メニュー
Use when an OpenCode task involves UI design, interface craft, Figma, design systems, shadcn/ui, Tailwind, Atomic Design, research synthesis, component specs, design audits, or design-to-code generation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when a task spans interface understanding, design-system memory, UI audits, design CI, Figma, shadcn or Tailwind code generation, research, or agent design workflows and needs the correct Memi capability selected.
Use when a Grok Build task involves UI design, interface understanding, Figma, design systems, shadcn/ui, Tailwind, UX audits, Atomic Design, component specs, MCP, or design-to-code generation.
Use when a Hermes session involves UI design, interface craft, Figma, design systems, shadcn/ui, Tailwind, Atomic Design, research synthesis, component specs, design audits, or code generation from design evidence.
Use when an OpenClaw workspace task involves UI design, interface craft, Figma, design systems, shadcn/ui, Tailwind, Atomic Design, research synthesis, design audits, component specs, or code generation from design evidence.
Use when reviewing or changing a React, Next.js, Tailwind, or shadcn interface and you need evidence-backed findings for accessibility, hierarchy, tokens, states, and responsive design before editing code.
Use when a coding agent must design, scaffold, implement, or verify an iOS or macOS SwiftUI interface with Apple-platform state, accessibility, availability, testing, and Xcode evidence.
| name | memoire-design-tooling |
| description | Use when an OpenCode task involves UI design, interface craft, Figma, design systems, shadcn/ui, Tailwind, Atomic Design, research synthesis, component specs, design audits, or design-to-code generation. |
Use Memi for compact, code-first interface evidence before frontend work.
npx -y @memi-design/cli@2.6.1 agent brief . --agent opencode --intent "<interface task>" --detail compact --json
npx -y @memi-design/cli@2.6.1 diagnose . --json --no-write --fail-on none
Read product instructions, components, routes, tokens, states, and research evidence before editing. Prefer existing or shadcn primitives, semantic Tailwind tokens, and explicit Atomic Design levels. Re-run the same check and report file-level evidence after the change.