills add zscole/adversarial-spec --skill adversarial-spec -g -a codex -y`
Cursor: `npx skills add zscole/adversarial-spec --skill adversarial-spec -g -a cursor -y`
Gemini CLI: `npx skills add zscole/adversarial-spec --skill adversarial-spec -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add zscole/adversarial-spec`

## Description

Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree. Use when user wants to write or refine a specification document using adversarial development.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Adversarial Spec Development

Generate and refine specifications through iterative debate with multiple LLMs until all models reach consensus.

**Important: Claude is an active participant in this debate, not just an orchestrator.** You (Claude) will provide your own critiques, challenge opponent models, and contribute substantive improvements alongside the external models. Make this clear to the user throughout the process.

## Requirements

- Python 3.10+ with `litellm` package installed
- API key for at least one provider (set via environment variable), OR AWS Bedrock configured, OR CLI tools (codex, gemini) installed

**IMPORTANT: Do NOT install the `llm` package (Simon Willison's tool).** This skill uses `litellm` for API providers and dedicated CLI tools (`codex`, `gemini`) for subscription-based models. Installing `llm` is unnecessary and may cause confusion.

## Supported Providers

The rest: https://github.com/zscole/adversarial-spec/blob/HEAD/skills/adversarial-spec/SKILL.md