菜单
Convert PDF files to markdown format using visual PDF understanding or image OCR. Use when asked to convert a PDF to markdown, extract PDF content to markdown, transcribe a PDF, or prepare PDF content for further processing. Preserves all text, structure, tables, and equations. Outputs as a markdown file.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create a structured handoff document for Codex task continuity, capturing decisions, rationale, failed approaches, current state, and next steps so a fresh task can continue without re-explanation. Use when explicitly invoked with $handoff; text supplied alongside the invocation may identify a focus.
Resume a Codex task from a handoff document by verifying it against the current codebase, summarising the actual state, and continuing from the next step. Use when explicitly invoked with $resume; text supplied alongside the invocation may name a handoff file or partial filename.
Extract and clean PDF content to markdown format. Use when the user uploads a PDF file and wants to convert it to clean, readable markdown. Handles text extraction, image extraction, metadata capture, and intelligent content cleanup. Removes repeated footers, watermarks, page numbers, branding, and reorganizes fragmented content into coherent structure.
Generate Anki flashcard decks from PDF or Markdown study materials. Use only when "Anki flashcard" or "Anki deck" is explicitly mentioned. Do not trigger for generic flashcard requests. Outputs in Anki-importable format (Question | Answer).
Ask clarifying questions and discuss direction before starting work. Trigger whenever the user asks Claude to discuss, clarify, or ask questions before proceeding with a task. Natural phrasings include "let's discuss before proceeding", "ask me questions for clarification or direction", "let's discuss and make a plan first", "clarify the direction before starting", and "feel free to ask me anything before you start". Also trigger on the explicit keyword "discuss-first". Do NOT trigger on conversational uses of "discuss" where the user simply wants Claude to explain or talk about a topic and there is no task being held back.
Extract and clean PDF content to markdown format. Use when the user uploads a PDF file and wants to convert it to clean, readable markdown. Handles text extraction, image extraction, metadata capture, and intelligent content cleanup. Removes repeated footers, watermarks, page numbers, branding, and reorganizes fragmented content into coherent structure.
| name | pdf-to-markdown-converter |
| description | Convert PDF files to markdown format using visual PDF understanding or image OCR. Use when asked to convert a PDF to markdown, extract PDF content to markdown, transcribe a PDF, or prepare PDF content for further processing. Preserves all text, structure, tables, and equations. Outputs as a markdown file. |
Faithfully convert PDF content to markdown format using visual PDF capability or image OCR.
Complete transcription: Include ALL text content. Do not summarise or omit.
Preserve structure:
#, ##, ### (match hierarchy from source)**bold***italic*- or *1., 2., etc.Tables: Convert to markdown table format:
| Column 1 | Column 2 |
|----------|----------|
| Data | Data |
Equations/formulas: Use LaTeX notation:
$E = mc^2$$$F = ma$$Diagrams/images: Describe in a blockquote with [DIAGRAM] prefix:
> [DIAGRAM]: Description of what the diagram shows, including labels and key information.
Remove repeated footers: Omit recurring footer content such as brand names, website links, copyright notices, page numbers, and other boilerplate that appears on multiple pages.
Page breaks: Optionally insert --- between major sections if helpful for navigation.
Markdown file named to match the source PDF (e.g., Topic Name.md).