skills/2389-research/test-kitchen/omakase-off/SKILL.md
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.
npx skillsauth add aiskillstore/marketplace omakase-offInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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]
development
Apple Human Interface Guidelines for content display components. Use this skill when the user asks about charts component, collection view, image view, web view, color well, image well, activity view, lockup, data visualization, content display, displaying images, rendering web content, color pickers, or presenting collections of items in Apple apps. Also use when the user says how should I display charts, what's the best way to show images, should I use a web view, how do I build a grid of items, what component shows media, or how do I present a share sheet. Cross-references: hig-foundations for color/typography/accessibility, hig-patterns for data visualization patterns, hig-components-layout for structural containers, hig-platforms for platform-specific component behavior.
tools
Automate HelpDesk tasks via Rube MCP (Composio): list tickets, manage views, use canned responses, and configure custom fields. Always search tools first for current schemas.
testing
Expert Haskell engineer specializing in advanced type systems, pure functional design, and high-reliability software. Use PROACTIVELY for type-level programming, concurrency, and architecture guidance.
tools
GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server. This skill covers schema design, resolvers, DataLoader for N+1 prevention, federation for microservices, and client integration with Apollo/urql. Key insight: GraphQL is a contract. The schema is the API documentation. Design it carefully.