home/productivity/vlm-prompt-with-markdown

Vlm Prompt With Markdown

GPTClaudeDeepSeek··▲ 1,395 copies·updated 2026-07-14

vlm-prompt-with-markdown.prompt

IMPORTANT: THE ENTIRE RESPONSE MUST BE WRITTEN IN [LANGUAGE]. DO NOT USE ANY OTHER LANGUAGE.

Describe the content of this page for a visually impaired person.
This is page [PAGE_NUM] of [TOTAL_PAGES].

YOUR TASK:
1. Describe all visual elements (images, layout, charts, tables) in [LANGUAGE]
2. Include all text content in [LANGUAGE]
3. Organize the information in a structured way
4. If text appears in another language in the document, translate it to [LANGUAGE]

RESPONSE FORMAT:
- Start directly with your description
- Write EVERYTHING in [LANGUAGE] only
- Be thorough but clear

Start your response now in [LANGUAGE]:

As additional context, here is a preliminary text extraction from the page:

when to use it

Community prompt sourced from the open-source GitHub repo DavidLMS/DescribePDF (MIT). A "Vlm Prompt With Markdown" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.