From test-kitchen
Entry gate for build/create/implement requests: offers brainstorm or omakase parallel exploration of approaches, detects indecision during brainstorming.
npx claudepluginhub 2389-research/claude-plugins --plugin test-kitchenThis skill uses the workspace's default tool permissions.
Chef's choice exploration - when you're not sure WHAT to build, explore different approaches in parallel.
Guides strict Test-Driven Development (TDD): write failing tests first for features, bugfixes, refactors before any production code. Enforces red-green-refactor cycle.
Guides systematic root cause investigation for bugs, test failures, unexpected behavior, performance issues, and build failures before proposing fixes.
Guides A/B test setup with mandatory gates for hypothesis validation, metrics definition, sample size calculation, and execution readiness checks.
Chef's choice exploration - when you're not sure WHAT to build, explore different approaches in parallel.
Part of Test Kitchen Development:
omakase-off - Chef's choice exploration (different approaches/plans)cookoff - Same recipe, multiple cooks compete (same plan, multiple implementations)Core principle: Let indecision emerge naturally during brainstorming, then implement multiple approaches in parallel to let real code + tests determine the best solution.
When: "I want to build...", "Create a...", "Implement...", "Add a feature..."
Present:
Before we brainstorm the details, would you like to:
1. Brainstorm together - We'll explore requirements and design step by step
2. Omakase (chef's choice) - I'll generate 3-5 best approaches, implement them
in parallel, and let tests pick the winner
Detection signals:
When detected:
You seem flexible on the approach. Would you like to:
1. I'll pick what seems best and continue brainstorming
2. Explore multiple approaches in parallel (omakase-off)
| Phase | Description |
|---|---|
| 0. Entry | Present brainstorm vs omakase choice |
| 1. Brainstorm | Passive slot detection during design |
| 1.5. Decision | If slots detected, offer parallel exploration |
| 2. Plan | Generate implementation plan per variant |
| 3. Implement | Dispatch ALL agents in SINGLE message |
| 4. Evaluate | Scenario tests → fresh-eyes → judge survivors |
| 5. Complete | Finish winner, cleanup losers |
See references/detailed-workflow.md for full phase details.
docs/plans/<feature>/
design.md # Shared context from brainstorming
omakase/
variant-<slug>/
plan.md # Implementation plan for this variant
result.md # Final report
.worktrees/
variant-<slug>/ # Omakase variant worktree
| Type | Examples | Worth exploring? |
|---|---|---|
| Architectural | Storage engine, framework, auth method | Yes |
| Trivial | File location, naming, config format | No |
Only architectural decisions become slots for parallel exploration.
Max 5-6 implementations. Don't do full combinatorial explosion:
| Dependency | Usage |
|---|---|
brainstorming | Modified flow with passive slot detection |
writing-plans | Generate implementation plan per variant |
git-worktrees | Create isolated worktree per variant |
parallel-agents | Dispatch all variant subagents in parallel |
scenario-testing | Run same scenarios against all variants |
fresh-eyes | Quality review on survivors → input for judge |
finish-branch | Handle winner (merge/PR), cleanup losers |
User: "I need to build a CLI todo app."
Claude: [Triggers omakase-off]
Before we dive in, how would you like to approach this?
1. Brainstorm together
2. Omakase (chef's choice)
User: "1"
Claude: [Brainstorming proceeds, detects indecision on storage]
You seem flexible on storage (JSON vs SQLite). Would you like to:
1. Explore in parallel - I'll implement both variants
2. Best guess - I'll pick JSON (simpler)
User: "1"
[Creates plans for variant-json, variant-sqlite]
[Dispatches parallel agents in SINGLE message]
[Runs scenario tests on both]
[Fresh-eyes review on survivors]
[Presents comparison, user picks winner]
[Cleans up loser, finishes winner branch]