$npx -y skills add nguyenphp/antigravity-marketing --skill banner-designDesign banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print.
| 1 | # Banner Design - Multi-Format Creative Banner System |
| 2 | |
| 3 | Design banners across social, ads, web, and print formats. Generates multiple art direction options per request with AI-powered visual elements. This skill handles banner design only. Does NOT handle video editing, full website design, or print production. |
| 4 | |
| 5 | ## When to Activate |
| 6 | |
| 7 | - User requests banner, cover, or header design |
| 8 | - Social media cover/header creation |
| 9 | - Ad banner or display ad design |
| 10 | - Website hero section visual design |
| 11 | - Event/print banner design |
| 12 | - Creative asset generation for campaigns |
| 13 | |
| 14 | ## Workflow |
| 15 | |
| 16 | ### Step 1: Gather Requirements (AskUserQuestion) |
| 17 | |
| 18 | Collect via AskUserQuestion: |
| 19 | 1. **Purpose** — social cover, ad banner, website hero, print, or creative asset? |
| 20 | 2. **Platform/size** — which platform or custom dimensions? |
| 21 | 3. **Content** — headline, subtext, CTA, logo placement? |
| 22 | 4. **Brand** — existing brand guidelines? (check `docs/brand-guidelines.md`) |
| 23 | 5. **Style preference** — any art direction? (show style options if unsure) |
| 24 | 6. **Quantity** — how many options to generate? (default: 3) |
| 25 | |
| 26 | ### Step 2: Research & Art Direction |
| 27 | |
| 28 | 1. Activate `ui-ux-pro-max` skill for design intelligence |
| 29 | 2. Use Chrome browser to research Pinterest for design references: |
| 30 | ``` |
| 31 | Navigate to pinterest.com → search "[purpose] banner design [style]" |
| 32 | Screenshot 3-5 reference pins for art direction inspiration |
| 33 | ``` |
| 34 | 3. Select 2-3 complementary art direction styles from references: |
| 35 | `references/banner-sizes-and-styles.md` |
| 36 | |
| 37 | ### Step 3: Design & Generate Options |
| 38 | |
| 39 | For each art direction option: |
| 40 | |
| 41 | 1. **Create HTML/CSS banner** using `frontend-design` skill |
| 42 | - Use exact platform dimensions from size reference |
| 43 | - Apply safe zone rules (critical content in central 70-80%) |
| 44 | - Max 2 typefaces, single CTA, 4.5:1 contrast ratio |
| 45 | - Inject brand context via `inject-brand-context.cjs` |
| 46 | |
| 47 | 2. **Generate visual elements** with `ai-artist` + `ai-multimodal` skills |
| 48 | |
| 49 | **a) Search prompt inspiration** (6000+ examples in ai-artist): |
| 50 | ```bash |
| 51 | python3 .claude/skills/ai-artist/scripts/search.py "<banner style keywords>" |
| 52 | ``` |
| 53 | |
| 54 | **b) Generate with Standard model** (fast, good for backgrounds/patterns): |
| 55 | ```bash |
| 56 | .claude/skills/.venv/bin/python3 .claude/skills/ai-multimodal/scripts/gemini_batch_process.py \ |
| 57 | --task generate --model gemini-2.5-flash-image \ |
| 58 | --prompt "<banner visual prompt>" --aspect-ratio <platform-ratio> \ |
| 59 | --size 2K --output assets/banners/ |
| 60 | ``` |
| 61 | |
| 62 | **c) Generate with Pro model** (4K, complex illustrations/hero visuals): |
| 63 | ```bash |
| 64 | .claude/skills/.venv/bin/python3 .claude/skills/ai-multimodal/scripts/gemini_batch_process.py \ |
| 65 | --task generate --model gemini-3-pro-image-preview \ |
| 66 | --prompt "<creative banner prompt>" --aspect-ratio <platform-ratio> \ |
| 67 | --size 4K --output assets/banners/ |
| 68 | ``` |
| 69 | |
| 70 | **When to use which model:** |
| 71 | | Use Case | Model | Quality | |
| 72 | |----------|-------|---------| |
| 73 | | Backgrounds, gradients, patterns | Standard (Flash) | 2K, fast | |
| 74 | | Hero illustrations, product shots | Pro | 4K, detailed | |
| 75 | | Photorealistic scenes, complex art | Pro | 4K, best quality | |
| 76 | | Quick iterations, A/B variants | Standard (Flash) | 2K, fast | |
| 77 | |
| 78 | **Aspect ratios:** `1:1`, `16:9`, `9:16`, `3:4`, `4:3`, `2:3`, `3:2` |
| 79 | Match to platform - e.g., Twitter header = `3:1` (use `3:2` closest), Instagram story = `9:16` |
| 80 | |
| 81 | **Pro model prompt tips** (see `ai-artist` references/nano-banana-pro-examples.md): |
| 82 | - Be descriptive: style, lighting, mood, composition, color palette |
| 83 | - Include art direction: "minimalist flat design", "cyberpunk neon", "editorial photography" |
| 84 | - Specify no-text: "no text, no letters, no words" (text overlaid in HTML step) |
| 85 | |
| 86 | 3. **Compose final banner** — overlay text, CTA, logo on generated visual in HTML/CSS |
| 87 | |
| 88 | ### Step 4: Export Banners to Images |
| 89 | |
| 90 | After designing HTML banners, export each to PNG using `chrome-devtools` skill: |
| 91 | |
| 92 | 1. **Serve HTML files** via local server (python http.server or similar) |
| 93 | 2. **Screenshot each banner** at exact platform dimensions: |
| 94 | ```bash |
| 95 | # Export banner to PNG at exact dimensions |
| 96 | node .claude/skills/chrome-devtools/scripts/screenshot.js \ |
| 97 | --url "http://localhost:8765/banner-01-minimalist.html" \ |
| 98 | --width 1500 --height 500 \ |
| 99 | --output "assets/banners/{campaign}/{variant}-{size}.png" |
| 100 | ``` |
| 101 | 3. **Auto-compress** |