Parallel exploration of implementation approaches - run multiple variants simultaneously and let tests determine the winner
npx claudepluginhub 2389-research/claude-plugins --plugin test-kitchenThis 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.
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.
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.
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 · 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 |
/plugin marketplace add 2389-research/claude-plugins
/plugin install test-kitchen@2389-research
"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]
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
Which approach?
Option 1 (Brainstorm) proceeds to brainstorming skill (or fallback brainstorming), with passive slot detection.
Option 2 (Omakase) does the following:
During brainstorming, slot detection can also trigger it:
Claude: What storage approach would you prefer?
User: "not sure, either could work"
Claude: [marks storage as architectural slot]
Claude: For authentication?
User: "no preference, you pick"
Claude: [marks auth as slot, detects 2+ uncertain responses]
You seem flexible on the approach. Would you like to:
1. I'll pick what seems best and continue
2. Explore multiple approaches in parallel (omakase-off)
→ I'll implement 2-3 variants and let tests decide
User: "Looks good, let's implement"
Claude: I'm using test-kitchen:cookoff.
How would you like to implement this design?
1. Cookoff (recommended) - 3 parallel agents, each creates own plan, pick best
→ Complexity: medium feature
2. Single subagent - One agent plans and implements
3. Local - Plan and implement here
Which approach?
Option 1 (Cookoff):
Options 2/3 -- single agent or local implementation proceeds normally.
Skills can't passively detect "uncertainty" or "readiness" -- they must claim specific moments in the conversation flow.
Test Kitchen orchestrates these skills (falls back gracefully if not installed):
superpowers:brainstormingsuperpowers:writing-planssuperpowers:executing-planssuperpowers:using-git-worktreessuperpowers:dispatching-parallel-agentssuperpowers:test-driven-developmentsuperpowers:verification-before-completionscenario-testing:skillsfresh-eyes-review:skillssuperpowers:finishing-a-development-branchNamed after a restaurant test kitchen, where chefs try multiple approaches before putting a dish on the menu.
If Test Kitchen saved you from building the wrong approach first, a ⭐ helps us know it's landing.
Built by 2389 · Part of the Claude Code plugin marketplace
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Automates browser interactions for web testing, form filling, screenshots, and data extraction
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.