WPS CLI Cloud Document Conversion
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md to install @wps/wpscli.
About this skill
Problem
Local scripts and offline converters often produce inconsistent results for complex layouts, tables, scanned PDFs, fonts, and cross-format conversion between PDF, Word, Excel, PPT, CAD, HTML, and images. When automation needs repeatable conversions, OCR, splitting, merging, encryption, and compression, environment-specific failures become costly. WPS CLI routes these operations through a single command-line path designed for agent and scripted workflows.
How It Works
It uses WPS Cloud to perform conversions: local files are uploaded, processed, and downloaded, so it requires network access and an API key. Core commands include pdf2word, word2pdf, pdf2cad, cad2image, pdf2html, word2html, plus pdfmerge, pdfsplit, pdf2photo, fileinfo, and image OCR. Use --help to discover supported commands in the current build. Output defaults to the input file's directory, with duplicate names automatically suffixed _1, _2. Prefer --json for structured results and --quiet when only the output path is needed.
Boundaries
It requires system Node.js 22+, a globally installed wpscli, and API key configuration. In Windows Git Bash, use C:/... style paths. Confirm before uploading sensitive files. Membership upgrades, CLI updates, and feedback pages require explicit user consent. If wpscli is unavailable or conversion is rejected, stop and report it; do not fall back to Python, LibreOffice, or other local converters.
Use Cases
- When archiving contracts, split scanned PDFs into numbered single-page files for clause-level retrieval.
- When releasing product docs, batch convert Word guides and PPT decks to PDF and verify output paths.
- When handing off engineering assets, convert drawings with `pdf2cad` and `cad2pdf` to compare cloud versions.
- Before data entry, OCR multiple table images and organize recognized text into Excel or Word.
Best For
- Pre-sales engineers who batch-convert client deliverables to PDF while preserving layout.
- Document managers who process scans, watermarks, and page-level changes in the cloud.
- Engineering assistants who convert CAD drawings to PDF or HTML for review.
- Operations analysts who extract image text into Excel or Word for structured follow-up.
Related Skills
Generate and edit .pptx decks with python-pptx, applying structured layouts, design rules, native charts, and visual QA to reduce template-like output.
Tencent Cloud Table Recognition V3 is an OCR skill for detecting and recognizing tables in images or PDFs, supporting various table types like linear and borderless tables, with Excel export.
The complete set of online document operation tools provided by Tencent Docs MCP, supporting creation, querying, and editing of smart docs, Excel, PPT, mind maps, and more.
Generate structured Chinese patent disclosure drafts in Word from existing documents or brief technical inputs, following Part A/B/C templates.