test-kitchen
Description
You have a spec. Three valid approaches exist. Instead of guessing which one to build, Test Kitchen builds all of them in parallel git worktrees and lets your tests pick the winner.
Installation
claude install-skill https://github.com/2389-research/test-kitchen README
Test Kitchen
You have a spec. Three valid approaches exist. Instead of guessing which one to build, Test Kitchen builds all of them in parallel git worktrees and lets your tests pick the winner.
Read more: [Cookoff: Same Spec, Different Code](https://2389.ai/posts/cookoff-same-spec-different-code/) · [Omakase: Show Me](https://2389.ai/posts/omakase-show-me/)
Parallel implementation framework with two gate skills:
| Skill | Gate | Trigger |
|---|---|---|
test-kitchen:omakase-off |
Entry | FIRST on any build/create/implement request |
test-kitchen:cookoff |
Exit | At design→implementation transition |
Installation
/plugin marketplace add 2389-research/claude-plugins
/plugin install test-kitchen@2389-research
Flow
"Build X" / "Create Y" / "Implement Z"
↓
┌─────────────────────────────────────┐
│ OMAKASE-OFF (entry gate) │
│ Wraps brainstorming │
│ │
│ Choice: │
│ 1. Brainstorm together │
│ 2. Omakase (3-5 parallel designs) │
└─────────────────────────────────────┘
↓
[Brainstorming / Design phase]
↓
Design complete, "let's implement"
↓
┌─────────────────────────────────────┐
│ COOKOFF (exit gate) │
│ Wraps implementation │
│ │
│ Choice: │
│ 1. Cookoff (2-5 parallel agents) │
│ 2. Single subagent │
│ 3. Local implementation │
└─────────────────────────────────────┘
↓
[Implementation]
Quick examples
Entry gate: omakase-off
When you make a build/create request:
User: "Build a notification system"
Claude: I'm using test-kitchen:omakase-off.
How would you like to explore this?
1. Brainstorm together - We'll work through the design step by step
2. Omakase - I'll generate 3-5 best approaches, implement in parallel, tests pick winner
...
Related Skills
Webapp Testing
When testing local web applications or verifying UI behaviorTest local web applications using Playwright for UI verification and debugging
Testing official #29
, [#52](https://github.com/affaan-m/everything-claude-code/issues/52), [#103](https://github.com/affaan-m/everything-claude-code/issues/103)). The behavior changed between Claude Code versions, leading to confusion. We now have a regression test to prevent this from being reintroduced.
Testing community Fix Issue
by metabase - Addresses GitHub issues by taking issue number as parameter, analyzing context, implementing solution, and testing/validating the fix for proper integration.
Testing community Pypict Test Design
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for optimized test suites
Testing community gstack
| 15,000+ | Garry Tan's exact Claude Code setup: 6 opinionated tools that serve as CEO, Eng Manager, Release Manager, and QA Engineer. 15K+ stars in 5 days. |
Testing community **playwright**
| claude-plugins-official | Browser automation, E2E testing, screenshots |
Testing community