aiskillstore/marketplace / skills/2389-research/omakase-off
omakase-off
VerifiedThis 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.8 KB |
| references/detailed-workflow.md | markdown | 7.9 KB |
| skill-report.json | config | 26.3 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-04T18:02:43.954Z",
"slug": "2389-research-omakase-off",
"source_url": "https://github.com/2389-research/claude-plugins/tree/main/test-kitchen/skills/omakase-off",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "c1ac5852c4e75d61bd0ab601e77dce3e121b300c49d2f973ae74837f9f9419aa",
"tree_hash": "b95c8233cdd9cafbb971d13edcfcd496364aa14df48357556dd9b8a24f4bbc79",
"provenance": {
"model_requested": "gpt-5.5:high",
"model_effective": "codex:gpt-5.5:high",
"fallback_chain": [
{
"agent": "codex",
"model": "gpt-5.5",
"effort": "high",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "omakase-off",
"description": "Guides software build requests through brainstorming, optional parallel approach exploration, variant implementation, scenario testing, and winner selection.",
"summary": "Explore competing software implementation approaches in parallel and choose a tested winner.",
"icon": "📦",
"version": "1.0.0",
"author": "2389-research",
"license": "MIT",
"tags": [
"workflow",
"parallel-exploration",
"architecture",
"implementation-planning",
"scenario-testing"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network"
],
"category": "coding"
},
"security_audit": {
"risk_level": "medium",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "The static findings are false positives from Markdown backticks, fenced examples, and ordinary planning language. No prompt injection or network reconnaissance evidence was found. One medium semantic risk remains because the workflow directs deletion of losing worktrees and branches during cleanup.",
"remediation": [
{
"issue": "Destructive cleanup guidance",
"suggestion": "Require explicit user confirmation, dirty-state checks, and recovery guidance before removing worktrees or deleting branches.",
"severity": "medium"
},
{
"issue": "Repository mutation disclosure",
"suggestion": "Document that the workflow may create and delete branches and worktrees, and recommend use only in user-owned repositories.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 11,
"line_end": 11
},
{
"file": "SKILL.md",
"line_start": 12,
"line_end": 12
},
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 29
},
{
"file": "SKILL.md",
"line_start": 29,
"line_end": 38
},
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 42
},
{
"file": "SKILL.md",
"line_start": 42,
"line_end": 61
},
{
"file": "SKILL.md",
"line_start": 61,
"line_end": 65
},
{
"file": "SKILL.md",
"line_start": 65,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 75,
"line_end": 105
},
{
"file": "SKILL.md",
"line_start": 105,
"line_end": 106
},
{
"file": "SKILL.md",
"line_start": 106,
"line_end": 107
},
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 108
},
{
"file": "SKILL.md",
"line_start": 108,
"line_end": 109
},
{
"file": "SKILL.md",
"line_start": 109,
"line_end": 110
},
{
"file": "SKILL.md",
"line_start": 110,
"line_end": 111
},
{
"file": "SKILL.md",
"line_start": 111,
"line_end": 115
},
{
"file": "SKILL.md",
"line_start": 115,
"line_end": 139
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 3,
"line_end": 3
}
]
}
],
"static_findings": [
{
"id": "blocker:references/detailed-workflow.md:87:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "references/detailed-workflow.md",
"line_start": 87,
"line_end": 87,
"snippet": "2. Best guess - I'll pick what seems best and proceed with one plan"
},
{
"id": "blocker:references/detailed-workflow.md:187:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "references/detailed-workflow.md",
"line_start": 187,
"line_end": 188,
"snippet": "- Verify all tests pass"
},
{
"id": "external_commands:SKILL.md:11:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 11,
"line_end": 11,
"snippet": "- `omakase-off` - Chef's choice exploration (different approaches/plans)"
},
{
"id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 12,
"line_end": 12,
"snippet": "- `cookoff` - Same recipe, multiple cooks compete (same plan, multiple implementations)"
},
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 23,
"line_end": 29,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 29,
"line_end": 38,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 38,
"line_end": 42,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 42,
"line_end": 61,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:61:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 61,
"line_end": 65,
"snippet": "See `references/detailed-workflow.md` for full phase details."
},
{
"id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 65,
"line_end": 75,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 75,
"line_end": 105,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 105,
"line_end": 106,
"snippet": "| `brainstorming` | Modified flow with passive slot detection |"
},
{
"id": "external_commands:SKILL.md:106:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 106,
"line_end": 107,
"snippet": "| `writing-plans` | Generate implementation plan per variant |"
},
{
"id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 107,
"line_end": 108,
"snippet": "| `git-worktrees` | Create isolated worktree per variant |"
},
{
"id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 108,
"line_end": 109,
"snippet": "| `parallel-agents` | Dispatch all variant subagents in parallel |"
},
{
"id": "external_commands:SKILL.md:109:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 109,
"line_end": 110,
"snippet": "| `scenario-testing` | Run same scenarios against all variants |"
},
{
"id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 110,
"line_end": 111,
"snippet": "| `fresh-eyes` | Quality review on survivors → input for judge |"
},
{
"id": "external_commands:SKILL.md:111:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 111,
"line_end": 115,
"snippet": "| `finish-branch` | Handle winner (merge/PR), cleanup losers |"
},
{
"id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 115,
"line_end": 139,
"snippet": "```"
},
{
"id": "network:SKILL.md:3:python-http-libraries",
"category": "network",
"severity": "low",
"pattern": "Python HTTP libraries",
"file": "SKILL.md",
"line_start": 3,
"line_end": 3,
"snippet": "description: This skill should be used as the entry gate for build/create/implement requests. Trigge"
},
{
"id": "blocker:SKILL.md:129:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "SKILL.md",
"line_start": 129,
"line_end": 129,
"snippet": "2. Best guess - I'll pick JSON (simpler)"
}
],
"finding_verdicts": [
{
"id": "blocker:references/detailed-workflow.md:87:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The line is a user-facing choice labeled \"Best guess\" during planning. It contains no network probing, host discovery, or reconnaissance behavior."
},
{
"id": "blocker:references/detailed-workflow.md:187:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The cited text says to verify tests pass before completion. This is normal quality verification, not network reconnaissance."
},
{
"id": "external_commands:SKILL.md:11:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks mark the skill name in Markdown prose. No Ruby backtick operator or shell execution is present."
},
{
"id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks mark another skill name in a Markdown bullet. This is documentation formatting, not executable code."
},
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This is the opening fence for a text prompt example. It does not execute a shell command or interpolate user input."
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This is the closing fence for a Markdown prompt example. It is static documentation, not runtime command execution."
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This is a fenced Markdown example showing a user choice prompt. It contains no shell or Ruby execution path."
},
{
"id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This closes a fenced Markdown prompt example. The backticks are documentation syntax, not shell execution."
},
{
"id": "external_commands:SKILL.md:61:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks wrap a local reference file path in prose. They do not invoke a command or evaluate code."
},
{
"id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The fenced block describes a planned directory layout. It is a documentation example and has no execution semantics."
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This closes the static directory-layout example. No command interpreter or Ruby code is involved."
},
{
"id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format a dependency name in a Markdown table. This is not a shell command or executable construct."
},
{
"id": "external_commands:SKILL.md:106:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format a dependency name in documentation. There is no command execution or dynamic evaluation."
},
{
"id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the git-worktrees skill name. This Markdown table row does not execute external commands."
},
{
"id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the parallel-agents skill name. It is static prose, not Ruby shell execution."
},
{
"id": "external_commands:SKILL.md:109:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the scenario-testing skill name. No command is invoked by this Markdown row."
},
{
"id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the fresh-eyes skill name. It is documentation text rather than executable shell syntax."
},
{
"id": "external_commands:SKILL.md:111:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the finish-branch skill name in a table. There is no Ruby backtick execution."
},
{
"id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This begins a fenced example flow between user and assistant. The content is illustrative workflow text, not executable code."
},
{
"id": "network:SKILL.md:3:python-http-libraries",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The word \"requests\" appears in the skill description as ordinary English. There is no Python requests import or HTTP client usage."
},
{
"id": "blocker:SKILL.md:129:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The line is an example option saying the assistant will pick JSON as a best guess. It has no network scanning or reconnaissance intent."
}
],
"semantic_findings": [
{
"title": "Destructive Git Cleanup Without Explicit Confirmation",
"description": "The workflow instructs cleanup of losing variants with git worktree removal and branch deletion. Without an explicit confirmation and dirty-state check, this could delete useful local work.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 98,
"line_end": 99
},
{
"file": "references/detailed-workflow.md",
"line_start": 191,
"line_end": 195
}
],
"confidence": 0.86,
"confidence_reasoning": "The files explicitly require cleanup of loser worktrees and show branch deletion commands. The risk is contextual because cleanup can be safe when confirmed and checked first."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Destructive Git Cleanup Without Explicit Confirmation",
"description": "The workflow instructs cleanup of losing variants with git worktree removal and branch deletion. Without an explicit confirmation and dirty-state check, this could delete useful local work.",
"locations": [
{
"file": "SKILL.md",
"line_start": 98,
"line_end": 99
},
{
"file": "references/detailed-workflow.md",
"line_start": 191,
"line_end": 195
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.86,
"confidence_reasoning": "The files explicitly require cleanup of loser worktrees and show branch deletion commands. The risk is contextual because cleanup can be safe when confirmed and checked first."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 2,
"total_lines": 368,
"audit_model": "codex",
"audited_at": "2026-07-04T18:02:43.954Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Explore Build Approaches in Parallel",
"value_statement": "Software build requests often have unclear architectural choices. This skill guides brainstorming, parallel implementation, testing, and winner selection.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"omakase-off skill",
"parallel implementation",
"architecture exploration",
"AI coding workflow",
"scenario testing",
"git worktrees",
"implementation planning"
],
"actual_capabilities": [
"Presents a brainstorm or omakase choice before detailed build planning.",
"Detects repeated uncertainty about architectural decisions during brainstorming.",
"Defines variant plans under a shared feature planning directory.",
"Orchestrates parallel agent implementation using isolated worktrees.",
"Requires scenario testing, fresh review, and judging before completion.",
"Documents the winning approach and cleanup results."
],
"limitations": [
"Depends on referenced skills or fallback workflows for full execution.",
"Can create several branches and worktrees in one repository.",
"Needs user context before it can choose useful implementation variants.",
"Cleanup steps require care to avoid deleting useful local work."
],
"use_cases": [
{
"title": "Choose a Feature Architecture",
"description": "Compare storage, API, or framework options by implementing focused variants and testing them against the same scenarios.",
"target_user": "Software developer"
},
{
"title": "Resolve Product Ambiguity",
"description": "Turn uncertain requirements into a small set of concrete implementation paths for stakeholder review.",
"target_user": "Product manager"
},
{
"title": "Evaluate Technical Tradeoffs",
"description": "Use real code, tests, and reviews to compare maintainability, fit, and implementation cost.",
"target_user": "Engineering lead"
}
],
"prompt_templates": [
{
"title": "Start a New Build",
"scenario": "Begin with a simple feature request.",
"prompt": "Build a small CLI todo app. Use omakase-off to help me choose the best approach."
},
{
"title": "Compare Two Options",
"scenario": "You already know the main alternatives.",
"prompt": "Implement this feature with two variants: one using JSON storage and one using SQLite. Compare them with scenario tests."
},
{
"title": "Find Open Decisions",
"scenario": "You want help identifying architectural choices.",
"prompt": "Brainstorm this dashboard feature with me. If I seem undecided about architecture, offer parallel exploration."
},
{
"title": "Run a Full Omakase Evaluation",
"scenario": "Use the complete workflow for a high-impact feature.",
"prompt": "Use omakase-off for this authentication redesign. Generate variants, plan each one, test them equally, review survivors, and recommend a winner."
}
],
"output_examples": [
{
"input": "Build a todo CLI, but I am unsure whether storage should be JSON or SQLite.",
"output": "The skill captures storage as an architectural slot, creates two variants, tests both with the same scenarios, and reports a winner."
},
{
"input": "Add authentication to my app. I do not know whether sessions or tokens fit better.",
"output": "The skill proposes session and token variants, plans each path, compares scenario results, and highlights tradeoffs for selection."
},
{
"input": "Create a data import feature and pick the best implementation path.",
"output": "The skill gathers essential context, generates distinct implementation approaches, runs reviews, and documents why the selected approach won."
}
],
"best_practices": [
"Use omakase when architectural choices affect maintainability, performance, or user workflow.",
"Keep variant count capped and define the primary decision axis first.",
"Review scenario results before selecting or merging a winning variant."
],
"anti_patterns": [
"Using the workflow for trivial naming or file placement decisions.",
"Running cleanup before checking branches for uncommitted or useful work.",
"Comparing variants with different tests or acceptance criteria."
],
"faq": [
{
"question": "What does this skill do?",
"answer": "It helps explore multiple implementation approaches in parallel, then compares them with tests and review."
},
{
"question": "When should I use it?",
"answer": "Use it when a build request has important architectural choices and no obvious best path."
},
{
"question": "Does it replace brainstorming?",
"answer": "No. It can start with brainstorming, then offer parallel exploration when important uncertainty appears."
},
{
"question": "How many variants does it create?",
"answer": "The workflow caps exploration at about five or six variants to avoid unnecessary work."
},
{
"question": "Does it require other skills?",
"answer": "It references planning, worktree, testing, review, and finishing skills, with fallback behavior when they are unavailable."
},
{
"question": "What should users review before cleanup?",
"answer": "Users should check dirty worktrees, unmerged commits, and branch value before deleting losing variants."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "detailed-workflow.md",
"type": "file",
"path": "references/detailed-workflow.md",
"lines": 228
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 140
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |