A structured product-judgment engine for deciding what NOT to build — faster. Applies the "spreadsheet test" (discipline problem in a tooling costume, or genuinely needs heavy machinery?), 80/20 structural analysis, figure/ground reading, and an adversarial evidence loop ending in the cheapest disconfirming test. Use whenever a user asks whether to build something, evaluates a feature/product/tool idea, asks "should we buy a tool or fix our process," brings a roadmap or backlog to prioritize, asks how to solve a product-team or CPO-level problem, proposes an AI initiative, or wants a verdict on where to invest effort. Also trigger on "is this worth building," "what should we cut," "help me prioritize," "do we need a tool for this," "evaluate this idea," or any request to assess an identified product opportunity. Trigger even when the user just describes a business problem and asks for a solution — the first move is always classifying the problem before solving it.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryProduct & designStars0
About this skill
A structured product-judgment engine for deciding what NOT to build — faster. Applies the "spreadsheet test" (discipline problem in a tooling costume, or genuinely needs heavy machinery?), 80/20 structural analysis, figure/ground reading, and an adversarial evidence loop ending in the cheapest disconfirming test. Use whenever a user asks whether to build something, evaluates a feature/product/tool idea, asks "should we buy a tool or fix our process," brings a roadmap or backlog to prioritize, asks how to solve a product-team or CPO-level problem, proposes an AI initiative, or wants a verdict on where to invest effort. Also trigger on "is this worth building," "what should we cut," "help me prioritize," "do we need a tool for this," "evaluate this idea," or any request to assess an identified product opportunity. Trigger even when the user just describes a business problem and asks for a solution — the first move is always classifying the problem before solving it.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
A structured product-judgment engine for deciding what NOT to build — faster. Applies the "spreadsheet test" (discipline problem in a tooling costume, or genuinely needs heavy machinery?), 80/20 structural analysis, figure/ground reading, and an adversarial evidence loop ending in the cheapest disconfirming test. Use whenever a user asks whether to build something, evaluates a feature/product/tool idea, asks "should we buy a tool or fix our process," brings a roadmap or backlog to prioritize, asks how to solve a product-team or CPO-level problem, proposes an AI initiative, or wants a verdict on where to invest effort. Also trigger on "is this worth building," "what should we cut," "help me prioritize," "do we need a tool for this," "evaluate this idea," or any request to assess an identified product opportunity. Trigger even when the user just describes a business problem and asks for a solution — the first move is always classifying the problem before solving it.
About this listing
Category
Product & design
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI