Banner Creator

作者 resciencelabd22efdccbe39無授權條款收錄於 2026年10月8日更新於 2026年10月8日

Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, cover image, GitHub banner, Twitter header, or readme banner.

包含腳本Design & Creative
AI 產生的概覽

以 AI 產生多種橫幅圖片變體,依使用者回饋反覆調整,並裁切成各平台所需比例。

功能
此技能引導一套反覆迭代的橫幅設計流程:先蒐集用途、目標比例、風格、文字元素與顏色等需求,再以 21:9 寬幅比例產生大量 AI 圖片變體。它會建立 HTML 預覽頁面供比較候選圖,依使用者回饋調整偏好的方案,並將確認的圖片裁切成目標尺寸。最終素材會存到以日期命名的封存目錄。
適用情境
當使用者需要製作橫幅、頁首、主視覺圖、封面圖、GitHub 橫幅、Twitter 頁首或 README 橫幅時使用。適合需要先檢視多個視覺方案、再調整其中一個並裁切成平台尺寸的情境。
執行需求
需要設定 GEMINI_API_KEY 環境變數,並依賴 nanobanana 影像產生技能及其腳本。此技能內含可執行的 crop_banner.py 腳本與 HTML 預覽範本,影像產生需要網路連線。

Banner Creator Skill

Create professional banners through AI image generation with an iterative design process.

Prerequisites

Required API Keys (set in environment):

Required Skills:

  • nanobanana - AI image generation (Gemini 3 Pro Image)

File Output Location

All generated files should be saved to the .skill-archive directory:

.skill-archive/banner-creator/<yyyy-mm-dd-summaryname>/

Example:

.skill-archive/banner-creator/2026-01-19-opc-banner/  banner-01.png  banner-02.png  ...  banner-03-cropped.png  preview.html

Workflow

Step 1: Discovery & Requirements

Before generating, gather requirements from user:

Ask about:

  1. Purpose - Where will the banner be used?

    • GitHub README
    • Twitter/X header
    • LinkedIn banner
    • Website hero
    • YouTube channel art
  2. Target ratio/size - See references/formats.md:

    • 2:1 (1280x640) - GitHub README
    • 3:1 (1500x500) - Twitter header
    • 16:9 (1920x1080) - Website hero
  3. Style preference:

    • Match existing logo/brand?
    • Pixel art / 8-bit retro
    • Minimalist / flat design
    • Gradient / modern
    • Illustrated / artistic
  4. Content elements:

    • Brand name / project name?
    • Tagline / slogan?
    • Logo character to include?
  5. Color preferences:

    • Existing brand colors?
    • Let AI decide?

Wait for user confirmation before proceeding!

Step 2: Generate Banner Variations

Generate 20 banner variations using the nanobanana skill:

bash
# Generate single bannerpython3 <nanobanana_skill_dir>/scripts/generate.py "{style} banner for {brand}, {description}, {text elements}" \  --ratio 21:9 -o .skill-archive/banner-creator/<date-name>/banner-01.png
# Batch generate 20 bannerspython3 <nanobanana_skill_dir>/scripts/batch_generate.py "{style} banner for {brand}, {description}, {text elements}" \  -n 20 --ratio 21:9 -d .skill-archive/banner-creator/<date-name> -p banner

Guidelines:

  • Generate at 21:9 ratio (widest available), crop later to target
  • Use batch_generate.py for multiple variations (includes auto-delay)
  • Use sequential naming: banner-01.png, banner-02.png, etc.

Image Editing (for incorporating existing logo):

bash
python3 <nanobanana_skill_dir>/scripts/generate.py "add {logo character} to the left side of the banner" \  -i /path/to/existing-logo.png --ratio 21:9 -o banner-with-logo.png

Step 3: Create HTML Preview

Copy the preview template and open in browser:

bash
cp <skill_dir>/templates/preview.html .skill-archive/banner-creator/<yyyy-mm-dd-summaryname>/preview.html

Then open in default browser:

bash
open .skill-archive/banner-creator/<yyyy-mm-dd-summaryname>/preview.html

IMPORTANT: Update the HTML to include the correct number of banners generated.

Step 4: Iterate with User

Ask user which banners they prefer:

  • "Which banners do you like? (e.g., #3, #7, #15)"
  • "What do you like about them?"
  • "Any changes you'd want?"

Based on feedback:

  1. Generate 10-20 more variations of favorite styles
  2. Use naming: banner-{original}-v{n}.png (e.g., banner-03-v1.png)
  3. Update HTML preview
  4. Repeat until user selects final banner

Step 5: Crop to Target Ratio

Once user approves a banner, crop to target size:

bash
python3 <skill_dir>/scripts/crop_banner.py {input.png} {output.png} --ratio 2:1 --width 1280

Common targets:

  • GitHub README: --ratio 2:1 --width 1280 → 1280x640
  • Twitter header: --ratio 3:1 --width 1500 → 1500x500
  • Website hero: --ratio 16:9 --width 1920 → 1920x1080

Step 6: Deliver Final Assets

Present final deliverables:

## Final Banner Assets
| File | Description | Size ||------|-------------|------|| banner-03.png | Original (21:9) | 2016x864 || banner-03-cropped.png | GitHub README (2:1) | 1280x640 |
All files saved to: `.skill-archive/banner-creator/<yyyy-mm-dd-summaryname>/`Copy final banner to user's desired location.

Quick Reference

Common Prompt Patterns

With Text:

Wide banner for {brand}, {style} style, featuring "{text}" prominently displayed, {colors}, {scene/elements}

With Character:

Wide banner featuring {character description}, {style} style, {scene}, text "{brand name}" on {position}, {colors}

Abstract/Gradient:

Abstract {style} banner, {colors} gradient, geometric patterns, modern tech feel, text "{brand}" centered

Scene-based:

{Style} illustration banner, {scene description}, {character} in {action}, "{brand}" text overlay, {colors}

Supported Aspect Ratios

Generate at widest ratio, then crop:

  • 21:9 - Ultra-wide (recommended for generation)
  • 16:9 - Wide
  • 3:2 - Standard wide

References

  • references/formats.md - Common banner sizes by platform
  • examples/opc-banner-creation.md - Full example conversation

來源與署名

來源:resciencelab/opc-skills位於skills/banner-creator提交d22efdc

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架