디자인 스킬

Orchestrate IA shard authoring via design and deepen passes, with pipeline-state-driven shard selection and ambiguity gates

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Draft IA shard sections from reconciled ideation and architecture sources, with write-as-you-go section locking

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design database schemas with normalization, relationships, and constraints. Use when creating new database schemas, designing tables, or planning data models for any database paradigm.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design direction interview methodology — SUPERSEDED. The `impeccable` skill's `/impeccable teach` command now handles design direction discovery with a more comprehensive, multi-round interview that writes PRODUCT.md and DESIGN.md. This file is kept for pipeline backward compatibility — all new design work should use `/impeccable teach` instead.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Compile architecture draft into dated architecture design and engineering standards with rubric-complete quality gates

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Apply the confirmed design direction to all visual surfaces. This skill now bridges the pipeline's placeholder system with the `impeccable` skill's PRODUCT.md and DESIGN.md files. If `{{DESIGN_DIRECTION}}` still appears as a literal placeholder, run `/impeccable teach` to establish design context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Universal AI design correction rules — SUPERSEDED. The `impeccable` skill now provides 27 deterministic anti-pattern rules plus a 12-rule LLM critique pass, which are more comprehensive and runtime-enforced via the `impeccable` CLI. This file is kept for backward compatibility — the `impeccable` skill's design laws and anti-patterns take precedence.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Decompose approved architecture design into IA shards and layered spec structure, then validate dependencies and tracking outputs

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Per-screen design spec generator for AI design tools (Stitch / Figma AI / Claude artifacts). Consumes per-feature PRDs from kta-prd-pipeline. Emits tool-agnostic markdown specs. Triggers — design spec, AI design prompt, screen mockup brief, Figma AI input, Stitch prompt, design system tokens, post-PRD design phase, generate design specs, design brief, mockup spec. DOES NOT generate Compose code, Kotlin code, or @Preview stubs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create Kotlin Compose design tokens from one of three supported sources — Google Stitch (MCP), Figma (MCP or JSON), or Claude Design (kta-design-spec output, Claude HTML/markdown artifacts). Three-layer architecture (Primitive/Semantic/Component) with code generation. Use when user asks to "generate design tokens", "create theme from Figma/Stitch/Claude design", "build Compose tokens from design spec", or "convert design source to tokens". Refuses any other input source and asks user for correct seed data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Per-screen design spec generator for AI design tools (Stitch / Figma AI / Codex artifacts). Consumes per-feature PRDs from kta-prd-pipeline. Emits tool-agnostic markdown specs. Triggers — design spec, AI design prompt, screen mockup brief, Figma AI input, Stitch prompt, design system tokens, post-PRD design phase, generate design specs, design brief, mockup spec. DOES NOT generate Compose code, Kotlin code, or @Preview stubs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create Kotlin Compose design tokens from one of three supported sources — Google Stitch (MCP), Figma (MCP or JSON), or Codex Design (kta-design-spec output, Codex HTML/markdown artifacts). Three-layer architecture (Primitive/Semantic/Component) with code generation. Use when user asks to "generate design tokens", "create theme from Figma/Stitch/Codex design", "build Compose tokens from design spec", or "convert design source to tokens". Refuses any other input source and asks user for correct seed data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Optimize a single Jetpack Compose @Composable function. Use when the user wants to improve, polish, animate, or refactor ONE Composable — keywords like "optimize this composable", "make this smoother", "add animation to this", "split this composable", "fix recomposition", "this composable is laggy", "polish this UI", or when user pastes/points to a single @Composable function. Analyzes the target for recomposition issues, missing animations, size/concern splits, and stability problems, then iterates with the user via AskUserQuestion to pick which optimizations to apply, then delegates implementation to the kta-compose-developer agent and summarizes changes. Input MUST be exactly one Composable (file path + function name, or function name alone).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

End-to-end Android indie idea workflow — feature-build phase only (no monetization). Phased — discover (if no idea) → generate 2 candidates → refine scope (offline/online, sharing, MVP vs full, core-value features) → risk/reward/tradeoff analysis when scoping down → emit idea brief. Use for greenfield app concepts, new feature ideation, idea discovery, or pre-design discovery before writing a design document. Triggers — new app idea, feature concept, indie dev brainstorm, validate idea, refine idea, what should I build, find an app idea, idea pipeline, I have no idea, help me find an app idea, scope down, MVP scoping, core value features.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when creating, modifying, or debugging Ionic Vue components, pages, forms, dialogs, or theme/safe-area UI behavior.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when working on login, logout, session restore, tokens, route guards, or any authentication and authorization behavior.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use Kanpeki component library in React projects. Activate when user wants to add, use, customize, or compose accessible UI components from Kanpeki (@kanpeki/*). Covers installation, component patterns, forms, theming, and dark mode with React Aria Components + Tailwind CSS 4.1 + CVA.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill is for interface design — dashboards, admin panels, apps, tools, and interactive products. NOT for marketing design (landing pages, marketing sites, campaigns).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build React animations with Motion (Framer Motion) - gestures (drag, hover, tap), scroll effects, spring physics, layout animations, SVG. Bundle: 2.3 KB (mini) to 34 KB (full). Use when: drag-and-drop, scroll animations, modals, carousels, parallax. Troubleshoot: AnimatePresence exit, list performance, Tailwind conflicts, Next.js "use client".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Apply SOLID principles to write flexible, maintainable, and testable code. Use when designing classes, interfaces, and module boundaries. Covers Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion with practical TypeScript examples and detection heuristics.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.