设计

UI/UX 方向、视觉设计与设计系统

显示 2377-2400 / 共 4598 个技能
malcolm1232

clean-slate

malcolm1232

Full board-steward teardown for a fresh-user / first-run test. Use when the user wants to wipe ALL board-steward state — kill the board server(s) and ports, remove autostart, purge ~/.board-steward (port registry + .onboarded marker), delete board.json(s), and uninstall the plugin — so a later reinstall starts truly clean and the first-run picker/popup fires. Triggers: "clean slate", "wipe the board", "kill all boards/ports", "fresh user test", "reset board-steward", "tear it all down so reinstall is clean".

CLI 工具 14 4个月前
cuioss

manage-terminal-title

cuioss

Pure platform-agnostic terminal-title composition consumed by platform-runtime via PYTHONPATH — plan-scoped pm:{phase} bodies and orchestrator Orchestrator-{SlugName} bodies

CLI 工具 5 2个月前
arisng

blazor-blueprint-ui

arisng

Comprehensive Blazor component library based on shadcn/ui design with 88 components (15 headless Primitives, 73 pre-styled Components), 1,640+ Lucide icons, and chart library. Use when building Blazor web applications that need UI components like forms (buttons, inputs, date pickers, tables), navigation (tabs, menus, sidebars), overlays (dialogs, sheets, tooltips, popovers), displays (avatars, badges, alerts, skeletons), charts (bar, line, area, pie, radar, radial), or when working with shadcn/ui-style Blazor components. Supports both controlled/uncontrolled state patterns, composition-based component structure, and dark mode.

分析 5 8个月前
futuregerald

ui-design

futuregerald

Practical UI design principles for developers and non-designers. Use when creating web interfaces, components, dashboards, landing pages, or any visual design work. Covers hierarchy, spacing, typography, color, depth, and polish. Based on Refactoring UI methodology.

代码生成 5 8个月前
fellipeutaka

design-patterns

fellipeutaka

Apply Gang of Four design patterns to solve architectural problems in TypeScript. Use when refactoring code architecture, implementing extensible systems, decoupling components, or following SOLID principles. Covers all 22 GoF patterns: Creational (Factory Method, Abstract Factory, Builder, Prototype, Singleton), Structural (Adapter, Bridge, Composite, Decorator, Facade, Flyweight, Proxy), and Behavioral (Chain of Responsibility, Command, Iterator, Mediator, Memento, Observer, State, Strategy, Template Method, Visitor).

代码生成 5 8个月前
futuregerald

design-principles

futuregerald

Enforce a precise, minimal design system inspired by Linear, Notion, and Stripe. Use this skill when building dashboards, admin interfaces, or any UI that needs Jony Ive-level precision - clean, modern, minimalist with taste. Every pixel matters.

数据处理 5 8个月前
parsoFish

reflector

parsoFish

Run a deep structured retrospective at the end of a merged initiative — repeated actions, roadblocks hit, and operator notes (agentic self-reflection + agent-prompted user questions + pure user feedback) — and write the findings into the central forge-owned brain.

代码评审 5 29天前
aganesy

qfai-grilling

aganesy

"Interrogate an unfixed design in rounds: a tree of open decisions, a frontier of the ones answerable now, facts read rather than asked, and an end condition the user holds. Use when a stage calls for a grilling session, or when asked to grill or stress-test a design."

设计 4 17天前
RatioArtificiosa

geo-audit

RatioArtificiosa

Use when asked whether a brand is visible in AI answers, why it is or is not cited, or which pages to fix first. Audits AI visibility across ChatGPT and Google AI Overviews, checks whether retrieved pages are actually cited, and ranks fixes by impact. Triggers on "is my brand in AI", "AI visibility", "GEO audit", "why doesn't ChatGPT recommend me", "am I cited by AI", "AI citations", "is my site in AI answers".

设计 1 24天前
KentoShimizu

design-system-foundations

KentoShimizu

"Define scalable design-system foundations with clear ownership and adoption boundaries. Use when multiple teams need shared component standards, foundational patterns, and ownership rules to deliver consistent UI across products; do not use for backend data-model or deployment pipeline decisions."

代码生成 8 8个月前
SyFI-ServingStudio

orchestrator-add-kernel-to-python-profile

SyFI-ServingStudio

Use when owning the Python-side ServingStudio Sim L1 profiling work for a new kernel kind or a new backend of an existing kind, either as the coordinator who writes implementer briefs or as the agent a whole kernel was handed to. Defines the steps, their completion checks, and the order of Torch reference work before framework backends. It does not cover Rust timing/cache wiring.

设计 1 12天前
ahmadzayan-hub

rta-style

ahmadzayan-hub

The user's house style for agent outputs, taken from their own executive-dashboard work: a red brand bar, navy and grey charts, tiles with a coloured leading edge, system fonts with Arabic support, light and dark. Colours, type and layout only, never a logo, name or data of any organisation. Use when a dashboard, evaluation report, clip, page or Claude Dashboard should look like the user's RTA-style work, or when the user asks for "RTA style".

设计 0 7天前
SyFI-ServingStudio

top-add-new-arch

SyFI-ServingStudio

Use as the top entry point when the user wants to add a whole new model architecture to ServingStudio Sim end to end — explore it, split its forward into kernels, categorize every element into L1/L2/L3/L4, build the kernels, ops, worklets, and model_arch, then add an independent model.work necessary-work label. The one criterion running through the timing layers is the timing-prediction wiring — where each element's timing comes from: L1 is the only layer that MEASURES a number (profile.db); L2/L3/L4 only COMPOSE measured L1 timings. Adding an arch is paired with alignment: capture a real vLLM/SGLang run first and let the measured kernel inventory — not source-reading guesswork — decide which kernels to add, largest first. Skipping the capture requires the user's explicit confirmation. This is a routing/sequencing skill; it delegates each phase to a lower skill and does not implement leaves itself. Landing the finished model on main is dev-finalize-model-addition.

设计 1 10天前
kesslerio

frontend-design-ultimate

kesslerio

Create distinctive, production-grade static sites with React, Tailwind CSS, and shadcn/ui — no mockups needed. Generates bold, memorable designs from plain text requirements with anti-AI-slop aesthetics, mobile-first responsive patterns, and single-file bundling. Use when building landing pages, marketing sites, portfolios, dashboards, or any static web UI. Supports both Vite (pure static) and Next.js (Vercel deploy) workflows.

动画 10 8个月前
smallnest

brand-guidelines

smallnest

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

设计 189 10个月前
smallnest

frontend-design

smallnest

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

动画 189 10个月前
smallnest

request-analyzer

smallnest

Proactively analyze user requests at the start of conversations to determine task type, assess prompt quality, and intelligently recommend which skills to activate. Should activate for ALL user requests to ensure optimal workflow. Evaluates clarity, specificity, and completeness to suggest prompt-optimizer when needed. Identifies UI design tasks for ui-analyzer and component requests for react-component-generator. Acts as intelligent skill coordinator.

自动化 189 10个月前
Russell-cell

ppt-as-code

Russell-cell

Build HTML-based web presentations with a creator-first workflow: keep quick mode lightweight, use basic mode for confirmed deck planning plus script plus image flow, and use advanced mode for reference-driven decks, static-first delivery, optional motion follow-up, optional PPTX export handoff, optional source-material normalization, visualization planning for charts and diagrams, an optional workbench architecture for visual editing, and safe fallbacks when file persistence or web search is unavailable. Also supports an optional Slidev-inspired deck.md draft input layer.

设计 188 6个月前
SyFI-ServingStudio

impl-compose-arch

SyFI-ServingStudio

Use when implementing an L4 model_arch under simulator/src/arch/ after its L3 worklets build — the full-model wire file for one worker type that forwards ModelCfg into worklet configs, compiles the per-iter CostTree once, and exposes IterwiseUnifiedModel. Covers the live code contract: build_configs/resolve_configs/ build + cost_tree/eval_iter + the Scale{n} layer fold + the config.rs selector. Follows the code, not design.md's retired dry_run/JitPlan/Describe. NOT for L3 worklets (impl-compose-worklet).

设计 1 12天前
smallnest

ui-analyzer

smallnest

Analyze UI design screenshots and generate React components with TypeScript and Tailwind CSS. Use this skill when the user provides UI mockups, design screenshots, or Figma exports and requests implementation. Provides detailed layout analysis, component breakdown, design token extraction, and production-ready code generation following best practices.

代码生成 189 10个月前
Gayaya999

ecommerce-detail-page-generator

Gayaya999

Turn product photos and a minimal brief into verified, platform-adapted e-commerce detail-page systems, including product fact review, visual analysis, localized copy, 6-10 module story planning, policy-aware text-free image generation or real-photo routing, deterministic Pillow typography, platform-sized slices, long-page previews, manifests, and automated validation. Supports 淘宝/天猫/京东/拼多多/抖音/小红书/Amazon/AliExpress/Temu/TikTok Shop/eBay/Etsy/Shopify. Use when a user asks for 电商详情页, 商品详情图, 商详设计, A+ content, listing galleries, or a short-input workflow that turns product photos into ready-to-review commerce assets without inventing unsupported claims.

设计 41 4个月前
mightyhuman101

seedance-prompt-en

mightyhuman101

Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.

设计 7 8个月前
Eli-yu-first

Responsive Breakpoint Advisor

Eli-yu-first

"Advises on responsive design breakpoints based on analytics data and device usage patterns"

设计 7 7个月前
SlashieApp

ui-component-from-image

SlashieApp

Builds a new reusable Chakra UI primitive under src/ui from a reference image (layout, typography, color), verifies light and dark themes with semantic tokens, and adds a colocated Storybook story. Use when the user attaches or links a design image for a new generic component, asks to match a mockup in src/ui, or wants a Card-style shared UI building block from a screenshot.

设计 0 6个月前