glmv-doc-based-writing

Generate Markdown content from PDF or DOCX documents using GLM-V.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/ViewWay/openclaw-skills --skill glmv-doc-based-writing-viewway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: glmv-doc-based-writing
Source: https://github.com/ViewWay/openclaw-skills/tree/main/glmv-doc-based-writing
Command: npx skills add https://github.com/ViewWay/openclaw-skills --skill glmv-doc-based-writing-viewway

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, PyMuPDF, and includes scripts (resource) components.

What problem does it solve?

GLMV Document-Based Writing helps users generate polished Markdown content by reading one or more documents (PDF/DOCX) and composing tailored text with the GLM-V multimodal model, saving time and ensuring consistency.

Core Features & Use Cases

  • Reads documents (PDF/DOCX) and produces structured Markdown outputs based on requirements.
  • Supports multiple documents and various writing styles (papers, articles, reports, reviews, briefs).
  • Integrates with ZHIPU API to deliver contextual, requirements-aligned content.

Quick Start

Provide 1–50 document URLs or local PDFs, set your writing requirements, and run the tool to generate Markdown content.

Frequently Asked Questions about glmv-doc-based-writing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate Markdown content from PDF documents for research writing?

To generate Markdown content from PDF documents, provide 1 to 50 document URLs or local PDFs and set your writing requirements. The tool reads the documents and outputs structured Markdown text using the GLM-V model.

What is the best way to draft articles and reports from multiple DOCX files?

Drafting articles and reports from multiple DOCX files is done by supplying document URLs and specifying the desired writing style. The tool processes up to 50 files to produce tailored Markdown output.

Do I need a ZHIPU API key to use multimodal document-based writing?

Yes, a ZHIPU API key is required to access the GLM-V multimodal model for document-based writing. The API key enables the tool to read documents and generate contextual content.

Can I process local PDFs and URL-based documents together for content generation?

You can process local PDFs alongside URL-based documents together for content generation. The tool supports up to 50 files, reading them to compose requirements-aligned Markdown text.

What are the limitations when converting PDFs to Markdown using GLM-V?

Limitations when converting PDFs to Markdown include a maximum of 50 URL-based documents or local PDFs per task. The tool requires a ZHIPU API key and focuses on generating text rather than parsing complex layouts.