docs: Clarify image processing rules in PDF conversion prompt

Refine the image processing instructions within the PDF conversion prompt to emphasize the critical importance of matching image descriptions to their exact filenames.

The previous instructions were ambiguous and could lead to incorrect image descriptions. This update adds:
- A "Critical" warning to match image names correctly.
- Detailed rules outlining how to process image references based on provided filenames.
- An example workflow to illustrate the correct matching process.
- A new "Critical" verification step in the final instructions to ensure image explanations correspond to their filenames.

This change aims to prevent errors where image descriptions might be mismatched or generated from the wrong image content, ensuring higher accuracy in the conversion process.

pdf_convertor_prompt.md

@@ -8,22 +8,36 @@ Examine the Markdown text and remove any conversion artifacts or strange formatt
 
 ## 2. Explain Image Content
 
-For image references that **already exist** in the original Markdown (format: `![...](...)`), refer to the corresponding charts, diagrams, and images in the PDF, and add detailed descriptions after each image reference.
+**Critical: Match image names to image content correctly**
+
+You will receive:
+
+- Original Markdown text with image references (e.g., `![Image](images/0.png)`)
+- Individual images labeled with their exact filenames (e.g., "This is image: 'images/0.png'")
+- The original PDF for reference
 
 **Processing rules:**
 
-- Only process existing image references - never create new ones
-- Keep the image path (inside parentheses) completely unchanged
-- You may modify the description text (inside square brackets) to be more descriptive
-- If images exist in the PDF but have no corresponding Markdown reference, ignore them
-- Add a blank line after the image reference for proper formatting
+- For each image reference in the Markdown (e.g., `![Image](images/0.png)`), find the EXACT matching image that was provided with that specific filename
+- ONLY describe the content of the image that matches the filename in the Markdown reference
+- DO NOT use images from the PDF to describe a different numbered image reference
+- If the Markdown shows `![Image](images/0.png)`, you MUST describe ONLY the image labeled "This is image: 'images/0.png'" or "This is image: '0.png'"
+- Keep image paths unchanged - only modify the description text in square brackets if needed
+- Add a detailed explanation after each image reference
+
+Example workflow:
+
+1. You see in Markdown: `![Image](images/5.png)`
+2. You find the provided image labeled: "This is image: 'images/5.png'" or "This is image: '5.png'"
+3. You describe ONLY that specific image content
+4. You add explanation after that specific reference
 
 Example format:
 
 ```markdown
-![Brief image description](./images/0.png)
+![Namespace isolation diagram](./images/5.png)
 
-A detailed explanation of the image, detailed enough to replace the image and help readers understand the content.
+This diagram illustrates how namespace isolation works in containerization. It shows... [describe the ACTUAL content of the image labeled as 'images/5.png' or '5.png']
 ```
 
 ## 3. Correct List Formatting
@@ -131,3 +145,4 @@ Translate the content into Simplified Chinese. Retain original English names for
 - Do not use JSON format or wrap output in code blocks (` ``` `)
 - Verify that heading structure (Rule 5) has been properly adjusted
 - Ensure all image references exist in the original input with unchanged paths
+- **Critical: Verify each image explanation matches its corresponding filename from the provided images**