@yejinlei

pdf-ocr-skill extracts text from scanned pdfs and images using four switchable ocr engines. supports local processing with rapidocr, paddleocr, or rapidoc, plus cloud recognition via siliconflow api. bilingual documentation provided.

pdf-ocr-skill extracts text from scanned pdfs and images using dual ocr engines: local rapidocr or cloud-based silicon flow api. supports chinese and english recognition with automatic fallback between engines.

excel-parser-skill extracts content from multiple excel formats using calamine. covers .xls, .xlsx, .xlsm parsing with configurable row limits and output as structured data or text.

mindsdb-mcp-skill provides natural language access to 200+ data sources via MindsDB, supporting queries, ai model creation, rag knowledge bases, and intelligent analysis. lacks explicit step-by-step procedures and edge case documentation.

通用网络搜索技能，支持多引擎搜索（百度、必应、DuckDuckGo），无需API密钥即可获取实时信息

支持双引擎的PDF OCR识别技能，可从影印版PDF文件和图片文件中提取中英文文字内容 | PDF OCR Skill with dual-engine support, capable of extracting Chinese and English text from scanned PDF files and…