adversarial-spec
A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.
- 557 stars
- 51 forks
- 3 open issues
- Language: Python
- License: MIT
- updated
Install
git clone https://github.com/zscole/adversarial-spec ~/.claude/skills/adversarial-spec- Clone the repository into your ~/.claude/skills directory (or copy the skill folder containing SKILL.md).
- Start a new Claude Code session so the skill registry reloads.
- Invoke it by name, or let Claude trigger it automatically when the task matches.
If the repo bundles several skills, copy only the folders you need.
1 items in this repository
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.
Skills overview
What people ask about adversarial-spec
What is zscole/adversarial-spec?
zscole/adversarial-spec is skills for the Claude AI ecosystem. A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus. It has 557 GitHub stars and its last recorded update is dated 2026-01-22.
How do I install adversarial-spec?
You can install adversarial-spec by cloning the repository (https://github.com/zscole/adversarial-spec) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is zscole/adversarial-spec safe to use?
Our security agent has analyzed zscole/adversarial-spec and assigned a Trust Score of 77/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains zscole/adversarial-spec?
zscole/adversarial-spec is maintained by zscole. The last recorded GitHub activity is dated 2026-01-22, with 3 open issues.
Are there alternatives to adversarial-spec?
Yes. On ClaudeWave you can browse similar skills at /categories/skills, sorted by popularity or recent activity.