rico-resource-article

Resource Recommendation Article Generator

This skill helps you create high-quality resource recommendation articles through a multi-turn interactive workflow, ensuring accurate content, complete structure, and professional style.

Core Features

• Intelligent Step-by-Step Generation: Collect candidates → User confirmation → Generate titles → Generate article
• Domain Adaptation: Auto-detect topic domain (Design/Development/Marketing/Product/Content) and apply professional terminology and writing style
• Broad Domain Support: Technical tools, design resources, development frameworks, online services, physical products, etc.
• Multiple Generation Modes: Smart step-by-step, one-shot, outline-based generation
• Professional Format Standards: Complete Front Matter and standard article structure
• Data Accuracy: Only use verifiable data (GitHub Stars, component counts, official metrics)

Triggers

This skill supports two trigger modes:

Mode 1: Explicit Command (rico article prefix)

• rico article [topic] / rico 文章 [主题]
• rico article 8 design tools / rico 文章 8个设计工具

Mode 2: Natural Language (explicit article intent required)

• "Generate a recommendation article about shadcn/ui"
• "写一篇工具推荐文章"
• "Create a resource list article"

Important: This skill ONLY triggers when user explicitly wants to generate an article. Do NOT trigger for simple questions like "recommend 8 tools" or "有哪些好用的工具" - answer directly.

Examples

Trigger examples:

• rico article 8 React hooks libraries
• rico 文章 10个设计工具
• Generate a recommendation article about shadcn/ui
• 写一篇 Figma 插件推荐文章

Do NOT trigger examples (just asking or conversing):

• "推荐 8 个组件库" - Answer directly
• "What are some good tools?" - Conversational inquiry
• "Generate 8 resources" - Unclear request without article intent
• "What plugins do you recommend?" - Question-only inquiry
• "生成 8 个资源" - 无明确文章生成意图的模糊请求
• "推荐几个好用的插件" - 单纯询问，不生成文章

---

🎯 Mode Selection and Priority

Default Mode: Intelligent Step-by-Step Generation

Mode Selection Priority:

1. User explicitly specifies mode → Use requested mode
2. User provides outline list → Use Outline-Based Generation
3. User only needs simple list → Use Quick Generation
4. Default fallback → Intelligent Step-by-Step Generation

When in doubt, always use Intelligent Step-by-Step Generation as it ensures highest quality through user confirmation.

---

🌟 Recommended Mode: Intelligent Step-by-Step Generation

This is the smartest, most controllable generation mode, ensuring article quality through multi-turn interaction.

Workflow

User inputs topic and quantity
  ↓
Step 0: Domain Detection (Auto-detect topic domain)
  ↓
Step 1: Collect candidate items (URL + recommendation reason + differentiating features + verifiable data)
  ↓
User confirms candidate list
  ↓
Step 2: Generate 6 title options (pain-point, exploratory, recommendation)
  ↓
User selects title
  ↓
Step 3: Generate complete article with domain-specific writing style
  ↓
Step 4: Ask about screenshots (Optional - ALWAYS ask after article generation)

Step 0: Domain Detection

Auto-detect the topic domain and apply corresponding writing template

Detection Rules

Domain	Keywords (EN/CN)	Target Audience	Focus Areas
Design	Figma, Sketch, UI, UX, design system, component, mockup, prototype, 插件, 设计, 组件库, 设计系统	Designers	创意效率, 视觉质量, 设计规范, Design System, 交付流程
Development	React, Vue, Angular, API, framework, library, TypeScript, npm, 框架, 库, 开发	Developers	技术栈, 性能优化, 代码质量, GitHub Stars, 社区生态
Marketing	SEO, ROI, conversion, A/B test, analytics, email marketing, 转化率, 营销, 分析	Marketers	ROI, 数据驱动, 转化效果, 受众分群, 自动化
Product	Prototype, user research, roadmap, collaboration, 原型, 用户调研, 路线图	Product Managers	功能完整性, 团队协作, 用户价值, 决策支持
Content	Writing, CMS, publishing, editing, 写作, 编辑, 发布	Content Creators	创作效率, 内容质量, 分发渠道, AI 辅助
General	fallback	General Users	易用性, 功能全面, 实用性

Detection Process

1. Extract keywords from user topic
2. Match against domain keyword library
3. Calculate confidence score based on keyword matches
4. If confidence ≥80%: Auto-select domain and inform user
5. If confidence 50-79%: Ask user to confirm
6. If confidence <50%: Use General template

Example Interaction

High Confidence (Auto-select):

### User Input
"生成一篇 Figma 插件推荐文章，推荐 6 个"

### AI Response
🔍 **检测到领域: Design (设计领域)**

基于关键词 "Figma" + "插件"，将使用设计领域专业模板，侧重：
- ✅ 设计工作流集成
- ✅ 创意效率提升
- ✅ Design System 兼容性

[继续执行 Step 1: 收集候选项目...]

Medium Confidence (Ask User):

### User Input
"生成一篇图片压缩工具推荐文章"

### AI Response
🤔 **检测到多个可能的领域方向**

"图片压缩工具" 可以是：
- A. 面向设计师（设计工作流、批量处理、保持质量）
- B. 面向开发者（API 集成、自动化处理、性能优化）

请问您希望侧重哪个方向？(回复 A 或 B，或直接跳过使用通用模板)

---

Step 1: Collect Candidate Items

Based on user's topic requirements, collect matching projects/websites/tools and list them in the following format:

Candidate List Format:

**1. [Project Name]**
- URL: {{website link}}
- Recommendation reason: {{2-3 sentences explaining why it's worth recommending}}
- Differentiating features: {{How it differs from similar projects}}
- Data: {{Verifiable metrics - GitHub Stars, component counts, official numbers}}

**2. [Project Name]**
...

⚠️ DATA ACCURACY RULES (CRITICAL):

1. Only Use Verifiable Data

• ✅ USE: GitHub Stars, GitHub Forks, NPM weekly downloads, Component/Template counts (from official site)
• ✅ USE: Contributor count, Last updated date, License type, Tech stack details
• ❌ DON'T USE: User counts, Customer numbers, Efficiency percentages, Fake metrics
• ❌ DON'T USE: "100万+ 用户", "效率提升 10 倍", "转化率提升 25%" (unless officially verified)

2. How to Collect Data

• Visit GitHub page → Get Stars, Forks, Contributors, Last Updated
• Visit official site → Get component/template counts, feature lists
• Visit NPM page → Get weekly/monthly download counts
• If unsure about data → Either omit or mark as "approximate"

⚠️ CRITICAL RULES (MUST FOLLOW):

1. NEVER Hallucinate Projects or URLs

• ❌ DO NOT invent or fabricate project names, URLs, or websites
• ❌ DO NOT create fake resources or fictional tools
• ✅ ONLY recommend real, verifiable projects that actually exist
• ✅ If unsure about a project's existence, either skip it or ask the user

2. Verify URLs Before Listing

• ✅ Ensure URLs are accessible and valid
• ✅ If a URL seems suspicious or broken, note it for user verification
• ❌ DO NOT include projects with broken or dubious URLs

Important: If you encounter these situations, ask the user first:

• Topic direction is unclear
• Insufficient candidate items (inform how many you found)
• Multiple related sub-topics discovered, need to confirm focus
• Certain project URLs need verification
• Unable to find enough real, verifiable candidates (tell user and ask for guidance)

After listing candidates, ALWAYS wait for user confirmation, tell the user:

Above are {{number}} candidate items. Please confirm:
1. Do you need to adjust any items?
2. Do you need to add or remove any items?
3. Reply 'y' or 'yes' to confirm and proceed

Step 2: Generate Title Options

After user confirms the candidate list, generate 6 article titles in different styles based on these items:

### Please select your preferred title style:

**A. Pain-Point Type**
- A1. {{title}}
- A2. {{title}}

**B. Exploratory Type**
- B1. {{title}}
- B2. {{title}}

**C. Recommendation Type**
- C1. {{title}}
- C2. {{title}}

Please tell me which title you choose (e.g., A1), or suggest modifications.

Title Style References:

• Pain-Point Type: Say no to homogenization!, Break through bottlenecks!, Farewell to XXX
• Exploratory Type: Inspiration exploration!, In-depth analysis!, XXX exploration
• Recommendation Type: Curated, Essential, Must-know, Make XXX, XXX essentials

Step 3: Generate Complete Article

After user selects a title, generate the complete article.

First, determine the article folder path:

1. Translate the Chinese title to a descriptive English slug
2. Use lowercase, hyphen-separated format
3. Inform the user: "Article will be saved to: {{article-slug}}/index.md"
4. If using screenshots, they will be saved in the same folder

Example:

Title: 精选 4 款最受欢迎的渐变生成器，每个设计师都值得收藏
Slug: featured-4-most-popular-gradient-generators
Path: featured-4-most-popular-gradient-generators/index.md

Then proceed with generating the article content.

Article Structure Standards

File Organization

Article files should follow this structure:

{{article-slug}}/
└── index.md          # Article content
├── screenshot-1.png   # Screenshots (if any)
├── screenshot-2.png
└── ...

Path Explanation:

• Articles are saved in current working directory
• Folder name: {{article-slug}}/ (e.g., featured-4-most-popular-gradient-generators/)
• Article file: always index.md
• Screenshots: saved in the same folder as article

Cover Image Location (separate from article folder):

assets/blog/
└── cover-{{article-slug}}.jpg  # Manually added cover images

Naming rules:

• Article folder: lowercase English, hyphen-separated, descriptive and concise
  • Example: shadcn-ui-component-libraries/, featured-4-most-popular-gradient-generators/
  • Rule: Translate Chinese title to English, use lowercase, connect with hyphens
  • Format: [adjective]-[number]-[category]-[items] or similar descriptive pattern
  • Examples:
    • "精选 4 款最受欢迎的渐变生成器" → featured-4-most-popular-gradient-generators/
    • "设计师必备的 8 个 Figma 插件" → essential-8-figma-plugins-for-designers/
    • "2026 年最佳 Vue 组件库" → best-vue-component-libraries-2026/
• File: always index.md
• Screenshots: saved in same folder as article, named after project (e.g., cssgradient-io.png)

1. Front Matter (Metadata)

---
title: {{user selected title}}
publishDate: {{today's date: YYYY-MM-DD}}
read: {{estimated reading time in minutes, typically 6-12}}
description: {{English subtitle, concise summary for SEO}}
tags:
  - {{English tag1}}
  - {{English tag2}}
  - {{Chinese tag1}}
  - {{Chinese tag2}}
img: "/assets/blog/cover-{{article-slug}}.jpg"
img_alt: "{{Chinese description of cover image}}"
---

Important Notes:

• img and img_alt are manually added cover images (not auto-generated)
• Image path should follow pattern: /assets/blog/cover-{{article-slug}}.jpg
• description should be in English, concise and SEO-friendly
• read is estimated reading time in minutes
• tags should include both Chinese and English keywords (4-6 items total)

2. Opening Paragraphs (3-4 paragraphs)

• Paragraph 1: Present industry background and current status
• Paragraph 2: Explain core value and significance of the topic
• Paragraph 3: Introduce the content to be recommended in the article
• Paragraph 4 (optional): Explain why these resources are being recommended

3. Body Content

Write content for each confirmed item in the following format:

### {{number}}. {{Project Name}}

- **官网**: [{{URL}}]({{URL}})
- **简介**: {{Core positioning, main functions, problems solved}}, covering {{specific content scope}}, {{special features/characteristics}}.
- **优势**: {{Why it's worth recommending, unique value, applicable scenarios, problems solved}}.

Body Requirements:

• Number of recommended items: As requested by user, typically 6-12
• Arrange in logical order (from basic to advanced, or from general to specialized)
• Description should explain core positioning and main content scope
• Advantages should highlight differentiated value and applicable scenarios
• Language should be professional but accessible, target reader appropriate

Aggregation Platforms (if applicable):

If there are aggregation platforms, list them separately:

Additionally, here are {{number}} aggregation platforms that collect {{platform purpose}}:

### {{number}}. {{Project Name}}
...

4. Conclusion (2 parts)

• Subheading (## level-2 heading): Should elevate the theme, not too generic

  • Example: ## Vibe Coding: Returning Design to "Creation" Itself
  • Or: ## Componentized Inspiration: Focusing Creativity on the Core

• Summary paragraphs (3-4 paragraphs):

  • Explain the overall value of these resources
  • Connect with current trends (e.g., AI assistance, automation)
  • Provide usage recommendations
  • Encourage reader action

Do not add author byline.

---

Step 4: Ask About Screenshots (ALWAYS ask after article generation)

After article generation is complete, ALWAYS ask the user:

✅ Article generated successfully! Saved to: `{{article-slug}}/index.md`

📸 Would you like to add screenshots for the recommended websites?

Quick Options:
- Type "n" or "no" - Skip screenshots
- Type "y" or "yes" - Use default service (ScreenshotOne)
- Type "u" or "urlscan" - Use urlscan.io (requires API key)

Default size: 1600×900 (16:9) - Best for blog articles

If user says "no" or "n": Skip and end the workflow.

If user says "yes" or "y": Proceed to screenshot process (see 📸 Optional: Add Screenshots section below).

If user wants custom size: Accept and proceed with specified dimensions.

---

📌 Other Generation Modes

Mode 1: One-Shot Generation

For scenarios where user knows exactly what they want and doesn't need multiple confirmations.

Workflow:

1. Understand user's topic
2. Collect candidate items directly
3. Generate one attention-grabbing title
4. Generate complete article

Article Format: Same as above (Front Matter + intro + body + conclusion)

Mode 2: Outline-Based Generation

For scenarios where user has already provided a candidate list.

Workflow:

1. Read the outline provided by user
2. Write description and advantages for each item
3. Generate title
4. Generate complete article

Additional Handling:

• If outline includes category tags (e.g., 3D, Animated, Minimal), reflect them in the "Advantages" section of corresponding items
• If outline includes URLs, verify link validity
• Adjust item count based on outline content

Mode 3: Quick Generation

Generate only the recommendation list, without intro, conclusion, or Front Matter.

### {{number}}. {{Project Name}}

- **官网**: [{{URL}}]({{URL}})
- **简介**: {{1-2 sentences}}
- **优势**: {{1-2 sentences}}

Note: Images are not included in quick generation mode. Users can manually add screenshots if needed.

---

Writing Style Requirements

1. Professional: Accurate terminology, clear logic
2. Practical: Each recommendation has clear use cases and value points
3. Readable: Moderate paragraph length, avoid lengthy discourse
4. Natural: Avoid common AI writing issues (excessive parallelism, vague descriptions, three-part rule, negative parallelism, vague attribution)
5. Original: Avoid copying official introductions, rephrase in your own words

Avoid Common AI Writing Issues

Issue 1: Excessive Parallelism

• ❌ "It has efficiency, flexibility, and scalability."
• ✅ "It's efficient and flexible, with easy scalability."

Issue 2: Vague Descriptions

• ❌ "This component library is very powerful and feature-rich."
• ✅ "Contains 200+ components, covering forms, data display, navigation, and other scenarios."

Issue 3: Three-Part Rule

• ❌ "Not only... but also... and..." / "Whether... or... all..."
• ✅ Use natural, varied sentence structures

Issue 4: Negative Parallelism

• ❌ "It doesn't need complex configuration, additional dependencies, or learning curve."
• ✅ "Simple configuration, zero dependencies, fast to get started."

Issue 5: Vague Attribution

• ❌ "Many people believe..." / "It is well known that..."
• ✅ Directly state opinions or provide specific data sources

---

Special Notes

Content Guidelines

• Tags should include Chinese and English keywords, 4-6 items
• URLs must be accurate and clickable
• Avoid exaggerated promotion, maintain objectivity and professionalism
• Do not add author byline
• Images are optional - users can manually add screenshots to the generated article if needed

⚠️ Safety and Compliance Rules (CRITICAL)

1. Prohibited Content

• ❌ DO NOT recommend pirated, cracked, or illegal software/resources
• ❌ DO NOT promote copyright-infringing content
• ❌ DO NOT recommend resources that violate terms of service
• ❌ DO NOT include adult content, gambling, or illegal activities
• ✅ ONLY recommend legitimate, legal, and ethical resources

2. Accuracy Requirements

• ❌ DO NOT hallucinate or fabricate projects, URLs, or websites
• ❌ DO NOT create fictional resources or tools
• ✅ ONLY recommend real, verifiable projects
• ✅ If insufficient real candidates exist, inform the user and ask for guidance

3. Verification

• ✅ Verify that recommended resources actually exist
• ✅ Ensure URLs are accessible and safe
• ❌ DO NOT include suspicious or broken URLs without warning the user

4. Disclosure

• ✅ If you're uncertain about a resource's legitimacy, note it
• ✅ If knowledge base has no matching content, tell user honestly
• ❌ DO NOT make up recommendations to satisfy the request

---

Mode Selection Guide

User Need	Recommended Mode	Reason
"Recommend X items... and generate an article"	Intelligent Step-by-Step	Let user participate in confirmation, highest quality
"Generate a recommendation article about XXX"	Intelligent Step-by-Step	Multi-turn interaction ensures accuracy
Provided an outline list	Outline-Based Generation	Quick completion, user confirmed content
Only need recommendation list	Quick Generation	Concise and efficient
Clear topic and quantity	One-Shot Generation	Fast output

---

Complete Example

User Input:

"Write a recommendation article about shadcn/ui component libraries, recommend 8"

AI Step 1: Collect Candidate Items

Here are 8 collected shadcn/ui component libraries:

**1. [Aceternity UI]**
- URL: https://ui.aceternity.com/
- Recommendation reason: Hottest component library in shadcn/ui ecosystem, 120k+ developers using it
- Differentiating features: Deeply integrated with Framer Motion, extensive visual effects components

**2. [Kibo UI]**
- URL: https://www.kibo-ui.com/
- Recommendation reason: Fills gaps in shadcn/ui's advanced components
- Differentiating features: Provides color picker, rich text editor and other advanced components

...

Above are 8 candidate items. Please confirm:
1. Do you need to adjust any items?
2. Do you need to add or remove any items?
3. Reply 'y' or 'yes' to confirm and proceed

User: y

AI Step 2: Generate Title Options

### Please select your preferred title style:

**A. Pain-Point Type**
- A1. Say No to Homogenization! 8 Curated Shadcn/UI Component Libraries
- A2. Break Through Design Bottlenecks! 8 Must-Try Shadcn/UI Extension Libraries

**B. Exploratory Type**
- B1. Inspiration Exploration! 8 Shadcn/UI-Focused Component Libraries
- B2. In-Depth Analysis: 8 Efficiency-Boosting Shadcn/UI Resources

**C. Recommendation Type**
- C1. 8 Shadcn/UI Component Libraries to Double Development Efficiency
- C2. Developer Essentials: 8 Quality Shadcn/UI Extension Libraries

Please tell me which title you choose (e.g., A1), or suggest modifications.

User: A1

AI Step 3: Generate Complete Article

File structure:

content/shadcn-ui-component-libraries/
└── index.md

Content:

---
title: Say No to Homogenization! 8 Curated Shadcn/UI Component Libraries
publishDate: 2026-03-03
read: 8
description: Top 8 Awesome Shadcn UI Component Libraries
tags:
  - Shadcn UI
  - Component Libraries
  - UI组件库
  - 组件库推荐
img: "./cover-shadcn-ui.jpg"
img_alt: "8 Curated Shadcn/UI Component Libraries"
---

shadcn/ui is one of the hottest component systems today...

### 1. Aceternity UI

- **官网**: [https://ui.aceternity.com/](https://ui.aceternity.com/)
- **简介**: Hottest component library in shadcn/ui ecosystem with 120k+ developers, covering 200+ production-quality components...
- **优势**: Deeply integrated with Framer Motion and Tailwind CSS, providing glow cards, text gradients, 3D globe and other unique visual components...

...

---

📸 Optional: Add Screenshots

After article generation, offer users the option to add screenshots for recommended websites.

When to Ask

Ask after article generation is complete:

✅ Article generated successfully!

Would you like to add screenshots for the recommended websites?

Quick Options:
- Type "n" or "no" - Skip screenshots
- Type "y" or "yes" - Use default service (ScreenshotOne)
- Type "u" or "urlscan" - Use urlscan.io (requires API key)

Current default: ScreenshotOne (JPG format, smaller file size)
Default size: 1600×900 (16:9) - 适合博客文章

💡 **自定义截图尺寸 / Customize Screenshot Size:**
   Just mention it when requesting / 在请求时直接说明:
   - "Use 1920×1080" / "用 1920×1080 截图"
   - "Screenshot at 1440×900" / "截图尺寸 1440×900"

Service Selection

If user chooses "yes" (uses default) or selects a specific service:

If user selected "yes" (default service):

Using default service: ScreenshotOne

✓ Fast (2-5 seconds per screenshot)
✓ 100 free screenshots/month
✗ Requires API key

If user wants to compare services:

Available screenshot services:

【ScreenshotOne】
✓ Fast (2-5 seconds)
✓ 100 free screenshots/month
✗ Requires API key

【urlscan.io】
✓ Free: 5,000 Public Scans/day
✓ Free: 1,000 Unlisted Scans/day  
✓ Free: 50 Private Scans/day
✗ Requires API key
✗ Slower than ScreenshotOne

Default: ScreenshotOne (configured in .env)

Configuration Check

IMPORTANT: Always check .env file first before asking user

Step 1: Check if .env file exists and has API key

Check order:
1. .rico-skills/.env (project-level)
2. ~/.rico-skills/.env (user-level)

If API key found → Use it directly ✓
If not found → Go to Step 2

Step 2: If no API key configured

Checking ScreenshotOne configuration...

⚠️ API Key not found in .env file

Get your free API key:
1. Visit: https://screenshotone.com/
2. Sign up (free, 2 minutes)
3. Copy your API Key

Choose how to configure:

[A] 💾 Create .env file (Recommended) - Key will be saved for future use
[B] 🔑 Enter API key now (One-time) - Key will only be used for this session
[C] ⏭️ Skip screenshots - Add manually later

Please reply A, B, or C:

If user selects [A] - Create .env file:

Great! I'll create the .env file for you.

Please enter your API Key: [wait for user input]

✓ Creating .rico-skills/.env file...
✓ Saving API key...
✓ Configuration complete! Key saved for future use.

Now proceeding with screenshots...

If user selects [B] - One-time use:

Please enter your API Key (will be used for this session only): [wait for user input]

✓ Key received. Proceeding with screenshots...
(Note: You'll need to enter the key again next time)

If user selects [C] - Skip:

✓ Skipping screenshots. You can add them manually later.

Manual screenshot guide:
- Save screenshots to: say-goodbye-to-stock-photos-3-ai-image-generators/
- Recommended size: 1600×900 (16:9)
- Naming: {website-name}.png

For urlscan.io (same flow):

Checking urlscan.io configuration...

⚠️ API Key not found in .env file

Get your free API key:
1. Visit: https://urlscan.io/user/ (login required)
2. Go to Settings → API Keys
3. Copy your API Key

Choose how to configure:

[A] 💾 Create .env file (Recommended) - Save for future use
[B] 🔑 Enter API key now (One-time) - Use for this session only
[C] ⏭️ Skip screenshots - Add manually later

Please reply A, B, or C:

After saving to .env, show confirmation:

✓ API key saved to .rico-skills/.env

Your configuration:
- Service: ScreenshotOne
- API Key: sk_•••••••••••••••• (hidden)
- Default size: 1600×900

This key will be automatically used for future screenshot requests.

Screenshot Dimensions

Default Screenshot Size: 1600×900 (16:9)

This is the optimal size for most blog and article layouts, providing:

• Clear visibility of website details
• Good aspect ratio for responsive design
• Reasonable file size for web loading

Customize Screenshot Size:

If you need different dimensions, specify when requesting screenshots:

Example requests:
- "使用 1920×1080 尺寸截图"
- "用 1440×900 截图"
- "截图尺寸设为 1200×800"
- "Take screenshots at 1920×1080"

Available Sizes:

Size	Aspect Ratio	Best For
1920×1080	16:9	Full HD displays
1600×900	16:9	Default - Blog posts
1440×900	16:10	Mac-style displays
1200×800	3:2	Tablets, smaller screens
1200×600	2:1	Wide banners
1200×900	4:3	Traditional displays

Note: urlscan.io has limited size options (typically 1920×1080 or similar). For custom sizes, use ScreenshotOne or manual screenshot tools.

Screenshot Process

Once configured:

For ScreenshotOne:

Found 8 URLs to screenshot

[1/8] Capturing https://ui.aceternity.com/...
  Waiting for screenshot...
✓ aceternity-ui.png (2.3s)

[2/8] Capturing https://www.kibo-ui.com/...
✓ kibo-ui.png (1.8s)

...

✓ Screenshots completed: 8/8
Saved to: ./ (current directory)

For urlscan.io:

Found 8 URLs to screenshot

[1/8] Submitting scan for https://ui.aceternity.com/...
  Scan UUID: abc123-def456-ghi789
  Waiting for scan to complete...
  Downloading screenshot...
✓ aceternity-ui.png (8.2s)

[2/8] Submitting scan for https://www.kibo-ui.com/...
  Scan UUID: xyz789-uvw456-rst123
  Waiting for scan to complete...
  Downloading screenshot...
✓ kibo-ui.png (7.5s)

...

✓ Screenshots completed: 8/8
Saved to: ./ (current directory)

Update Article with Screenshots

After screenshots are saved, ALWAYS update the article to include images.

For each recommended item, insert the screenshot image after the heading:

Before (without screenshot):

### 1. Aceternity UI

- **官网**: [https://ui.aceternity.com/](https://ui.aceternity.com/)
- **简介**: ...

After (with screenshot):

### 1. Aceternity UI

![Aceternity UI](aceternity-ui.jpg)

- **官网**: [https://ui.aceternity.com/](https://ui.aceternity.com/)
- **简介**: ...

Image insertion rules:

1. Insert image immediately after the item heading (### N. Project Name)
2. Use format: ![Project Name](filename.jpg)
3. Alt text should be the project name or brief description
4. Image files should be in the same directory as index.md

After updating the article, show confirmation:

✓ Article updated with 3 screenshots

Updated sections:
- Section 1: meshgradients-com.jpg
- Section 2: csshero-mesher.jpg
- Section 3: nicepkg-mesh-gradient.jpg

Screenshot File Naming

Screenshots are saved in the same directory as the article:

shadcn-ui-component-libraries/
├── index.md              # Article content
├── aceternity-ui.png     # Screenshot 1
├── kibo-ui.png           # Screenshot 2
├── ...
└── footer-design.png     # Screenshot 8

Naming rule: {project-name}.png

• Extracted from domain or project name
• Lowercase, hyphen-separated
• Example: aceternity-ui.png, kibo-ui.png

Error Handling

If screenshots fail:

⚠️ Some screenshots failed:
- kibo-ui.png: Timeout (30s)
- footer-design.png: API rate limit

✓ Successful: 6/8
❌ Failed: 2/8

You can manually add these screenshots later if needed.

Manual Screenshot Guide

If users prefer manual screenshots or hit API limits:

## Manual Screenshot Guide

### System Tools
- Mac: Cmd+Shift+4 (select area)
- Windows: Win+Shift+S (select area)

### Online Tools
- Screenshot.guru: https://screenshot.guru/
- Screenshot.rocks: https://screenshot.rocks/

### Recommended Dimensions
- Default: 16:9 (1600×900)
- Alternatives: 16:10, 3:2, 2:1, 4:3

### File Organization
Save screenshots in the same directory as the article:
- Article: `content/shadcn-ui-component-libraries/index.md`
- Screenshots: `content/shadcn-ui-component-libraries/*.png`

This keeps related files together and makes management easier.