logo-generator
Generate professional SVG logos and high-end showcase images. Use when the user wants to: (1) Create a logo or icon for their product/brand, (2) Generate logo design concepts based on product information, (3) Create professional logo showcase presentations with multiple background styles, (4) Export logos in various formats (SVG, PNG), or (5) Iterate on logo designs with different visual styles. Supports geometric patterns, dot matrix designs, line systems, and mixed compositions. Generates showcase images using Nano Banana (Gemini image generation) with 12 professional background styles.
- License 许可
- MIT
- 最近更新
- 2026-11-01
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- name
- logo-generator
- description
- Generate professional SVG logos and high-end showcase images. Use when the user wants to: (1) Create a logo or icon for their product/brand, (2) Generate logo design concepts based on product information, (3) Create professional logo showcase presentations with multiple background styles, (4) Export logos in various formats (SVG, PNG), or (5) Iterate on logo designs with different visual styles. Supports geometric patterns, dot matrix designs, line systems, and mixed compositions. Generates showcase images using Nano Banana (Gemini image generation) with 12 professional background styles.
02 资源文件 10
- 其他.gitignore133 B
- 资产文件assets/background_library.html29.2 KB
- 资产文件assets/showcase_template.html7.1 KB
- 参考文档README.md14.0 KB
- 参考文档references/background_styles.md9.2 KB
- 参考文档references/design_patterns.md28.1 KB
- 参考文档references/webgl_backgrounds.md4.7 KB
- 参考文档requirements.txt72 B
- 脚本scripts/generate_showcase.py12.3 KB
- 脚本scripts/svg_to_png.py1.8 KB
03 SKILL.md 正文
Logo Generator
Generate professional SVG logos and high-end showcase presentations for products and brands.
Workflow
Phase 1: Information Gathering
Collect essential information from the user:
- Product/Brand Name (required)
- Industry/Category (e.g., AI, fintech, design tools)
- Core Concept (e.g., connection, flow, security, simplicity)
- Design Preferences:
- Style: minimal/complex, geometric/organic
- Color preference: monochrome/specific colors
- Mood: cold/warm, professional/friendly
Ask concise questions to gather this information. Don't overwhelm the user with too many questions at once.
Phase 2: Pattern Matching & SVG Generation
Based on the gathered information:
-
Generate at least 6 design variants based on
references/design_patterns.md- Match patterns to product characteristics
- Use different pattern types and combinations for diversity
- Include both single-pattern and mixed-pattern compositions
- Vary complexity levels (simple geometric to layered compositions)
- Each variant should feel distinctly different, not just parameter tweaks
- Explain the design rationale for each variant
-
Generate SVG code for each variant
- Use viewBox="0 0 100 100" for easy scaling
- Keep code clean and well-structured
- Use
currentColorfor flexible color control - Add subtle animations for web display (optional)
-
Create interactive showcase webpage
- Display all 6+ logo variants in a grid layout
- Use the template from
assets/showcase_template.html - Include hover effects and smooth transitions
- Add design rationale for each variant
- Allow easy comparison between variants
Phase 3: Iteration & Refinement
Allow user to provide feedback:
- Select favorite variants (narrow down from 6+ to 2-3)
- Adjust specific parameters (size, spacing, rotation)
- Combine elements from different variants
- Change colors or add gradients
- Modify animations or effects
- Generate additional variants exploring specific directions
Make targeted adjustments based on feedback. Don't regenerate everything unless requested.
Phase 4: High-End Showcase Generation
Once the user selects a preferred logo direction:
-
Export SVG to PNG
- Use
scripts/svg_to_png.pyto convert SVG to PNG - Default size: 1024x1024px
- Ensure transparent background
- Use
-
Select showcase styles
- Review
references/background_styles.md - Recommend 4 styles based on product type and mood
- Explain why each style fits
- Review
-
Generate showcase images
- Set up environment (copy
.env.exampleto.env, add API key) - Use
scripts/generate_showcase.pywith--all-stylesflag - Or generate specific styles individually
- Each image uses the PNG as reference with Nano Banana API
- Set up environment (copy
-
Create final presentation webpage
- Combine SVG variants and showcase images
- Use professional layout with micro-typography
- Include download links for all assets
Phase 5: Delivery
Provide the user with:
- Interactive HTML showcase page
- SVG files (editable vector format)
- PNG exports (various sizes if requested)
- Showcase images (4 professional backgrounds)
Key Design Principles
- Provide Variety: Generate at least 6 distinct variants to give users real choices
- Start Simple: Begin with basic patterns, add complexity only when needed
- Meaningful Design: Connect visual elements to product concepts
- Scalability: Ensure logos work at all sizes
- Professional Quality: Match high-end brand identity standards
- Flexibility: Provide multiple variants for different use cases
Technical Notes
SVG Best Practices
- Keep viewBox at
0 0 100 100for consistency - Use semantic grouping with
<g>tags - Leverage
<defs>for reusable elements - Use
<clipPath>for masking effects - Prefer geometric primitives over complex paths when possible
Showcase Image Generation
The generate_showcase.py script requires:
- Python 3.8+
- Dependencies:
pip install -r requirements.txt - Environment variables in
.envfile - Reference PNG image (exported from SVG)
Supports both official Google Gemini API and third-party endpoints via GEMINI_API_BASE_URL.
Available Background Styles
From references/background_styles.md:
12 Professional Styles Available:
Dark Styles (6):
- void (绝对虚空) - Absolute minimalism, hardcore tech
- frosted (磨砂穹顶) - Modern breathing space, premium products
- fluid (流体深渊) - AI-native fluidity, dynamic systems
- spotlight (物理影棚) - Studio lighting, editorial quality
- analog_liquid (物理流体) - Metallic shimmer on solid color base, creative brands
- led_matrix (数字硬件) - Digital retro, cyberpunk aesthetics
Light Styles (6):
- editorial (纸本编辑) - Specialty paper, humanistic brands
- iridescent (幻彩透砂) - Optical materials, tech hardware
- morning (晨雾光域) - AI softness, approachable products
- clinical (无菌影棚) - Spatial order, algorithm-driven brands
- ui_container (容器化界面) - Digital product native, SaaS platforms
- swiss_flat (瑞士扁平) - Absolute flatness, timeless authority
Each style has specific visual characteristics and suitable use cases. Consult the reference document for details.
Common Patterns
Pattern: Concentric Circle Dots
<svg viewBox="0 0 100 100">
<g>
<!-- Inner ring: 6 dots -->
<circle cx="50" cy="38" r="3" fill="currentColor"/>
<!-- Add more dots in circular arrangement -->
</g>
</svg>
Pattern: Geometric Shape with Line Accent
<svg viewBox="0 0 100 100">
<polygon points="50,30 70,60 30,60" fill="none" stroke="currentColor" stroke-width="2"/>
<circle cx="50" cy="30" r="4" fill="currentColor"/>
</svg>
Pattern: Node Network
<svg viewBox="0 0 100 100">
<path d="M 30 70 Q 50 70, 50 50 T 70 30" stroke="currentColor" stroke-width="2" fill="none"/>
<circle cx="30" cy="70" r="4" fill="currentColor"/>
<circle cx="50" cy="50" r="5" fill="currentColor"/>
<circle cx="70" cy="30" r="4" fill="currentColor"/>
</svg>
For more patterns and combinations, see references/design_patterns.md.
Troubleshooting
SVG not displaying correctly: Check viewBox and ensure all paths are closed
PNG export fails: Verify cairosvg is installed (pip install cairosvg)
Showcase generation fails:
- Check
.envfile has validGEMINI_API_KEY - Verify reference PNG exists and is readable
- Check API quota/rate limits
Third-party API not working: Ensure GEMINI_API_BASE_URL is correctly formatted (e.g., https://api.example.com/v1)
04 同仓库更多 Skills
seedance-prompt-en
Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.
onepage-pdf
Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds and selectable text. Use when the user asks to turn an HTML file/report/proposal into a "single-page PDF", "long PDF", "不分页 PDF", "单页 PDF", "长图式 PDF", or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.
native-feel-cross-platform-desktop
Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include "cross-platform desktop", "Electron alternative", "Tauri vs native", "WebView wrapper", "near-native performance", "Raycast architecture", "WebKit/WebView2 quirks", "WKWebView", "system tray app", "global hotkey app", "launcher app". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.
gstack
Router for the gstack skill suite. (gstack)
fireworks-tech-graph
Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG. Trigger on: "画图" "帮我画" "生成图" "做个图" "架构图" "流程图" "可视化一下" "出图" "generate diagram" "draw diagram" "visualize" or any system/flow description the user wants illustrated.
dbs-video-extract
接收抖音、小红书、微信视频号等短视频链接或分享文案,查询作品/账号数据并提取语音文字稿,按作者和标题归档为 Markdown。用户希望完整解析短视频、取得数据或文字稿时使用;运行前检查 TikHub 与轻抖使用凭证,缺少时用新手能理解的方式引导购买和安全配置。