Design AI Skills

Use this skill any time the user wants to create diagrams, flowcharts, or visual structures. This includes: architecture diagrams, mind maps, org charts, user journey maps, system design diagrams, ER…

Use only when verifying or troubleshooting OCI Landing Zone Orchestrator contract/runtime behavior such as rms-facade source settings, dependency and output files, stack sequencing, duplicate…

把用户自己的照片、玩偶、头像、角色设定或品牌吉祥物接入简约漫画信息图体系时使用。用于新 IP 入驻、IP DNA 分析、把照片转成扁平手绘漫画角色、生成正面全身确认图、三视图、表情动作参考包、伴随角色规则，以及可交给其他漫画信息图技能使用的…

Fix a specific design-system integration finding in a Figma screen or component, including missing shared components, local overrides, and unbound tokens.

Expert guide for designing iOS, macOS, watchOS, tvOS, and visionOS apps following Apple Human Interface Guidelines. Use when building Apple platform apps or interfaces, implementing SF Symbols,…

프리뷰 산문(public/preview/*/preview.html — 라이트·다크 한 파일의 캡션 등 글 전체)이 services/*.md 나 상류가 뒷받침하지 않는 주장을 하는지 대조·판정할 때 쓴다. 판정 근거의 등급, 상류(Claude Design 번들 또는 브랜드 발행물) 확인 절차, 슬러그별 상류 판정표, 그 되돌리기가 남긴 판정 규칙을 담는다.…

Consulte sur le système de design d'un produit et produit `docs/DESIGN.md` + un preview HTML (spécimen typo + palette + 1 mockup d'écran). Propose un système cohérent et opinioné (aesthetic,…

Build or review native Apple interfaces, including platform controls, accessibility, state, navigation, and macOS window behavior.

Ask Gemini via local CLI and capture a reusable artifact

Scaffold, build, package, and install a custom visualization into Splunk using the dashboard-studio-extension framework. Use when the user wants to create a new custom viz, add a visualization to an…

Download and install Claude Code skills from various sources. Supports GitHub repositories, compressed archives (.zip, .tar.gz, .skill), and direct URLs. Use when user wants to download, install, or…

品牌宣传短片 —— 宣传片线方向之一：新品发布、官网展示与社交推广用的品牌宣传短片。

Use this skill when optimizing Divi 5 site performance, improving Core Web Vitals (LCP, INP, CLS), reducing render-blocking CSS, working with Divi's Critical CSS / Dynamic CSS / Inline Stylesheet…

Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI…

REST API-designmønstre, versjonering, feilhåndtering (RFC 9457) og OpenAPI-konvensjoner for Nav-tjenester

Produce visual assets from AI image and UI models through MCP — Stitch screens, Fal.ai (Imagen, FLUX, Veo), Recraft V3 vectors, GPT-Image and Figma file access — with prompt patterns and quality…

c2d2c d2c pipeline — the standard eight-step workflow for implementing or updating UI from Figma designs. Use EVERY time the user provides figma.com/design/... links asking to build, update, restyle,…

Style for edit-video: the real speaker with moving proof in footage-matched glass panels, centered captions and event-matched sound. Use for talking-head product, tool and explainer reels with real…

Convert deep research output (Claude Research, ChatGPT Deep Research, Gemini, Codex — any long-form MD/Word/text) into a consulting-quality HTML report: pyramid structure, numbers promoted to…

DesignCraft is the ArtCraft team's clean-room, open-source InDesign-class page-layout app (pure Rust; `.designcraft` project format; IDML/INDD/INDT import; PDF/X-4 and PDF/X-1a export, PDF/A-2b, EPUB…

Your AI Founder Partner for building and scaling startups — diagnose your stage, run hypothesis experiments, make pricing decisions, design growth loops, and ship weekly execution reviews.

Create and manage local Issue specs (specs/issues/) - individual work items with testable acceptance criteria. Use for "create issue", "new task", "list issues", "check issues", "pick issue". NOTE -…

Escalate critical decisions to a human with options, tradeoffs, and recommendation. TRIGGER when: major safety risk, high irreversible impact, large GPU spend, destructive data ops, shared-memory…

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,…

Run Phase Optimize — humanize, meta build, schema, internal link, GEO optimize, visual design, CTA module + deterministic lint gates (render / density / keyword / PAA alignment / locale spelling /…

Generate a high-density A4 cheat sheet for open-book exams. Two output paths: LaTeX (XeLaTeX) or self-contained HTML with CSS print layout. Both paths produce visually consistent results.

Enforces the Array UI (array-ui) editorial systems design system for any frontend, UI, website, blog, personal site, SaaS dashboard, or documentation development task. Trigger on "ape design", "Array…

Render UI wireframes as labeled ASCII art where every region maps to a real component in YOUR design system. Use when someone asks for an ASCII prototype, a text wireframe, a monospace mockup, or…

Models Kotlin logical failures with Arrow's context-parameter Raise DSL and wrappers such as Either, nullable, Option, and Ior. Use when implementing or simplifying typed-error flows, translating…

Turn a brief, approved moodboard, or existing scene image into a structured scene-art direction contract, model-ready environment prompts, reference upload rules, multi-view continuity notes, and…

Still-image generation guide for SpriteCook. Use with spritecook-workflow-essentials when generating pixel art or detailed/HD assets, choosing models, and keeping style consistency with reference…

Build lightweight mood boards, visual territories, creative directions, style boards, reference boards, art-direction boards, campaign mood explorations, brand look-and-feel explorations, image…

Audit a live website's or local page's scroll experience and return a scored remediation plan. Use for an audit, review, score or benchmark request about scroll performance, parallax, pinned sections,…

Use when the user says 'extract my brand voice', 'what is my writing style', or 'analyze my tone', or before any skill that writes copy for the site. Reads 5-10 published posts and persists tone,…

Add your own ManyChat to your white-label social media app on the Zernio API: comment-to-DM with buttons, follower-only rewards with a one-tap confirm, story-mention replies, ref links and QR codes…

基于 BJ Fogg《福格行为模型 / Tiny Habits》的对话式习惯教练。用 B=MAP（行为=动机×能力×提示）和福格的行为设计流程，帮用户：(1) 诊断某个习惯为什么没坚持下来、怎么改善；(2) 从愿望出发设计新习惯（行为群→焦点地图→微行为→锚点→庆祝）；(3) 戒除坏习惯；(4) 设计庆祝/情绪以让习惯扎根；(5)…

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…

UI craft: build, redesign, or visually review an interface and its design system. Not for backend or other non-visual work.

为微信公众号文章排版并生成可在浏览器打开的本地实时预览页，支持固定右侧设置栏、5 套原创主题、联动换色、13 类丰富组件替换、字体与图片形式、字号字重和段落/标题/图片间距调整，可把 DIY 设置保存为当前浏览器的自定义风格，并复制富文本到公众号；也用于用户提供排版截图或公众号文章链接，要求分析、模仿、学习排版风格并沉淀到风格库。只写文章内容时应使用写作 Skill；只发布现成内容时应使用发布…

Use when applying a brand kit / brand style to an existing CoDesign / CE.SDK design — a rules-governed restyle (recolor + refont + logo + treatment by role), not a free-form style change; when a…

Apply product-grounded visual quality constraints during user-visible UI changes. Use for layout, styling, content hierarchy, theming, responsive behavior, or interaction affordances. Stay inactive…

把已有复杂分析组织成帮助人理解、判断和回应的顾问式交互 HTML 汇报。用于用户调用 `$brief-me`、要求就复杂问题做汇报，或希望通过图形和交互比较方案、审阅判断时；普通摘要、纯状态看板和没有判断任务的归档不适用。

Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or…

Convert any PDF or PPTX deck into a self-contained interactive HTML deck, one file, one link, shareable. Auto-detects input file extension (.pdf or .pptx) and routes to the matching extraction path.…

How to draw hands in drawn-by-code, in any style. Use it before drawing, redrawing or reviewing any hand, and whenever a character holds, grips, carries, throws, touches or points at something, or the…

Turns any request for an AI-generated image into precise, generation-ready prompt specs and — when the FAL.ai automation is configured — the generated files themselves, using the single model…

Use when deciding HOW an Apple-style interface should BEHAVE — the functional UX/interaction logic, not the looks. Navigation-model decisions (push vs sheet vs modal vs tab vs popover vs split-view vs…

用国际顶级咨询公司（McKinsey / BCG / Bain / Deloitte / IBM）的汇报风格，把一段文字/报告/文章提炼成 16:9 高清 HTML 演示页（1920×1080，纯白 + Flat Design）。四类页面各有专属做法——有数值出 ECharts 真实图表、软件/IT 系统方案出 SVG 架构图、有通用结构关系出 SVG 模型、只有并列类目用「线 +…

McKinsey/BCG-tier strategy decks. Dense, structured, signal-color callouts on neutral grounds. Use when the user asks for 'strategy', 'consulting', 'case', 'recommendation', 'McKinsey-style',…

Web quality skills from Google Chrome's Addy Osmani: a measurement-first web quality audit (Lighthouse-style), accessibility (WCAG 2.2), Core Web Vitals (LCP/INP/CLS), performance, SEO, and…

Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI…