Community Plugin

test-kitchen

Name: test-kitchen
Rating: 4.2 (23 reviews)
Author: 2389-research

Parallel exploration of implementation approaches - implements multiple variants simultaneously and lets tests determine the winner

1.0.0

Updated 9 days ago

AI Insight

Enables parallel development of multiple code variants, using tests to automatically compare and select the best implementation approach.

Why this plugin

Solves analysis paralysis by letting you explore different solutions simultaneously in isolated worktrees, with automated testing to objectively determine the optimal variant.

Prerequisites

Requires Git for worktree management and a testing framework. No specific API keys mentioned.

testing

parallel

development

Install

Run in your terminal

npx claudepluginhub 2389-research/claude-plugins

Components

Skills

cookoff

inherits

This skill should be used when moving from design to implementation. Triggers on "let's build", "implement this", "looks good let's code", "ready to implement". Presents options for parallel agent competition (cookoff), single subagent, or local implementation. Each agent creates own plan from shared design for genuine variation.

judge

inherits

Scoring framework for test-kitchen cookoff and omakase-off. Invoked at Phase 4 to evaluate implementations using 5-criteria scoring. Do not invoke directly - called by cookoff/omakase-off.

omakase-off

inherits

1 assets

This skill should be used as the entry gate for build/create/implement requests. Triggers on "build X", "create Y", "implement Z", "add feature", "try both approaches", "not sure which approach". Offers brainstorm-together or omakase (chef's choice parallel exploration) options. Detects indecision during brainstorming to offer parallel exploration.

Stats

Stars23

Forks1

MaintenanceExcellent

Last Commit9 days ago

Community Promotion

Collections

Links

View on GitHub

View README

Plugin Marketplace JSON

Similar Plugins

everything-claude-code

56.9k

149

Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use

v1.7.0

agent-browser

16.8k

Automates browser interactions for web testing, form filling, screenshots, and data extraction

v0.15.1

voltagent-qa-sec

10.9k

Testing, security, and code quality experts - code review, penetration testing, QA automation

v1.0.1

feature-dev

9.1k

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

v1.0.0