发现最适合你需求的 AI 技能
Extract text content from image-based/scanned PDFs using multiple vision APIs with automatic fallback. Supports Xflow (qwen3-vl-plus) and ZhipuAI (GLM-4.6V-Flash, GLM-5) vision models. This skill converts PDF pages to images and uses AI vision capabilities to extract structured text, tables, and content from scanned documents that cannot be processed with traditional text extraction methods.
Convert PDF documents to HTML using MinerU. Transforms PDF files into web-ready HTML with structure and formatting preserved. Features: PDF to HTML conversion with layout preservation. Handles text, tables, images, and formatting. Supports local files and URLs. Token-based extraction for full features. Use when you need to: convert a PDF to HTML, turn a PDF into a web page, generate HTML from a PDF document, publish PDF content on the web. Use when asked: 'how do I convert PDF to HTML', 'turn th
Convert PDF documents to Word (.docx) format using MinerU. Transforms PDF files into editable Word documents preserving layout, text, tables, and formatting. Features: PDF to DOCX conversion with layout preservation. Handles text, tables, images, and formatting. OCR mode for scanned PDFs. VLM mode for complex layouts. Page range selection for large documents. Use when you need to: convert a PDF to Word, turn a PDF into an editable document, make a PDF editable in Word, transform PDF to .docx. Us
Rename academic PDF papers to a standardized format "[Year] [Venue] Title.pdf" using a three-stage pipeline (Extract → Verify → Rename). Use when the user asks to organize, batch-rename, or metadata-enrich PDF files in a folder. Activates on keywords like "rename PDFs", "organize papers", "batch rename PDFs", "rename papers by metadata", "pdf重命名", "文献整理".
Read, extract, and analyze PDF files. Use when the user needs to: (1) Extract text from PDF documents, (2) Analyze PDF content, (3) Summarize PDF documents, (4) Search for specific information in PDFs, (5) Extract tables from PDFs
Analyze the structure, layout, and content of PDF documents using MinerU. Returns structured output preserving headings, tables, images, formulas, and document hierarchy. Features: comprehensive PDF analysis. Detects document structure: headings, paragraphs, tables, images, formulas. Multiple output formats (Markdown, HTML, JSON, LaTeX, DOCX). OCR and VLM modes for scanned or complex PDFs. Page range selection. Use when you need to: analyze a PDF document, understand PDF structure, inspect PDF c
|
|
|
|
Generate ethical, compliant, and patient-friendly recruitment advertisements for clinical trials.
Simplify informed consent documents into patient-friendly language while maintaining regulatory compliance (FDA 21CFR50, ICH-GCP, HIPAA) and required legal elements.
