Design & UX

Professional home organizer specializing in decluttering, space optimization, storage systems, and sustainable organization solutions. Triggers: 'home organizer', 'declutter', 'organize home', 'space optimization', 'professional organizing'

Figma专家：组件设计、Auto Layout、设计系统、Dev Mode、交互原型。Use when designing UI, creating design systems, prototyping interactions, or handing off to developers

Single-agent quick mock UI — render a screen or two as static HTML/CSS for fast visual feedback. UI only, no backend or DB.

Expert animator with 12+ years in 2D/3D animation, motion graphics, and visual effects for film, TV, and digital media. Specializes in character animation, timing and spacing, squash and stretch, and production workflows. Use when: animation, motion-graphics, visual-effects, 2d-animation, 3d-animation.

AI视效总监，专精用Seedance 2.0实现电影级视觉效果，包括环境构建、特效场景、幻想世界、灾难场景、超能力视觉化。掌握背景板技术、多模态参考合成和视效分层生产。Use when: 视觉特效, VFX, 特效场景, 环境构建, 幻想场景, Seedance视效.

AI音效设计师，专精利用Seedance 2.0的原生音频生成能力设计声音方案。涵盖音效Prompt语法、BGM情绪指导、对白音频输入策略、声画同步设计和音效分层工作流。Use when: 音效设计, 声音设计, BGM, 音频同步, native audio, Seedance音频.

AI美术指导/场景设计师，专精为Seedance 2.0构建可复用的场景世界观系统。涵盖背景板预制、场景美术设计、道具视觉规范、空间层次构建和跨镜头场景一致性管理。Use when: 美术指导, 场景设计, 背景板, production design, 世界观, 场景一致性.

AI MV导演，专精使用Seedance 2.0制作音乐视频。深度整合音频同步技术、歌词视觉化、表演拍摄和概念视觉叙事。擅长节奏匹配剪辑点设计、艺人形象管理和多风格MV制作。Use when: 音乐视频, MV制作, 艺人内容, 歌词视觉化, lip-sync, 音频同步.

AI游戏过场动画/宣传片导演，专精用Seedance 2.0制作游戏相关视频内容。涵盖游戏宣传片、英雄展示动画、过场动画CG、游戏玩法展示和电竞赛事内容制作。Use when: 游戏宣传片, 游戏CG, 英雄展示, game trailer, cinematic cutscene, 电竞内容.

AI广告导演，专精使用Seedance 2.0制作品牌商业内容。擅长品牌视觉语言设计、产品展示、人物代言、多版本广告生产和跨平台素材复用。Use when: 商业广告, 品牌内容, 产品视频, TVC, 广告片, Seedance商业制作.

AI漫改导演，专精将漫画/插画/小说IP用Seedance 2.0转化为动态视频内容。涵盖漫画面板到视频镜头的转译、原著视觉风格保留、IP角色迁移策略、文字/图像并行叙事和漫改短剧全流程。Use when: 漫改, 漫画改编, IP改编, comic adaptation, 插画动态化, 图文转视频.

AI摄影指导（DP），将专业电影摄影美学转化为Seedance 2.0可执行的镜头Prompt。专精摄影机运动语言、光线氛围设计、画面构图和色彩风格定义。Use when: 摄影指导, 摄影风格, 镜头设计, 布光方案, 画面美学, Seedance cinematography.

AI动画导演，专精用Seedance 2.0制作二维/水墨/日漫/美漫/3D风格动画内容。涵盖动画风格参考体系、运动感设计、动漫角色参考策略、动画叙事节奏和多集动漫制作工作流。Use when: 动画制作, 动漫, anime, 二维动画, 水墨动画, 国风动画, Seedance动画.

Analyze a video file (mov, mp4, webm, etc.) or a YouTube video by extracting still frames with ffmpeg and reading them chronologically with vision — Claude cannot ingest video files directly. Use whenever the user provides a video file path or YouTube URL and wants to know what happens in it: \"read this video\", \"watch this video\", \"check this recording\", \"what happens in this .mov/.mp4\", analyzing a screen recording of a UI bug, or verifying UI behavior captured in a video, even if th...

Edit and create KiCad schematic (.kicad_sch) files. Use when user says 'edit schematic', 'modify kicad', 'add component', 'change resistor value', 'update schematic'. Capabilities: (1) Modify schematics (change values, add/remove components, update connections), (2) Create new schematic content from specs or ASCII diagrams, (3) Analyze structure. KiCad 6+ S-expression format. Generated schematics may need GUI layout adjustment.

Read the currently selected Figma element and work with it. Use when: (1) User says 'figrefer', 'figma refer', 'check my figma selection', (2) User wants to implement or analyze a design selected in Figma desktop app, (3) User says 'what am I selecting in figma', 'implement this figma design'

Read a Figma design node directly from a share URL via the Figma REST API — no Dev Mode subscription, no MCP, no desktop app. Renders the node to PNG and dumps its full style/layout JSON so the design can be described, compared, or implemented. Use whenever the user gives a Figma design URL (figma.com/design/... or /file/...) and wants to see, read, inspect, reference, or implement that node — including `/fig-url-refer <url>`. This is the URL-based counterpart to `/figrefer` (which needs a De...

Provide Figma capture script installation guidance for web projects. Use when: (1) User wants to set up Figma capture in a web dev project, (2) User says 'figma script install', 'add figma capture', 'figma setup', (3) User wants to enable browser-to-Figma capture in their dev environment

Iterative visual design-polish loop for an existing or WIP web UI. Each round: capture the live page as screenshots, judge it from the rendered pixels, and apply CSS polish toward a better-looking target using /css-wisdom's tight-token strategy — then re-capture and compare. The target direction is set by codex-imagegen 'north-star' mockups generated from the current screenshot, so the loop pursues a genuinely better look instead of nudging the existing one in place. Use when: (1) user says '...

Generate or redesign raster images (PNG mockups, illustrations, photos, UI design polish) from inside Claude Code by driving Codex CLI's built-in $imagegen, billed to ChatGPT-included usage instead of per-image OpenAI API charges. Use whenever the user wants to create/generate an image, make a mockup or illustration, produce a photo, polish or redesign a UI from a screenshot, or get a PNG out of a session — even if they don't mention Codex or \"imagegen\". This is the preferred image-generati...

--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'refero-design-research-skill' description: 'Research-first UI design skill for using Refero MCP to study real app screens and flows before making product design decisions.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---

--> --- name: bio-reporting-figure-export description: Exports publication-ready figures in various formats with proper resolution, sizing, and typography. Use when preparing figures for journal submission, creating vector graphics for presentations, or ensuring consistent figure styling across analyses. tool_type: mixed primary_tool: matplotlib measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: nano-banana description: AI-powered reasoning image engine for generating and editing high-quality biomedical infographics and realistic images. license: Proprietary (Google) metadata: author: Google version: "Pro" compatibility: - system: Web Interface / API allowed-tools: - web_fetch measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. --- Nano Banana is a cutting-edge AI tool serving as a "reasoning image engine." It is particularly pow...

--> --- name: bio-immunoinformatics-epitope-prediction description: Predict B-cell and T-cell epitopes using BepiPred, IEDB tools, and structure-based methods for vaccine and antibody design. Identify immunogenic regions in antigens. Use when designing vaccines, mapping antibody binding sites, or predicting immunogenic peptides. tool_type: python primary_tool: BepiPred measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run...