⚔️

AI EngineeringPython

Adversarial Spec Development

Adversarial Spec Development is an AI Engineering skill for Claude Code, published by zscole in adversarial-spec.

556 stars48 forkson zscole/adversarial-specAdded 2026/08/25Repository updated 2026/01/22

View source on GitHub Download repo ZIP

anthropicclaude-aiclaude-codeclaude-code-pluginclaude-skillsllmorchestration

Install in seconds

Install Adversarial Spec Development

Copy Adversarial Spec 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/zscole/adversarial-spec/tree/main/skills/adversarial-spec ~/.claude/skills/adversarial-spec

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

Without Node.js

git clone https://github.com/zscole/adversarial-spec.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/adversarial-spec/SKILL.md in zscole/adversarial-spec
Installs to: ~/.claude/skills/adversarial-spec
Collection: The only skill cataloged from this repository
Category: AI Engineering — 2451 skills

What Adversarial Spec Development does

Adversarial Spec Development refines product specs by debating changes across multiple LLMs until they converge. Use it when you want to write or improve a specification with adversarial review and consensus building.

Adversarial Spec Development is cataloged under AI Engineering on DirSkills. Adversarial Spec Development comes from a repository tagged anthropic, claude-ai, claude-code, claude-code-plugin and claude-skills.

Documentation

README

Excerpt

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

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

Commands Adversarial Spec Development provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/login
/logout

Frequently asked about Adversarial Spec Development

How does Adversarial Spec Development compare to other AI Engineering skills?
Adversarial Spec Development ranks #2033 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. 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 Adversarial Spec Development against them. Open each page to compare what they document and how they install.

More AI Engineering skills

Adversarial Spec Development is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #2033 by stars among them.

Browse all AI Engineering skills →

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.