Ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.
A Claude Code plugin that iteratively refines product specifications through multi-model debate until consensus is reached. **Key insight:** A single LLM reviewing a spec will miss things. Multiple LLMs debating a spec will catch gaps, challenge assumptions, and surface edge cases that any one model would overlook. The result is a document that has survived rigorous adversarial review. **Claude is an active
git clone --depth 1 https://github.com/zscole/adversarial-spec.git ~/.claude/skills/adversarial-spec
Restart Claude Code afterwards. See the README for skill-specific setup.
Using Codex CLI? Copy the same folder to ~/.codex/skills/adversarial-spec instead.
No specific triggers listed.
A Claude Code plugin that iteratively refines product specifications through multi-model debate until consensus is reached. **Key insight:** A single LLM reviewing a spec will miss things. Multiple LLMs debating a spec will catch gaps, challenge assumptions, and surface edge cases that any one model would overlook. The result is a document that has survived rigorous adversarial review. **Claude is an active
Clone it into your personal skills folder: git clone --depth 1 https://github.com/zscole/adversarial-spec.git ~/.claude/skills/adversarial-spec — then restart Claude Code.
Adversarial Spec is open source on GitHub (559 stars at last check) and published by zscole.
Browse other meta skills in the Meta category of this directory.