[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71EPX5FAG18BPP7VJQ29SZN":3,"skill-same:01M71EPX5FAG18BPP7VJQ29SZN":123},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M71EPX5FAG18BPP7VJQ29SZN","frontend-slides",null,"Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use for solution decks, presales\u002Fsales pitches, client proposals, pitch decks, teaching tutorials, conference talks, and internal presentations. Ideal for sales and presales teams. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.","ViewWay\u002Fhermes-by-everythings","ViewWay","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F57283862?v=4","01M71ENR60K309MXA64A23SEW5","01M71ENR6QYM7NQHP29W53HSXT",3,"MIT","https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"slides","frontend slides","frontend","use","aesthetic","teams","scratch","for","proposals","rich","html","powerpoint","presentations","create","teaching","pitch","files","discover","exploration","Animation","2026-11-10 10:12:30",false,"---\nname: frontend-slides\ndescription: Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use for solution decks, presales\u002Fsales pitches, client proposals, pitch decks, teaching tutorials, conference talks, and internal presentations. Ideal for sales and presales teams. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.\n---\n\n# Frontend Slides Skill\n\nCreate zero-dependency, animation-rich HTML presentations that run entirely in the browser. This skill helps non-designers discover their preferred aesthetic through visual exploration (\"show, don't tell\"), then generates production-quality slide decks.\n\n**Reference files:** When generating CSS, image processing, PPT extraction, HTML structure, edit button, or animation code, read the corresponding file under `reference\u002F` (and STYLE_PRESETS.md for presets and CSS Gotchas) so output is correct and complete.\n\n---\n\n## 🧠 Core Design Philosophy\n\n### 1. Visual Style & Material\n\n**Principle**: Form follows function. All visual decisions (color, layout, material) must serve the user's mental model and business goals.\n\n| Style Position | Use Cases | Core Characteristics |\n|---|---|---|\n| **Future & Depth** | Frontier exploration, tech product launches | Frosted glass + dark mode, halos and transparency for layering |\n| **Efficiency & Speed** | Professional tools, data dashboards | Clean flat style + Bento UI, clear boundaries, modular |\n| **Trust & Professional** | Finance, formal presentations, enterprise solutions | Swiss minimalism, generous whitespace, relies on typography and strict grids |\n| **Care & Resonance** | Humanities, lifestyle, brand stories | Low-saturation natural colors + extreme rounding, ultra-soft diffuse shadows |\n| **Immersion & Expression** | Entertainment, narrative, creative showcases | Skeuomorphic materials + high-contrast emotional colors, breaks conventional grids |\n\n**Style Selection Rules:**\n- Solution deck \u002F presales proposal → Trust & Professional (Swiss Modern) or Efficiency & Speed (Bento UI)\n- Product launch \u002F tech showcase → Future & Depth (Dark Botanical \u002F Electric Studio)\n- Brand story \u002F humanities content → Care & Resonance (Pastel Geometry \u002F Vintage Editorial)\n- Creative proposal \u002F marketing campaign → Immersion & Expression (Neon Cyber \u002F Creative Voltage)\n\n### 2. Spatial & Typography Organization\n\n- **Density Hierarchy**: Density is inversely proportional to importance. Core focus areas need low density \u002F large margins. Data lists need high density \u002F small margins.\n- **Typography System**:\n  - Prefer modern sans-serif fonts (Clash Display, Satoshi, DM Sans)\n  - Establish significant **weight** and **size** contrast between headings and body\n  - Body line-height: `leading-[1.5]` or `leading-[1.6]` for visual breathability\n- **Font Size Constraints**:\n  - Minimum readable size: `12px` (annotations only)\n  - Standard body: `14px\u002F16px`\n  - Headings use `clamp()` for responsive scaling\n\n### 3. Affordance & Resilience\n\nAlthough the output is static HTML, when handling multiple similar components (lists, navigation, card groups), **you must hardcode and render different interaction states within the same container** to exhaustively show the component's full lifecycle.\n\n- **⚠️ Warning**: Do not rely solely on Tailwind's `hover:` pseudo-class for interactions. You must directly change the base class of specific items to make states **simultaneously visible** in static screenshots!\n- **Example**: In a card group, first card uses default state, second card uses `bg-white\u002F10` to simulate hover state, third card uses `border-cyan-400` to simulate selected state\n\n### 4. System Integrity Constraints\n\n**All design decisions must map to the following limited variable set (no odd numbers, decimals, or random values allowed):**\n\n| System | Constraints |\n|---|---|\n| **Color System** | Primary color defines brand; **complementary color** for strong guidance; **analogous colors** for soft guidance. No arbitrary colors |\n| **Spatial Spacing (8-Point Grid)** | Spacing and padding limited to: `8` \u002F `12` \u002F `16` \u002F `20` \u002F `24` \u002F `32` \u002F `40` (strictly apply to gap and padding) |\n| **Corner Radius** | Choose based on style, default starts at `rounded-[12px]`. Care style can use `rounded-[24px]` or `rounded-full` |\n| **Size Minimums** | Minimum click hotspot `44px`; minimum readable size `12px`; standard body `14px\u002F16px` |\n| **Shadow Control** | Must use diffuse lighting like `shadow-[0_10px_30px_rgba(0,0,0,0.08)]`, no harsh shadows |\n\n---\n\n### 5. 🌀 Emerging Design Trends 2026\n\nIntegrate the following four trends organically into presentation design. Select 1-2 dominant trends based on content theme.\n\n#### Trend 1: Ghostly Agency\n**Core**: Agentic UX — The interface acts like a translucent butler, preparing everything before the user asks\n\n| Design Strategy | Implementation | Use Cases |\n|---|---|---|\n| **Predictive Presence** | Progressive content reveal (`.reveal` animations trigger in stages) | AI products, automation services, intelligent assistants |\n| **Invisible Butler** | Translucent elements + subtle floating animations (`opacity: 0.6~0.8`, `animation: float 3s ease-in-out`) | Backend systems, data dashboards, settings interfaces |\n| **Intent Visualization** | Use halos\u002Fparticles to suggest \"thinking\" (`box-shadow` pulse animations) | AI-generated content, smart recommendations |\n\n**CSS Prompt Examples:**\n```css\n\u002F* Ghostly Float *\u002F\n@keyframes float { 0%, 100% { transform: translateY(0); } 50% { transform: translateY(-8px); } }\n.ghostly-card { background: rgba(255,255,255,0.06); backdrop-filter: blur(12px); animation: float 4s ease-in-out infinite; }\n\n\u002F* Predictive Halo *\u002F\n@keyframes pulse-glow { 0%, 100% { box-shadow: 0 0 20px rgba(0,212,255,0.3); } 50% { box-shadow: 0 0 40px rgba(0,212,255,0.6); } }\n.agentic-hint { animation: pulse-glow 2s ease-in-out infinite; }\n```\n\n---\n\n#### 趋势二：粗砺真实 (The Grain of Truth)\n**核心**：Imperfect & Organic — 反秩序审美，有瑕疵的真实感\n\n| 设计策略 | 实现方式 | 适用场景 |\n|---|---|---|\n| **数字褶皱** | SVG 噪点纹理叠加 (`background-image: url(\"data:image\u002Fsvg+xml,...\")` 含 `\u003CfeTurbulence>`) | 创意品牌、独立工作室、手作品牌 |\n| **有机排版** | 轻微旋转 (`transform: rotate(-1deg~2deg)`), 非严格对齐 | 艺术展览、音乐活动、个人作品集 |\n| **触觉质感** | 颗粒感背景 + 不规则边框 (`border-radius: 48% 52% 50% 50% \u002F 50% 48% 52% 50%`) | 生活方式、食品、时尚 |\n\n**CSS Prompt Examples:**\n```css\n\u002F* Grain Texture Background *\u002F\n.grain-overlay { background-image: url(\"data:image\u002Fsvg+xml,%3Csvg viewBox='0 0 200 200' xmlns='http:\u002F\u002Fwww.w3.org\u002F2000\u002Fsvg'%3E%3Cfilter id='noise'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.9' numOctaves='4' \u002F%3E%3C\u002Ffilter%3E%3Crect width='100%25' height='100%25' filter='url(%23noise)' opacity='0.08'\u002F%3E%3C\u002Fsvg%3E\"); }\n\n\u002F* Organic Shape *\u002F\n.organic-shape { border-radius: 48% 52% 50% 50% \u002F 50% 48% 52% 50%; transform: rotate(-1.5deg); }\n```\n\n---\n\n#### Trend 3: Liminal Multimodality\n**Core**: Multimodal Seamlessness — Experience flows between voice, gesture, eye tracking, and touch\n\n| Design Strategy | Implementation | Use Cases |\n|---|---|---|\n| **Sensory Flow** | Wave animations suggest voice interaction (`animation: wave 1.5s ease-in-out`) | Voice assistants, podcasts, audio products |\n| **Spatial Hints** | 3D perspective + parallax scroll hints (`perspective: 1000px; transform: translateZ()`) | AR\u002FVR, spatial computing, metaverse |\n| **Multimodal Icons** | Visual elements of sound waves, gesture outlines, eye tracking paths | Cross-device experiences, seamless collaboration tools |\n\n**CSS Prompt Examples:**\n```css\n\u002F* Voice Wave *\u002F\n@keyframes wave { 0%, 100% { height: 8px; } 50% { height: 24px; } }\n.voice-wave span { display: inline-block; width: 4px; background: #00d4ff; animation: wave 1s ease-in-out infinite; }\n.voice-wave span:nth-child(2) { animation-delay: 0.1s; }\n.voice-wave span:nth-child(3) { animation-delay: 0.2s; }\n\n\u002F* Spatial Perspective *\u002F\n.liminal-space { perspective: 1000px; transform-style: preserve-3d; }\n.depth-layer { transform: translateZ(50px); }\n```\n\n---\n\n#### Trend 4: Emotional Sovereignty\n**Core**: Hyper-Personalized Ethical — Design for \"resonance\" rather than \"retention\"\n\n| Design Strategy | Implementation | Use Cases |\n|---|---|---|\n| **Transparent Explanation** | \"Why this recommendation\" tooltip (`data-explanation` shows on hover) | Healthcare, education, finance, AI recommendations |\n| **User Confirmation** | Clear \"Accept\u002FReject\" options, not default checkboxes | Privacy settings, data collection, personalization options |\n| **Personalized Visuals** | Dynamic color adjustment based on content theme (`--user-theme` CSS variables) | Personal dashboards, learning platforms, health apps |\n\n**CSS Prompt Examples:**\n```css\n\u002F* Explanatory Hint *\u002F\n.explainable-ui { position: relative; }\n.explainable-ui::after {\n  content: attr(data-explanation);\n  position: absolute; bottom: 100%; left: 0;\n  background: rgba(0,0,0,0.9); color: #fff;\n  padding: 8px 12px; border-radius: 8px;\n  font-size: 12px; max-width: 280px;\n  opacity: 0; transform: translateY(8px); transition: all 0.2s;\n}\n.explainable-ui:hover::after { opacity: 1; transform: translateY(0); }\n\n\u002F* Personalized Theme Variables *\u002F\n:root { --user-primary: #00d4ff; --user-secondary: #7b2fff; --user-accent: #00ffa3; }\n.personalized-card { border-left: 4px solid var(--user-primary); }\n```\n\n---\n\n### Trend Application Decision Tree\n\n```\nUser Need → Select Dominant Trends\n\nAI \u002F Automation Products → Ghostly Agency + Emotional Sovereignty\nCreative \u002F Art Content → Grain of Truth + Immersion & Expression\nTech \u002F Frontier Launches → Ghostly Agency + Liminal Multimodality\nHumanities \u002F Lifestyle → Grain of Truth + Care & Resonance\nEnterprise \u002F Professional → Emotional Sovereignty + Trust & Professional\n```\n\n**⚠️ Notes:**\n- Apply maximum **2 trends per presentation** to avoid visual chaos\n- Trends serve content — never use trends for trends' sake\n- Explain trend options to users during Style Discovery phase\n\n---\n\n## CRITICAL: Viewport Fitting Requirements\n\n**Mandatory for ALL presentations.** Every slide must be fully visible without scrolling on any screen size.\n\n### The Golden Rule\n\n- Each slide = exactly one viewport height (`100vh` \u002F `100dvh`).\n- Content overflows? → Split into multiple slides or reduce content. Never scroll within a slide.\n\n### Content Density Limits (per slide)\n\n| Slide Type    | Maximum Content                                              |\n|---------------|--------------------------------------------------------------|\n| Title slide   | 1 heading + 1 subtitle + optional tagline                    |\n| Content slide | 1 heading + 4–6 bullet points OR 1 heading + 2 paragraphs    |\n| Feature grid  | 1 heading + 6 cards max (2×3 or 3×2)                         |\n| Code slide    | 1 heading + 8–10 lines of code                                |\n| Quote slide   | 1 quote (max 3 lines) + attribution                          |\n| Image slide   | 1 heading + 1 image (max 60vh height)                        |\n\n**Required base CSS:** Include the full mandatory base styles in every presentation. **Copy from [reference\u002Fviewport-and-base.css](reference\u002Fviewport-and-base.css)** (or inline equivalent). It covers: html\u002Fbody lock, `.slide` = 100vh\u002F100dvh + overflow hidden, `.slide-content`, `:root` clamp() variables, cards\u002Flists\u002Fgrids\u002Fimages, responsive breakpoints (700px, 600px, 500px height; 600px width), and reduced-motion.\n\n### Overflow Prevention Checklist\n\nBefore generating: (1) Every `.slide` has `height: 100vh; height: 100dvh; overflow: hidden;` (2) All font sizes and spacing use `clamp()` or viewport units (3) Content containers have `max-height` (4) Images `max-height: min(50vh, 400px)` or similar (5) Grids use `auto-fit` + `minmax()` (6) Breakpoints for heights 700\u002F600\u002F500 (7) No fixed pixel heights on content (8) Per-slide content within density limits.\n\n### When Content Doesn't Fit\n\n**DO:** Split into multiple slides; reduce bullets (max 5–6); shorten text; smaller code snippets; \"continued\" slide; when adding images, move image to new slide or reduce other content first. **DON'T:** Shrink fonts below readable; remove padding; allow scrolling; cram.\n\n### Testing Viewport Fit\n\nRecommend testing at: Desktop 1920×1080, 1440×900, 1280×720; Tablet 1024×768, 768×1024; Mobile 375×667, 414×896; Landscape 667×375, 896×414.\n\n---\n\n## Phase 0: Detect Mode\n\n- **Mode A — New Presentation:** User wants slides from scratch → Phase 1 (Content Discovery).\n- **Mode B — PPT Conversion:** User has .ppt\u002F.pptx → Phase 4 (PPT Extraction).\n- **Mode C — Existing HTML Enhancement:** Read file, enhance; **always maintain viewport fitting.**\n\n### Mode C: Modification Rules\n\nBefore adding content: check current slide against density limits. **Images:** max `min(50vh, 400px)`; if slide already full → split into two slides (e.g. new slide for image). **Text:** max 4–6 bullets or 2 paragraphs per slide; if over → split or continuation slide. After any change: verify `.slide` has `overflow: hidden`, new elements use `clamp()`, new images have viewport max-height, density respected. If modifications cause overflow → **automatically split** and tell user. Test at 1280×720, 768×1024, 375×667.\n\n---\n\n## Solution PPT (解决方案 PPT) — 售前\u002F销售专用\n\nWhen purpose is **solution deck \u002F 解决方案汇报 \u002F 售前方案 \u002F 投标演示**, use this default outline (10–20 slides): (1) Title (2) Agenda (3) Background & objectives (4) Pain points & challenges (5) Solution overview (6–8) Capabilities \u002F product value (9) Case study (10) Implementation \u002F roadmap (11) Next steps & contact. Adjust as needed; respect content density. **Style:** Prefer **Swiss Modern**, **Electric Studio**, **Dark Botanical**, **Notebook Tabs**. Avoid highly playful styles unless asked.\n\n---\n\n## Phase 1: Content Discovery (New Presentations)\n\n**If AskUserQuestion is available:** Collect in one form. **If not (e.g. Cursor):** Ask the same questions in conversation, in order, and record answers before Phase 2.\n\n### Step 1.1: Context + Images (single form or sequence)\n\nAsk these five in one form (AskUserQuestion) or in sequence:\n\n1. **Purpose:** What is this presentation for? — Solution deck (解决方案 PPT) | Pitch deck | Teaching\u002FTutorial | Conference talk | Internal presentation\n2. **Length:** Approximately how many slides? — Short (5–10) | Medium (10–20) | Long (20+)\n3. **Content:** Do you have content ready or need help? — I have all content ready | I have rough notes | I have topic only\n4. **Images:** No images | .\u002Fassets | Other (let user type\u002Fpaste folder path, e.g. ~\u002FDesktop\u002Fscreenshots)\n5. **Editing:** Do you need to edit text in the browser after generation? — Yes (in-browser edit, auto-save, export) | No\n\nRemember the editing choice — it controls whether Phase 3 includes the edit button (see reference\u002Fedit-button-implementation.md).\n\n**Get the content:** If user said \"I have all content ready\" → ask them to share it (paste text, bullet points, or path to file). If \"I have rough notes\" or \"I have topic only\" → help structure an outline, then ask for or draft the slide-by-slide content. You need concrete titles and body content before Phase 2.\n\n### Step 1.2: Image Evaluation (if user provided images)\n\nIf \"No images\" → skip image pipeline; use text + CSS visuals. If folder provided: (1) List image files (2) Read\u002Fview each (3) Mark USABLE \u002F NOT USABLE with reason; note content signal, shape, dominant colors (4) Propose slide outline with image assignments (5) Confirm outline via AskUserQuestion or conversation: \"Looks good\" | \"Adjust images\" | \"Adjust outline\". Co-design: usable images shape the outline from the start. Logo in previews: if USABLE logo exists, embed (e.g. base64) in the 3 style previews so user sees their brand in each style.\n\n---\n\n## Phase 2: Style Discovery\n\n**Option A — Guided:** Ask mood (Impressed\u002FConfident | Excited\u002FEnergized | Calm\u002FFocused | Inspired\u002FMoved; multiSelect up to 2). Create directory `.claude-design\u002Fslide-previews\u002F` if needed. Generate **3 style previews** there (style-a.html, style-b.html, style-c.html): single title slide each, self-contained, ~50–100 lines. Pick 3 presets by mood (e.g. Impressed → Bold Signal, Electric Studio, Dark Botanical). **Never use:** purple gradients on white, Inter\u002FRoboto, standard blue, predictable hero. **Use:** distinctive fonts (Clash Display, Satoshi, Cormorant Garamond, DM Sans), cohesive colors, atmospheric backgrounds, signature animation. Present previews; user picks Style A\u002FB\u002FC or \"Mix elements\". **Option B — Direct:** Ask \"Which preset?\" and show the preset list (below or from STYLE_PRESETS.md). User picks by name → skip to Phase 3.\n\n**Presets (see STYLE_PRESETS.md for full list):** Bold Signal | Electric Studio | Creative Voltage | Dark Botanical | Notebook Tabs | Pastel Geometry | Split Pastel | Vintage Editorial | Neon Cyber | Terminal Green | Swiss Modern | Paper & Ink. Mood → preset mapping: Impressed\u002FConfident → Bold Signal, Electric Studio, Dark Botanical; Excited\u002FEnergized → Creative Voltage, Neon Cyber, Split Pastel; Calm\u002FFocused → Notebook Tabs, Paper & Ink, Swiss Modern; Inspired\u002FMoved → Dark Botanical, Vintage Editorial, Pastel Geometry.\n\n---\n\n## Phase 3: Generate Presentation\n\nUse content from Phase 1 and style from Phase 2. If no images, generate text-only with CSS visuals. If images: **Image pipeline** — process before HTML. **Operations:** See [reference\u002Fimage-processing.py](reference\u002Fimage-processing.py) for `crop_circle`, `resize_max`, `add_padding`. Dependency: `pip install Pillow`. Never repeat same image (except logo on title+closing); add CSS framing (border\u002Fglow) when image clashes with style. Save processed images to a new filename (e.g. `logo_round.png`, `screenshot_processed.png`); never overwrite originals. Reference in HTML with relative paths (e.g. `assets\u002Flogo_round.png`). **Image CSS:** `.slide-image` max-height min(50vh, 400px); `.screenshot` border+shadow; `.logo` max-height min(30vh, 200px). Adapt border\u002Fshadow to style accent. Placement: title = logo centered; feature = screenshot one side, text other; full-bleed or inline as needed.\n\n**File structure:** Single: `presentation.html` + `assets\u002F`. Multiple: `[name].html` + `[name]-assets\u002F`.\n\n**HTML architecture:** Follow [reference\u002Fhtml-architecture.md](reference\u002Fhtml-architecture.md). Include mandatory viewport base CSS, theme variables (clamp() for all typography\u002Fspacing), .slide + .slide-content, responsive breakpoints, .reveal + .visible for animations.\n\n**Required JS:** Implement SlidePresentation: keyboard (arrows, space), touch\u002Fswipe, mouse wheel; progress bar and navigation dots (click dot to jump to slide); Intersection Observer to add `.visible` when a slide enters the viewport so .reveal animations run. Optional: cursor trail, particles, parallax, tilt, inline editing. **Edit button (only if user opted Yes):** See [reference\u002Fedit-button-implementation.md](reference\u002Fedit-button-implementation.md). Use JS hover with delay (no CSS ~ sibling); hotzone + E key + click to toggle.\n\n**Code quality:** Clear section comments; semantic HTML; keyboard nav; ARIA where needed; reduced motion. **CSS negation:** Use `calc(-1 * clamp(...))`, never `-clamp()`. See STYLE_PRESETS.md \"CSS Gotchas\". Viewport: always respect density and overflow rules above.\n\n---\n\n## Phase 4: PPT Conversion\n\n1. **Extract:** Run the logic from [reference\u002Fppt-extract.py](reference\u002Fppt-extract.py): `extract_pptx(user_pptx_path, output_dir)`. Dependency: `pip install python-pptx`. Use an output_dir (e.g. current directory or a new folder) so images are saved to `output_dir\u002Fassets\u002F` and the future HTML can use `assets\u002F` as sibling. Returns slides_data (per slide: title, content[], images[], notes).\n2. **Confirm:** Present extracted slide list to user; ask to proceed to style selection.\n3. **Style:** Phase 2 (Style Discovery) with extracted content in mind.\n4. **Generate:** Build the HTML presentation in the **same output_dir** used in step 1 so that `assets\u002F` is next to the .html file. Convert to chosen style; preserve text, images (reference from assets\u002F), slide order, speaker notes (as HTML comments or separate file).\n\n---\n\n## Phase 5: Delivery\n\n1. Delete `.claude-design\u002Fslide-previews\u002F` if present.\n2. Open presentation in browser (e.g. `open [filename].html`).\n3. Summary: file, style, slide count; navigation (arrows, space, scroll, dots); customization (:root, fonts, .reveal). If inline editing: hover top-left or E to edit; Ctrl+S or \"Save file\".\n\n---\n\n## Style Reference: Effect → Feeling\n\n- **Dramatic\u002FCinematic:** Slow fades, scale transitions, dark + spotlight, parallax, full-bleed.\n- **Techy\u002FFuturistic:** Neon glow, particles, grid, monospace accents, cyan\u002Fmagenta palette.\n- **Playful\u002FFriendly:** Bouncy easing, rounded, pastel\u002Fbright, floating animations.\n- **Professional\u002FCorporate:** Subtle fast animations (200–300ms), clean sans, navy\u002Fslate, minimal decor.\n- **Calm\u002FMinimal:** Slow subtle motion, whitespace, muted palette, serif, content-focused.\n- **Editorial:** Strong type hierarchy, pull quotes, image-text interplay, serif headline + sans body.\n\n**Animation patterns (entrance, backgrounds, interactive):** See [reference\u002Fanimation-patterns.md](reference\u002Fanimation-patterns.md).\n\n---\n\n## Troubleshooting\n\n- **Fonts not loading:** Check Fontshare\u002FGoogle URL; font names in CSS.\n- **Animations not triggering:** Intersection Observer; .visible class.\n- **Scroll snap:** scroll-snap-type on html; scroll-snap-align on each .slide.\n- **Mobile:** Disable heavy effects at 768px; test touch; reduce particles.\n- **Performance:** Use will-change sparingly; prefer transform\u002Fopacity; throttle scroll\u002Fmousemove.\n\n---\n\n## Example Flows\n\n**New presentation:** User wants pitch\u002Fsolution deck → ask purpose, length, content, images, editing → (if images) evaluate, outline, confirm → ask vibe → 3 previews → user picks style → (if images) run Pillow ops → generate HTML → open in browser.\n\n**PPT conversion:** User has .pptx → extract with ppt-extract.py → confirm content → style selection → generate HTML with assets.\n","# Frontend Slides Skill\n\nCreate zero-dependency, animation-rich HTML presentations that run entirely in the browser. This skill helps non-designers discover their preferred aesthetic through visual exploration (\"show, don't tell\"), then generates production-quality slide decks.\n\n**Reference files:** When generating CSS, image processing, PPT extraction, HTML structure, edit button, or animation code, read the corresponding file under `reference\u002F` (and STYLE_PRESETS.md for presets and CSS Gotchas) so output is correct and complete.\n\n---\n\n## 🧠 Core Design Philosophy\n\n### 1. Visual Style & Material\n\n**Principle**: Form follows function. All visual decisions (color, layout, material) must serve the user's mental model and business goals.\n\n| Style Position | Use Cases | Core Characteristics |\n|---|---|---|\n| **Future & Depth** | Frontier exploration, tech product launches | Frosted glass + dark mode, halos and transparency for layering |\n| **Efficiency & Speed** | Professional tools, data dashboards | Clean flat style + Bento UI, clear boundaries, modular |\n| **Trust & Professional** | Finance, formal presentations, enterprise solutions | Swiss minimalism, generous whitespace, relies on typography and strict grids |\n| **Care & Resonance** | Humanities, lifestyle, brand stories | Low-saturation natural colors + extreme rounding, ultra-soft diffuse shadows |\n| **Immersion & Expression** | Entertainment, narrative, creative showcases | Skeuomorphic materials + high-contrast emotional colors, breaks conventional grids |\n\n**Style Selection Rules:**\n- Solution deck \u002F presales proposal → Trust & Professional (Swiss Modern) or Efficiency & Speed (Bento UI)\n- Product launch \u002F tech showcase → Future & Depth (Dark Botanical \u002F Electric Studio)\n- Brand story \u002F humanities content → Care & Resonance (Pastel Geometry \u002F Vintage Editorial)\n- Creative proposal \u002F marketing campaign → Immersion & Expression (Neon Cyber \u002F Creative Voltage)\n\n### 2. Spatial & Typography Organization\n\n- **Density Hierarchy**: Density is inversely proportional to importance. Core focus areas need low density \u002F large margins. Data lists need high density \u002F small margins.\n- **Typography System**:\n  - Prefer modern sans-serif fonts (Clash Display, Satoshi, DM Sans)\n  - Establish significant **weight** and **size** contrast between headings and body\n  - Body line-height: `leading-[1.5]` or `leading-[1.6]` for visual breathability\n- **Font Size Constraints**:\n  - Minimum readable size: `12px` (annotations only)\n  - Standard body: `14px\u002F16px`\n  - Headings use `clamp()` for responsive scaling\n\n### 3. Affordance & Resilience\n\nAlthough the output is static HTML, when handling multiple similar components (lists, navigation, card groups), **you must hardcode and render different interaction states within the same container** to exhaustively show the component's full lifecycle.\n\n- **⚠️ Warning**: Do not rely solely on Tailwind's `hover:` pseudo-class for interactions. You must directly change the base class of specific items to make states **simultaneously visible** in static screenshots!\n- **Example**: In a card group, first card uses default state, second card uses `bg-white\u002F10` to simulate hover state, third card uses `border-cyan-400` to simulate selected state\n\n### 4. System Integrity Constraints\n\n**All design decisions must map to the following limited variable set (no odd numbers, decimals, or random values allowed):**\n\n| System | Constraints |\n|---|---|\n| **Color System** | Primary color defines brand; **complementary color** for strong guidance; **analogous colors** for soft guidance. No arbitrary colors |\n| **Spatial Spacing (8-Point Grid)** | Spacing and padding limited to: `8` \u002F `12` \u002F `16` \u002F `20` \u002F `24` \u002F `32` \u002F `40` (strictly apply to gap and padding) |\n| **Corner Radius** | Choose based on style, default starts at `rounded-[12px]`. Care style can use `rounded-[24px]` or `rounded-full` |\n| **Size Minimums** | Minimum click hotspot `44px`; minimum readable size `12px`; standard body `14px\u002F16px` |\n| **Shadow Control** | Must use diffuse lighting like `shadow-[0_10px_30px_rgba(0,0,0,0.08)]`, no harsh shadows |\n\n---\n\n### 5. 🌀 Emerging Design Trends 2026\n\nIntegrate the following four trends organically into presentation design. Select 1-2 dominant trends based on content theme.\n\n#### Trend 1: Ghostly Agency\n**Core**: Agentic UX — The interface acts like a translucent butler, preparing everything before the user asks\n\n| Design Strategy | Implementation | Use Cases |\n|---|---|---|\n| **Predictive Presence** | Progressive content reveal (`.reveal` animations trigger in stages) | AI products, automation services, intelligent assistants |\n| **Invisible Butler** | Translucent elements + subtle floating animations (`opacity: 0.6~0.8`, `animation: float 3s ease-in-out`) | Backend systems, data dashboards, settings interfaces |\n| **Intent Visualization** | Use halos\u002Fparticles to suggest \"thinking\" (`box-shadow` pulse animations) | AI-generated content, smart recommendations |\n\n**CSS Prompt Examples:**\n```css\n\u002F* Ghostly Float *\u002F\n@keyframes float { 0%, 100% { transform: translateY(0); } 50% { transform: translateY(-8px); } }\n.ghostly-card { background: rgba(255,255,255,0.06); backdrop-filter: blur(12px); animation: float 4s ease-in-out infinite; }\n\n\u002F* Predictive Halo *\u002F\n@keyframes pulse-glow { 0%, 100% { box-shadow: 0 0 20px rgba(0,212,255,0.3); } 50% { box-shadow: 0 0 40px rgba(0,212,255,0.6); } }\n.agentic-hint { animation: pulse-glow 2s ease-in-out infinite; }\n```\n\n---\n\n#### 趋势二：粗砺真实 (The Grain of Truth)\n**核心**：Imperfect & Organic — 反秩序审美，有瑕疵的真实感\n\n| 设计策略 | 实现方式 | 适用场景 |\n|---|---|---|\n| **数字褶皱** | SVG 噪点纹理叠加 (`background-image: url(\"data:image\u002Fsvg+xml,...\")` 含 `\u003CfeTurbulence>`) | 创意品牌、独立工作室、手作品牌 |\n| **有机排版** | 轻微旋转 (`transform: rotate(-1deg~2deg)`), 非严格对齐 | 艺术展览、音乐活动、个人作品集 |\n| **触觉质感** | 颗粒感背景 + 不规则边框 (`border-radius: 48% 52% 50% 50% \u002F 50% 48% 52% 50%`) | 生活方式、食品、时尚 |\n\n**CSS Prompt Examples:**\n```css\n\u002F* Grain Texture Background *\u002F\n.grain-overlay { background-image: url(\"data:image\u002Fsvg+xml,%3Csvg viewBox='0 0 200 200' xmlns='http:\u002F\u002Fwww.w3.org\u002F2000\u002Fsvg'%3E%3Cfilter id='noise'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.9' numOctaves='4' \u002F%3E%3C\u002Ffilter%3E%3Crect width='100%25' height='100%25' filter='url(%23noise)' opacity='0.08'\u002F%3E%3C\u002Fsvg%3E\"); }\n\n\u002F* Organic Shape *\u002F\n.organic-shape { border-radius: 48% 52% 50% 50% \u002F 50% 48% 52% 50%; transform: rotate(-1.5deg); }\n```\n\n---\n\n#### Trend 3: Liminal Multimodality\n**Core**: Multimodal Seamlessness — Experience flows between voice, gesture, eye tracking, and touch\n\n| Design Strategy | Implementation | Use Cases |\n|---|---|---|\n| **Sensory Flow** | Wave animations suggest voice interaction (`animation: wave 1.5s ease-in-out`) | Voice assistants, podcasts, audio products |\n| **Spatial Hints** | 3D perspective + parallax scroll hints (`perspective: 1000px; transform: translateZ()`) | AR\u002FVR, spatial computing, metaverse |\n| **Multimodal Icons** | Visual elements of sound waves, gesture outlines, eye tracking paths | Cross-device experiences, seamless collaboration tools |\n\n**CSS Prompt Examples:**\n```css\n\u002F* Voice Wave *\u002F\n@keyframes wave { 0%, 100% { height: 8px; } 50% { height: 24px; } }\n.voice-wave span { display: inline-block; width: 4px; background: #00d4ff; animation: wave 1s ease-in-out infinite; }\n.voice-wave span:nth-child(2) { animation-delay: 0.1s; }\n.voice-wave span:nth-child(3) { animation-delay: 0.2s; }\n\n\u002F* Spatial Perspective *\u002F\n.liminal-space { perspective: 1000px; transform-style: preserve-3d; }\n.depth-layer { transform: translateZ(50px); }\n```\n\n---\n\n#### Trend 4: Emotional Sovereignty\n**Core**: Hyper-Personalized Ethical — Design for \"resonance\" rather than \"retention\"\n\n| Design Strategy | Implementation | Use Cases |\n|---|---|---|\n| **Transparent Explanation** | \"Why this recommendation\" tooltip (`data-explanation` shows on hover) | Healthcare, education, finance, AI recommendations |\n| **User Confirmation** | Clear \"Accept\u002FReject\" options, not default checkboxes | Privacy settings, data collection, personalization options |\n| **Personalized Visuals** | Dynamic color adjustment based on content theme (`--user-theme` CSS variables) | Personal dashboards, learning platforms, health apps |\n\n**CSS Prompt Examples:**\n```css\n\u002F* Explanatory Hint *\u002F\n.explainable-ui { position: relative; }\n.explainable-ui::after {\n  content: attr(data-explanation);\n  position: absolute; bottom: 100%; left: 0;\n  background: rgba(0,0,0,0.9); color: #fff;\n  padding: 8px 12px; border-radius: 8px;\n  font-size: 12px; max-width: 280px;\n  opacity: 0; transform: translateY(8px); transition: all 0.2s;\n}\n.explainable-ui:hover::after { opacity: 1; transform: translateY(0); }\n\n\u002F* Personalized Theme Variables *\u002F\n:root { --user-primary: #00d4ff; --user-secondary: #7b2fff; --user-accent: #00ffa3; }\n.personalized-card { border-left: 4px solid var(--user-primary); }\n```\n\n---\n\n### Trend Application Decision Tree\n\n```\nUser Need → Select Dominant Trends\n\nAI \u002F Automation Products → Ghostly Agency + Emotional Sovereignty\nCreative \u002F Art Content → Grain of Truth + Immersion & Expression\nTech \u002F Frontier Launches → Ghostly Agency + Liminal Multimodality\nHumanities \u002F Lifestyle → Grain of Truth + Care & Resonance\nEnterprise \u002F Professional → Emotional Sovereignty + Trust & Professional\n```\n\n**⚠️ Notes:**\n- Apply maximum **2 trends per presentation** to avoid visual chaos\n- Trends serve content — never use trends for trends' sake\n- Explain trend options to users during Style Discovery phase\n\n---\n\n## CRITICAL: Viewport Fitting Requirements\n\n**Mandatory for ALL presentations.** Every slide must be fully visible without scrolling on any screen size.\n\n### The Golden Rule\n\n- Each slide = exactly one viewport height (`100vh` \u002F `100dvh`).\n- Content overflows? → Split into multiple slides or reduce content. Never scroll within a slide.\n\n### Content Density Limits (per slide)\n\n| Slide Type    | Maximum Content                                              |\n|---------------|--------------------------------------------------------------|\n| Title slide   | 1 heading + 1 subtitle + optional tagline                    |\n| Content slide | 1 heading + 4–6 bullet points OR 1 heading + 2 paragraphs    |\n| Feature grid  | 1 heading + 6 cards max (2×3 or 3×2)                         |\n| Code slide    | 1 heading + 8–10 lines of code                                |\n| Quote slide   | 1 quote (max 3 lines) + attribution                          |\n| Image slide   | 1 heading + 1 image (max 60vh height)                        |\n\n**Required base CSS:** Include the full mandatory base styles in every presentation. **Copy from [reference\u002Fviewport-and-base.css](reference\u002Fviewport-and-base.css)** (or inline equivalent). It covers: html\u002Fbody lock, `.slide` = 100vh\u002F100dvh + overflow hidden, `.slide-content`, `:root` clamp() variables, cards\u002Flists\u002Fgrids\u002Fimages, responsive breakpoints (700px, 600px, 500px height; 600px width), and reduced-motion.\n\n### Overflow Prevention Checklist\n\nBefore generating: (1) Every `.slide` has `height: 100vh; height: 100dvh; overflow: hidden;` (2) All font sizes and spacing use `clamp()` or viewport units (3) Content containers have `max-height` (4) Images `max-height: min(50vh, 400px)` or similar (5) Grids use `auto-fit` + `minmax()` (6) Breakpoints for heights 700\u002F600\u002F500 (7) No fixed pixel heights on content (8) Per-slide content within density limits.\n\n### When Content Doesn't Fit\n\n**DO:** Split into multiple slides; reduce bullets (max 5–6); shorten text; smaller code snippets; \"continued\" slide; when adding images, move image to new slide or reduce other content first. **DON'T:** Shrink fonts below readable; remove padding; allow scrolling; cram.\n\n### Testing Viewport Fit\n\nRecommend testing at: Desktop 1920×1080, 1440×900, 1280×720; Tablet 1024×768, 768×1024; Mobile 375×667, 414×896; Landscape 667×375, 896×414.\n\n---\n\n## Phase 0: Detect Mode\n\n- **Mode A — New Presentation:** User wants slides from scratch → Phase 1 (Content Discovery).\n- **Mode B — PPT Conversion:** User has .ppt\u002F.pptx → Phase 4 (PPT Extraction).\n- **Mode C — Existing HTML Enhancement:** Read file, enhance; **always maintain viewport fitting.**\n\n### Mode C: Modification Rules\n\nBefore adding content: check current slide against density limits. **Images:** max `min(50vh, 400px)`; if slide already full → split into two slides (e.g. new slide for image). **Text:** max 4–6 bullets or 2 paragraphs per slide; if over → split or continuation slide. After any change: verify `.slide` has `overflow: hidden`, new elements use `clamp()`, new images have viewport max-height, density respected. If modifications cause overflow → **automatically split** and tell user. Test at 1280×720, 768×1024, 375×667.\n\n---\n\n## Solution PPT (解决方案 PPT) — 售前\u002F销售专用\n\nWhen purpose is **solution deck \u002F 解决方案汇报 \u002F 售前方案 \u002F 投标演示**, use this default outline (10–20 slides): (1) Title (2) Agenda (3) Background & objectives (4) Pain points & challenges (5) Solution overview (6–8) Capabilities \u002F product value (9) Case study (10) Implementation \u002F roadmap (11) Next steps & contact. Adjust as needed; respect content density. **Style:** Prefer **Swiss Modern**, **Electric Studio**, **Dark Botanical**, **Notebook Tabs**. Avoid highly playful styles unless asked.\n\n---\n\n## Phase 1: Content Discovery (New Presentations)\n\n**If AskUserQuestion is available:** Collect in one form. **If not (e.g. Cursor):** Ask the same questions in conversation, in order, and record answers before Phase 2.\n\n### Step 1.1: Context + Images (single form or sequence)\n\nAsk these five in one form (AskUserQuestion) or in sequence:\n\n1. **Purpose:** What is this presentation for? — Solution deck (解决方案 PPT) | Pitch deck | Teaching\u002FTutorial | Conference talk | Internal presentation\n2. **Length:** Approximately how many slides? — Short (5–10) | Medium (10–20) | Long (20+)\n3. **Content:** Do you have content ready or need help? — I have all content ready | I have rough notes | I have topic only\n4. **Images:** No images | .\u002Fassets | Other (let user type\u002Fpaste folder path, e.g. ~\u002FDesktop\u002Fscreenshots)\n5. **Editing:** Do you need to edit text in the browser after generation? — Yes (in-browser edit, auto-save, export) | No\n\nRemember the editing choice — it controls whether Phase 3 includes the edit button (see reference\u002Fedit-button-implementation.md).\n\n**Get the content:** If user said \"I have all content ready\" → ask them to share it (paste text, bullet points, or path to file). If \"I have rough notes\" or \"I have topic only\" → help structure an outline, then ask for or draft the slide-by-slide content. You need concrete titles and body content before Phase 2.\n\n### Step 1.2: Image Evaluation (if user provided images)\n\nIf \"No images\" → skip image pipeline; use text + CSS visuals. If folder provided: (1) List image files (2) Read\u002Fview each (3) Mark USABLE \u002F NOT USABLE with reason; note content signal, shape, dominant colors (4) Propose slide outline with image assignments (5) Confirm outline via AskUserQuestion or conversation: \"Looks good\" | \"Adjust images\" | \"Adjust outline\". Co-design: usable images shape the outline from the start. Logo in previews: if USABLE logo exists, embed (e.g. base64) in the 3 style previews so user sees their brand in each style.\n\n---\n\n## Phase 2: Style Discovery\n\n**Option A — Guided:** Ask mood (Impressed\u002FConfident | Excited\u002FEnergized | Calm\u002FFocused | Inspired\u002FMoved; multiSelect up to 2). Create directory `.claude-design\u002Fslide-previews\u002F` if needed. Generate **3 style previews** there (style-a.html, style-b.html, style-c.html): single title slide each, self-contained, ~50–100 lines. Pick 3 presets by mood (e.g. Impressed → Bold Signal, Electric Studio, Dark Botanical). **Never use:** purple gradients on white, Inter\u002FRoboto, standard blue, predictable hero. **Use:** distinctive fonts (Clash Display, Satoshi, Cormorant Garamond, DM Sans), cohesive colors, atmospheric backgrounds, signature animation. Present previews; user picks Style A\u002FB\u002FC or \"Mix elements\". **Option B — Direct:** Ask \"Which preset?\" and show the preset list (below or from STYLE_PRESETS.md). User picks by name → skip to Phase 3.\n\n**Presets (see STYLE_PRESETS.md for full list):** Bold Signal | Electric Studio | Creative Voltage | Dark Botanical | Notebook Tabs | Pastel Geometry | Split Pastel | Vintage Editorial | Neon Cyber | Terminal Green | Swiss Modern | Paper & Ink. Mood → preset mapping: Impressed\u002FConfident → Bold Signal, Electric Studio, Dark Botanical; Excited\u002FEnergized → Creative Voltage, Neon Cyber, Split Pastel; Calm\u002FFocused → Notebook Tabs, Paper & Ink, Swiss Modern; Inspired\u002FMoved → Dark Botanical, Vintage Editorial, Pastel Geometry.\n\n---\n\n## Phase 3: Generate Presentation\n\nUse content from Phase 1 and style from Phase 2. If no images, generate text-only with CSS visuals. If images: **Image pipeline** — process before HTML. **Operations:** See [reference\u002Fimage-processing.py](reference\u002Fimage-processing.py) for `crop_circle`, `resize_max`, `add_padding`. Dependency: `pip install Pillow`. Never repeat same image (except logo on title+closing); add CSS framing (border\u002Fglow) when image clashes with style. Save processed images to a new filename (e.g. `logo_round.png`, `screenshot_processed.png`); never overwrite originals. Reference in HTML with relative paths (e.g. `assets\u002Flogo_round.png`). **Image CSS:** `.slide-image` max-height min(50vh, 400px); `.screenshot` border+shadow; `.logo` max-height min(30vh, 200px). Adapt border\u002Fshadow to style accent. Placement: title = logo centered; feature = screenshot one side, text other; full-bleed or inline as needed.\n\n**File structure:** Single: `presentation.html` + `assets\u002F`. Multiple: `[name].html` + `[name]-assets\u002F`.\n\n**HTML architecture:** Follow [reference\u002Fhtml-architecture.md](reference\u002Fhtml-architecture.md). Include mandatory viewport base CSS, theme variables (clamp() for all typography\u002Fspacing), .slide + .slide-content, responsive breakpoints, .reveal + .visible for animations.\n\n**Required JS:** Implement SlidePresentation: keyboard (arrows, space), touch\u002Fswipe, mouse wheel; progress bar and navigation dots (click dot to jump to slide); Intersection Observer to add `.visible` when a slide enters the viewport so .reveal animations run. Optional: cursor trail, particles, parallax, tilt, inline editing. **Edit button (only if user opted Yes):** See [reference\u002Fedit-button-implementation.md](reference\u002Fedit-button-implementation.md). Use JS hover with delay (no CSS ~ sibling); hotzone + E key + click to toggle.\n\n**Code quality:** Clear section comments; semantic HTML; keyboard nav; ARIA where needed; reduced motion. **CSS negation:** Use `calc(-1 * clamp(...))`, never `-clamp()`. See STYLE_PRESETS.md \"CSS Gotchas\". Viewport: always respect density and overflow rules above.\n\n---\n\n## Phase 4: PPT Conversion\n\n1. **Extract:** Run the logic from [reference\u002Fppt-extract.py](reference\u002Fppt-extract.py): `extract_pptx(user_pptx_path, output_dir)`. Dependency: `pip install python-pptx`. Use an output_dir (e.g. current directory or a new folder) so images are saved to `output_dir\u002Fassets\u002F` and the future HTML can use `assets\u002F` as sibling. Returns slides_data (per slide: title, content[], images[], notes).\n2. **Confirm:** Present extracted slide list to user; ask to proceed to style selection.\n3. **Style:** Phase 2 (Style Discovery) with extracted content in mind.\n4. **Generate:** Build the HTML presentation in the **same output_dir** used in step 1 so that `assets\u002F` is next to the .html file. Convert to chosen style; preserve text, images (reference from assets\u002F), slide order, speaker notes (as HTML comments or separate file).\n\n---\n\n## Phase 5: Delivery\n\n1. Delete `.claude-design\u002Fslide-previews\u002F` if present.\n2. Open presentation in browser (e.g. `open [filename].html`).\n3. Summary: file, style, slide count; navigation (arrows, space, scroll, dots); customization (:root, fonts, .reveal). If inline editing: hover top-left or E to edit; Ctrl+S or \"Save file\".\n\n---\n\n## Style Reference: Effect → Feeling\n\n- **Dramatic\u002FCinematic:** Slow fades, scale transitions, dark + spotlight, parallax, full-bleed.\n- **Techy\u002FFuturistic:** Neon glow, particles, grid, monospace accents, cyan\u002Fmagenta palette.\n- **Playful\u002FFriendly:** Bouncy easing, rounded, pastel\u002Fbright, floating animations.\n- **Professional\u002FCorporate:** Subtle fast animations (200–300ms), clean sans, navy\u002Fslate, minimal decor.\n- **Calm\u002FMinimal:** Slow subtle motion, whitespace, muted palette, serif, content-focused.\n- **Editorial:** Strong type hierarchy, pull quotes, image-text interplay, serif headline + sans body.\n\n**Animation patterns (entrance, backgrounds, interactive):** See [reference\u002Fanimation-patterns.md](reference\u002Fanimation-patterns.md).\n\n---\n\n## Troubleshooting\n\n- **Fonts not loading:** Check Fontshare\u002FGoogle URL; font names in CSS.\n- **Animations not triggering:** Intersection Observer; .visible class.\n- **Scroll snap:** scroll-snap-type on html; scroll-snap-align on each .slide.\n- **Mobile:** Disable heavy effects at 768px; test touch; reduce particles.\n- **Performance:** Use will-change sparingly; prefer transform\u002Fopacity; throttle scroll\u002Fmousemove.\n\n---\n\n## Example Flows\n\n**New presentation:** User wants pitch\u002Fsolution deck → ask purpose, length, content, images, editing → (if images) evaluate, outline, confirm → ask vibe → 3 previews → user picks style → (if images) run Pillow ops → generate HTML → open in browser.\n\n**PPT conversion:** User has .pptx → extract with ppt-extract.py → confirm content → style selection → generate HTML with assets.\n",{"name":5,"description":7},"main","0446e11613ad1942de249b12f7deea3889c25af4","skills\u002Ffrontend-slides",0,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings","https:\u002F\u002Fgithub.com\u002FViewWay","rust can do everything","2026-06-19 23:27:05",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add ViewWay\u002Fhermes-by-everythings --skill frontend-slides",{"tool":65,"command":66},"bunx","bunx skills add ViewWay\u002Fhermes-by-everythings --skill frontend-slides",{"tool":68,"command":69},"pnpm","pnpm dlx skills add ViewWay\u002Fhermes-by-everythings --skill frontend-slides","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002FSKILL.md",true,[73,79,83,87,91,95,99,105,109,115,119],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"_meta.json","REFERENCE","参考文档",134,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002F_meta.json",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},".clawhub\u002Forigin.json",147,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002F.clawhub\u002Forigin.json",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"README.md",5703,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002FREADME.md",{"path":88,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":89,"sourceHtmlUrl":90},"reference\u002Fanimation-patterns.md",1343,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002Freference\u002Fanimation-patterns.md",{"path":92,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":93,"sourceHtmlUrl":94},"reference\u002Fedit-button-implementation.md",1437,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002Freference\u002Fedit-button-implementation.md",{"path":96,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":97,"sourceHtmlUrl":98},"reference\u002Fhtml-architecture.md",2138,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002Freference\u002Fhtml-architecture.md",{"path":100,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":103,"sourceHtmlUrl":104},"reference\u002Fimage-processing.py","SCRIPT","脚本",1753,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002Freference\u002Fimage-processing.py",{"path":106,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":107,"sourceHtmlUrl":108},"reference\u002Fppt-extract.py",2023,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002Freference\u002Fppt-extract.py",{"path":110,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":113,"sourceHtmlUrl":114},"reference\u002Fviewport-and-base.css","OTHER","其他",3662,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002Freference\u002Fviewport-and-base.css",{"path":116,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":117,"sourceHtmlUrl":118},"REVIEW.md",9135,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002FREVIEW.md",{"path":120,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":121,"sourceHtmlUrl":122},"STYLE_PRESETS.md",13934,"https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-slides\u002FSTYLE_PRESETS.md",[124,159,185,210,241,262],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":139,"publishedAt":46},"01M71EREGWXCCGBGDZ969RZQA7","ui-ux-pro-max","UI\u002FUX design intelligence and implementation guidance for building polished interfaces. Use when the user asks for UI design, UX flows, information architecture, visual style direction, design systems\u002Ftokens, component specs, copy\u002Fmicrocopy, accessibility, or to generate\u002Fcritique\u002Frefine frontend UI (HTML\u002FCSS\u002FJS, React, Next.js, Vue, Svelte, Tailwind). Includes workflows for (1) generating new UI layouts and styling, (2) improving existing UI\u002FUX, (3) producing design-system tokens and component guidelines, and (4) turning UX recommendations into concrete code changes.","https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Fui-ux-pro-max\u002FSKILL.md",[130,131,134],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":132,"categoryName":133,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":135,"categoryName":136,"taxonomyType":137,"taxonomyTypeDesc":138},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[140,141,142,143,144,145,146,147,148,149,150,151,28,152,153,154,155,156,157,158],"ux","max","ui ux","ui","ui ux pro max","pro","information architecture","css","microcopy","direction","Tailwind","flows","design","new","svelte","design systems","information","workflows","when",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":46},"01M71ERBY797MAY4HTFMSHPXMY","springboot-verification","Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.","https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Fspringboot-verification\u002FSKILL.md",[],[166,167,168,169,170,171,172,33,173,174,175,176,177,178,179,180,181,182,183,184],"springboot verification","verification","coverage","projects","verification loop","pr","diff","static","tests","spring boot","diff review","spring","loop","boot","analysis","review","with","build","release",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":194,"publishedAt":46},"01M71ER9TQGK9Y00JEEM6RW9RY","springboot-patterns","Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.","https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Fspringboot-patterns\u002FSKILL.md",[191],{"categoryNo":192,"categoryName":193,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",[195,196,197,198,175,152,199,200,201,202,203,204,205,206,207,33,208,209,29,177],"patterns","springboot patterns","processing","rest api design","access","caching","architecture","api","spring boot architecture","work","data","architecture patterns","logging","async","java spring",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":223,"publishedAt":46},"01M71ER6XTWDJ0NVE5RFY28RE7","security-auditor","Use when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS\u002FCSP headers, handling secrets, input validation, SQL injection prevention, XSS protection, or any security-related code review.","https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Fsecurity-auditor\u002FSKILL.md",[216,219,220],{"categoryNo":217,"categoryName":218,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":192,"categoryName":193,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":221,"categoryName":222,"taxonomyType":137,"taxonomyTypeDesc":138},"01JBSEEDCAT000000000000033","数据分析师",[224,225,226,227,228,151,229,230,231,158,232,233,234,235,181,236,237,238,239,240],"security","security auditor","auditor","authentication","code review","implementing","csrf","Input Validation","encryption","code","vulnerability","xss","top","owasp top 10","audit","sql","secrets",{"skillNo":242,"name":243,"nameZh":6,"description":244,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":245,"categories":246,"keywords":250,"publishedAt":46},"01M71ER4PHRJ1EKXQTQPEPYQ6J","rust-testing","Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.","https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Frust-testing\u002FSKILL.md",[247],{"categoryNo":248,"categoryName":249,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",[251,252,253,168,254,255,195,256,208,257,174,258,259,260,261],"rust","testing","rust testing","unit","testing patterns","integration tests","mocking","unit tests","tdd","integration","methodology",{"skillNo":263,"name":264,"nameZh":6,"description":265,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":266,"categories":267,"keywords":268,"publishedAt":46},"01M71ER0XW3N4K7YTQSXXWW3M3","rust-patterns","Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.","https:\u002F\u002Fgithub.com\u002FViewWay\u002Fhermes-by-everythings\u002Fblob\u002Fmain\u002Fskills\u002Frust-patterns\u002FSKILL.md",[],[251,195,269,270,271,272,273,274,33,275,276,277,278],"rust patterns","error","traits","concurrency","safe","idiomatic","applications","best practices","error handling","ownership"]