A Claude Code plugin that iteratively refines product specifications through multi-model debate until consensus is reached.
How to install adversarial-spec?
zscole/adversarial-spec
$claude plugin marketplace add zscole/adversarial-specInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install adversarial-spec by running `claude plugin marketplace add zscole/adversarial-spec`, then use it for the current task and follow its documentation at https://github.com/zscole/adversarial-spec.
.claude-plugin/plugin.json
| 1 | # .claude-plugin/plugin.json |
| 2 | claude plugin marketplace add zscole/adversarial-spec |
Related
6 picksType
- planning-with-filesPersistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style.Jul 2026
- pm-skillsPM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.Jul 2026
- product-manager-skillsA comprehensive library of PM skills covering discovery, strategy, delivery, finance, AI orchestration, and career leadership.Jul 2026
- arc-kitThe Enterprise Architecture Governance Harness — strategy, architecture, delivery, and assurance using AI coding assistantsJul 2026
- skillsWondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 62 skills for product strategy, UX design, marketing, sales, motivation, conversion optimization, code quality, and systems architecture, plus 12 guided-journey metaskills that…Jul 2026
- pm-claude-skills822 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — decode a lease, write a PRD, run the AGM, prep the D&D session, practice the salary negotiation. Plain-markdown, MIT, in Anthropic's official plugin directory.Jul 2026
