Sn Da Non Spreadsheet Analysis

This is a document parsing engine for Word, PDF, and PowerPoint files that handles the messy parts: extracting tables, understanding charts through vision models, dealing with scanned PDFs, and aggregating data across multiple files. It's meant to kick in automatically when you upload a .docx or .ppt and ask for analysis, or when you use phrases like "PDF解析" or "合同分析". The workflow routes to format-specific parsers and enforces full scans (no stopping at the first table or slide), which matters when you're doing counts or multi-document comparisons. For image-heavy content like charts in slides or scanned invoices, it delegates to a caption script instead of trying OCR libraries. Solid choice if you're tired of half-parsed documents or need to pull structured data from reports and presentations at scale.

Install to Claude Code

npx -y skills add opensensenova/sensenova-skills --skill sn-da-non-spreadsheet-analysis --agent claude-code