Maximum-creativity design pass: take a screen, page, or app to the far edge of distinctive — committed art direction, one signature element, an adversarial judge loop — when distinctiveness is the brief, not a nice-to-have. Use when the user says 'go all out', 'push the design to its limits', 'blow me away', 'make something nobody has seen', 'design it like an award-winning studio', or asks for the most creative interface you can produce. Do NOT use for an app-wide polish sweep that keeps the product recognizably itself, a standard screen build or routine cleanup of generated UI where professional is enough, usability or WCAG audits of an existing flow, developer-facing surfaces (APIs, CLIs, docs), retention or re-engagement strategy on its own, or runtime performance work.
EnglishDelegate work to an external CLI coding agent — have Codex, Claude Code, or Cursor implement, refactor, analyze, research, or review something on its own. Triggers: 'have Codex/Claude Code/Cursor implement X', 'delegate this to a CLI agent', 'ask another agent to review my changes', 'get a second opinion from a different model', 'fan out these subtasks to parallel agents', 'Codex/cursor-agent auth or setup is failing'. Covers claude -p, codex exec/review, and cursor-agent: scope the task, pick the CLI and model (cursor-agent for cross-provider second opinions), run read-only by default, verify the output before trusting it. Do NOT use for auditing a codebase or a CLI's UX yourself, hardening a repo for coding agents, designing a new CLI/SDK, or ordinary in-session coding with no delegation or different-model signal.
EnglishAudit and prune per-session context waste — MCP servers, plugins, skills, slash commands, subagents. Triggers: 'what's eating my context', 'trim my agent setup', 'what am I not using'. Do NOT use to harden a repo's agent config or hooks, for runtime trace/eval observability, or to size prompt text.
EnglishElite polish pass: sweep a working-but-plain app until it feels built by a top-tier designer and elite PM — visual craft, subtle micro-interactions plus rationed 3D signature moments, habit-forming loops, and a usability floor, orchestrated in one pass. Use when the user says 'add polish', 'make it feel premium', 'make the experience unforgettable', 'it works but looks generic', 'elevate the whole app', or asks for creative animation and delight across the product. Do NOT use for a usability or WCAG audit of one flow, designing a brand-new screen or design system from scratch, a one-off animation on a single element, a maximum-creativity showpiece where distinctiveness is the whole brief, a retention or re-engagement strategy on its own, developer-facing surfaces (APIs, CLIs, docs), or runtime performance work.
EnglishIncludes All Out UX, CLI Delegation, Context Budget Audit, and other workflows.
Supported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
All Out UX
Maximum-creativity design pass: take a screen, page, or app to the far edge of distinctive — committed art direction, one signature element, an adversarial judge loop — when distinctiveness is the brief, not a nice-to-have. Use when the user says 'go all out', 'push the design to its limits', 'blow me away', 'make something nobody has seen', 'design it like an award-winning studio', or asks for the most creative interface you can produce. Do NOT use for an app-wide polish sweep that keeps the product recognizably itself, a standard screen build or routine cleanup of generated UI where professional is enough, usability or WCAG audits of an existing flow, developer-facing surfaces (APIs, CLIs, docs), retention or re-engagement strategy on its own, or runtime performance work.
CLI Delegation
Delegate work to an external CLI coding agent — have Codex, Claude Code, or Cursor implement, refactor, analyze, research, or review something on its own. Triggers: 'have Codex/Claude Code/Cursor implement X', 'delegate this to a CLI agent', 'ask another agent to review my changes', 'get a second opinion from a different model', 'fan out these subtasks to parallel agents', 'Codex/cursor-agent auth or setup is failing'. Covers claude -p, codex exec/review, and cursor-agent: scope the task, pick the CLI and model (cursor-agent for cross-provider second opinions), run read-only by default, verify the output before trusting it. Do NOT use for auditing a codebase or a CLI's UX yourself, hardening a repo for coding agents, designing a new CLI/SDK, or ordinary in-session coding with no delegation or different-model signal.
Context Budget Audit
Audit and prune per-session context waste — MCP servers, plugins, skills, slash commands, subagents. Triggers: 'what's eating my context', 'trim my agent setup', 'what am I not using'. Do NOT use to harden a repo's agent config or hooks, for runtime trace/eval observability, or to size prompt text.
Moonshot UX
Elite polish pass: sweep a working-but-plain app until it feels built by a top-tier designer and elite PM — visual craft, subtle micro-interactions plus rationed 3D signature moments, habit-forming loops, and a usability floor, orchestrated in one pass. Use when the user says 'add polish', 'make it feel premium', 'make the experience unforgettable', 'it works but looks generic', 'elevate the whole app', or asks for creative animation and delight across the product. Do NOT use for a usability or WCAG audit of one flow, designing a brand-new screen or design system from scratch, a one-off animation on a single element, a maximum-creativity showpiece where distinctiveness is the whole brief, a retention or re-engagement strategy on its own, developer-facing surfaces (APIs, CLIs, docs), or runtime performance work.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the All Out UX skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.