glmv-doc-based-writing
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseGLM-V Document-Based Writing Skill
GLM-V 基于文档的写作技能
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.
借助智谱GLM-V多模态模型,理解给定文档后,按照你的需求生成文本内容(论文/文章/随笔/报告/评论/帖子/简报/提案/计划)。
When to Use
适用场景
- Write a textual content according to specified requirements, AFTER reading provided document(s)
- User mentions "基于文档的写作", "文章撰写", "文档解读", "新闻稿撰写", "简报撰写", "影评/书评撰写", "内容总结", "内容创作", "评论写作", "文档续写", "文档翻译", "方案策划", "发言稿撰写", "document-based writing", "article writing", "document reading", "press release writing", "brief writing", "film/book review writing", "content summarization", "content creation", "commentary writing", "document continuation", "document translation", "proposal planning ", "speech writing"
- 读取提供的文档后,按照指定要求生成文本内容
- 用户提到「基于文档的写作」、「文章撰写」、「文档解读」、「新闻稿撰写」、「简报撰写」、「影评/书评撰写」、「内容总结」、「内容创作」、「评论写作」、「文档续写」、「文档翻译」、「方案策划」、「发言稿撰写」、document-based writing、article writing、document reading、press release writing、brief writing、film/book review writing、content summarization、content creation、commentary writing、document continuation、document translation、proposal planning、speech writing
Supported Input Types
支持的输入类型
| 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.is required (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pip install PyMuPDF(PyMuPDF)。URL 文件支持 pdf/docx/txt 等全格式。pip install PyMuPDF
| 类型 | 格式 | 最大数量 | 来源 |
|---|---|---|---|
| 文档(URL) | pdf, docx | 50 | URL |
| 文档(本地) | pdf only | 总页数 ≤ 50 | 本地路径 |
Local PDF / 本地 PDF: Local PDF files are converted page-by-page into images (base64) before sending to the model.is required (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pip install PyMuPDF(PyMuPDF)。URL 文件支持 pdf/docx/txt 等全格式。pip install PyMuPDF
📋 Output Display Rules (MANDATORY)
📋 输出展示规则(强制要求)
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!".
运行脚本后,必须完整展示返回的全部内容(Markdown格式)。不要进行总结、截断、翻译、评论,也不要只说「写作完成!」。
Resource Links
资源链接
| Resource | Link |
|---|---|
| Get API Key | https://bigmodel.cn/usercenter/proj-mgmt/apikeys |
| API Docs | Chat Completions / 对话补全 |
| 资源 | 链接 |
|---|---|
| 获取API Key | https://bigmodel.cn/usercenter/proj-mgmt/apikeys |
| API文档 | Chat Completions / 对话补全 |
Prerequisites
前置要求
API Key Setup / API Key 配置(Required / 必需)
API Key Setup / API Key 配置(Required / 必需)
This script reads the key from the environment variable and shares it with other Zhipu skills.
脚本通过 环境变量获取密钥,与其他智谱技能共用同一个 key。
ZHIPU_API_KEYZHIPU_API_KEYGet 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 inunder
openclaw.json:skills.entries.glmv-doc-based-writing.envjson"glmv-doc-based-writing": { "enabled": true, "env": { "ZHIPU_API_KEY": "你的密钥" } } -
Shell environment variable / Shell 环境变量: Add to:
~/.zshrcbashexport ZHIPU_API_KEY="你的密钥"
💡 If you already configured another Zhipu skill (for exampleorzhipu-tools), they share the sameglmv-caption, so no extra setup is needed. 💡 如果你已为其他智谱 skill(如ZHIPU_API_KEY、zhipu-tools)配置过 key,它们共享同一个glmv-caption,无需重复配置。ZHIPU_API_KEY
This script reads the key from the environment variable and shares it with other Zhipu skills.
脚本通过 环境变量获取密钥,与其他智谱技能共用同一个 key。
ZHIPU_API_KEYZHIPU_API_KEY获取Key / 获取 Key: 访问智谱开放平台 API Keys / 智谱开放平台 API Keys 创建或复制你的密钥。
配置方式 / 配置方式(任选一种):
-
OpenClaw config (推荐) / OpenClaw 配置(推荐): 在的
openclaw.json下配置:skills.entries.glmv-doc-based-writing.envjson"glmv-doc-based-writing": { "enabled": true, "env": { "ZHIPU_API_KEY": "你的密钥" } } -
Shell环境变量 / Shell 环境变量: 添加到中:
~/.zshrcbashexport ZHIPU_API_KEY="你的密钥"
💡 如果你已为其他智谱 skill(如、zhipu-tools)配置过 key,它们共享同一个glmv-caption,无需重复配置。ZHIPU_API_KEY
How to Use
使用方法
Basic Screening
基础使用
bash
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"bash
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"Save as Markdown
保存为Markdown
bash
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.mdbash
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.mdSave as JSON
保存为JSON
bash
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 --prettybash
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 --prettyCustom System Prompt
自定义系统提示词
bash
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"bash
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"Output Example
输出示例
The model outputs a Markdown content like this:
markdown
XXX模型会输出如下格式的Markdown内容:
markdown
XXXCLI Reference
CLI参数参考
python scripts/doc_based_writing.py --files FILE [FILE...] --requirements REQUIREMENTS [OPTIONS]| Parameter | Required | Description |
|---|---|---|
| ✅ | Document file URLs (pdf/docx, URL only, max 50) |
| ✅ | Writing requirements text |
| No | Model name (default: |
| No | Custom system prompt (default: professional HR assistant) |
| No | Sampling temperature 0-1 (default: 0.6) |
| No | Max output tokens (default: 10000) |
| No | Save result to file ( |
| No | Pretty-print JSON output |
python scripts/doc_based_writing.py --files FILE [FILE...] --requirements REQUIREMENTS [OPTIONS]| 参数 | 是否必填 | 描述 |
|---|---|---|
| ✅ | 文档文件URL(支持pdf/docx,仅支持URL,最多50个) |
| ✅ | 写作要求文本 |
| 否 | 模型名称(默认: |
| 否 | 自定义系统提示词(默认:专业HR助理) |
| 否 | 采样温度,取值范围0-1(默认:0.6) |
| 否 | 最大输出token数(默认:10000) |
| 否 | 将结果保存到文件( |
| 否 | 格式化输出JSON内容 |
Error Handling
错误处理
API key not configured: → Guide user to configure
ZHIPU_API_KEYAuthentication 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: → field present → content blocked by safety review
warningTimeout: → Documents too large or too many → reduce file count
未配置API key: → 引导用户配置
ZHIPU_API_KEY认证失败 (401/403): → API key无效/已过期 → 重新配置
触发频率限制 (429): → 配额耗尽 → 等待后重试
传入本地路径: → 错误:仅支持URL
内容被过滤: → 存在字段 → 内容被安全审查拦截
warning请求超时: → 文档过大或数量过多 → 减少文件数量