Use when about to ask the user to choose between 2+ substantive implementation approaches — architecture, algorithm, data structure, library, or design pattern choices where the answer benefits from a side-by-side comparison of real implementations — OR when undecided between competing hypotheses, interpretations of an ambiguous request, or research directions where pursuing each branch would settle which is right. Symptoms include drafting a message like "Option A or Option B — which do you prefer?", listing trade-offs in the abstract, recommending a path while uncertain whether an alternative would be cleaner, or picking the likelier of two explanations and moving on. Do NOT use for trivial choices (variable names, formatting, single-line refactors, choices the user already specified). For non-code forks (competing explanations, interpretations, research directions), the comparison happens via investigation rather than worktrees — see dig.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryScience & researchStars0
About this skill
Use when about to ask the user to choose between 2+ substantive implementation approaches — architecture, algorithm, data structure, library, or design pattern choices where the answer benefits from a side-by-side comparison of real implementations — OR when undecided between competing hypotheses, interpretations of an ambiguous request, or research directions where pursuing each branch would settle which is right. Symptoms include drafting a message like "Option A or Option B — which do you prefer?", listing trade-offs in the abstract, recommending a path while uncertain whether an alternative would be cleaner, or picking the likelier of two explanations and moving on. Do NOT use for trivial choices (variable names, formatting, single-line refactors, choices the user already specified). For non-code forks (competing explanations, interpretations, research directions), the comparison happens via investigation rather than worktrees — see dig.
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.
Use when about to ask the user to choose between 2+ substantive implementation approaches — architecture, algorithm, data structure, library, or design pattern choices where the answer benefits from a side-by-side comparison of real implementations — OR when undecided between competing hypotheses, interpretations of an ambiguous request, or research directions where pursuing each branch would settle which is right. Symptoms include drafting a message like "Option A or Option B — which do you prefer?", listing trade-offs in the abstract, recommending a path while uncertain whether an alternative would be cleaner, or picking the likelier of two explanations and moving on. Do NOT use for trivial choices (variable names, formatting, single-line refactors, choices the user already specified). For non-code forks (competing explanations, interpretations, research directions), the comparison happens via investigation rather than worktrees — see `dig`.
About this listing
Category
Science & research
Reported license
Not specified
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