Write a textual content based on given document(s) and requirements, using ZhiPu GLM-V multimodal model. Read and comprehend one or multiple documents (PDF/DOCX), write a content in Markdown format according to the specified requirements. Use when the user wants to draft a paper/article/essay/report/review/post/brief/proposal/plan, etc.
Comprehend the given document(s) and write a textual content (paper/article/essay/report/review/post/brief/proposal/plan) according to your requirements using the ZhiPu GLM-V multimodal model.
| Type | Formats | Max Count | Source |
|---|---|---|---|
| Document (URL) | pdf, docx | 50 |
| URL |
| Document (Local) | pdf only | pages ≤ 50 total | Local path |
Local PDF / 本地 PDF: Local PDF files are converted page-by-page into images (base64) before sending to the model.
PyMuPDFis required (pip install PyMuPDF). URL files support full formats including pdf/docx/txt. 本地 PDF 会自动逐页转为图片（base64）传给模型，需要安装PyMuPDF（pip install PyMuPDF）。URL 文件支持 pdf/docx/txt 等全格式。
After running the script, you must display the complete content (Markdown format) exactly as returned. Do not summarize, truncate, translate, comment, or only say "Writing Completed!".
| Resource | Link |
|---|---|
| Get API Key | https://bigmodel.cn/usercenter/proj-mgmt/apikeys |
| API Docs | Chat Completions / 对话补全 |
This script reads the key from the ZHIPU_API_KEY environment variable and shares it with other Zhipu skills.
脚本通过 ZHIPU_API_KEY 环境变量获取密钥，与其他智谱技能共用同一个 key。
Get Key / 获取 Key： Visit Zhipu Open Platform API Keys / 智谱开放平台 API Keys to create or copy your key.
Setup options / 配置方式（任选一种）：
OpenClaw config (recommended) / OpenClaw 配置（推荐）： Set in openclaw.json under skills.entries.glmv-doc-based-writing.env:
"glmv-doc-based-writing": { "enabled": true, "env": { "ZHIPU_API_KEY": "你的密钥" } }
Shell environment variable / Shell 环境变量： Add to ~/.zshrc:
export ZHIPU_API_KEY="你的密钥"
💡 If you already configured another Zhipu skill (for example
zhipu-toolsorglmv-caption), they share the sameZHIPU_API_KEY, so no extra setup is needed. 💡 如果你已为其他智谱 skill（如zhipu-tools、glmv-caption）配置过 key，它们共享同一个ZHIPU_API_KEY，无需重复配置。
python scripts/doc_based_writing.py \
--files "https://example.com/doucment1.pdf" "https://example.com/doucment2.docx" \
--requirements "基于这篇论文撰写公众号文章，要求偏技术风格"
python scripts/doc_based_writing.py \
--files "https://example.com/doucment1.pdf" "https://example.com/doucment2.docx" \
--requirements "总结文档主要内容和核心观点" \
--output result.md
python scripts/doc_based_writing.py \
--files "https://example.com/doucment1.pdf" "https://example.com/doucment2.docx" \
--criteria "撰写新闻稿" \
--output result.json --pretty
python scripts/doc_based_writing.py \
--files "https://example.com/doucment1.pdf" \
--criteria "为这本书撰写书评" \
--system-prompt "你是一位拥有20年跨领域写作经验的资深写作专家，擅长撰写书评"
The model outputs a Markdown content like this:
XXX
python scripts/doc_based_writing.py --files FILE [FILE...] --requirements REQUIREMENTS [OPTIONS]
| Parameter | Required | Description |
|---|---|---|
--files, -f | ✅ | Document file URLs (pdf/docx, URL only, max 50) |
--requirements, -c | ✅ | Writing requirements text |
--model, -m | No | Model name (default: glm-4.6v) |
--system-prompt, -s | No | Custom system prompt (default: professional HR assistant) |
--temperature, -t | No | Sampling temperature 0-1 (default: 0.6) |
--max-tokens | No | Max output tokens (default: 10000) |
--output, -o | No | Save result to file (.md for markdown, .json for JSON) |
--pretty | No | Pretty-print JSON output |
API key not configured: → Guide user to configure ZHIPU_API_KEY
Authentication failed (401/403): → API key invalid/expired → reconfigure
Rate limit (429): → Quota exhausted → wait and retry
Local path provided: → Error: only URLs supported
Content filtered: → warning field present → content blocked by safety review
Timeout: → Documents too large or too many → reduce file count