glmv-doc-based-writing

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

GLM-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

TypeFormatsMax CountSource
Document (URL)pdf, docx50URL
Document (Local)pdf onlypages ≤ 50 totalLocal path
Local PDF / 本地 PDF: Local PDF files are converted page-by-page into images (base64) before sending to the model.
PyMuPDF
is 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。
类型格式最大数量来源
文档(URL)pdf, docx50URL
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.
PyMuPDF
is 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。

📋 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

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
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):
  1. OpenClaw config (recommended) / OpenClaw 配置(推荐): Set in
    openclaw.json
    under
    skills.entries.glmv-doc-based-writing.env
    :
    json
    "glmv-doc-based-writing": { "enabled": true, "env": { "ZHIPU_API_KEY": "你的密钥" } }
  2. Shell environment variable / Shell 环境变量: Add to
    ~/.zshrc
    :
    bash
    export ZHIPU_API_KEY="你的密钥"
💡 If you already configured another Zhipu skill (for example
zhipu-tools
or
glmv-caption
), they share the same
ZHIPU_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。
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。
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):
  1. OpenClaw config (推荐) / OpenClaw 配置(推荐):
    openclaw.json
    skills.entries.glmv-doc-based-writing.env
    下配置:
    json
    "glmv-doc-based-writing": { "enabled": true, "env": { "ZHIPU_API_KEY": "你的密钥" } }
  2. Shell环境变量 / Shell 环境变量: 添加到
    ~/.zshrc
    中:
    bash
    export ZHIPU_API_KEY="你的密钥"
💡 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。

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.md
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.md

Save 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 --pretty
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 --pretty

Custom 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
XXX

CLI Reference

CLI参数参考

python scripts/doc_based_writing.py --files FILE [FILE...] --requirements REQUIREMENTS [OPTIONS]
ParameterRequiredDescription
--files
,
-f
Document file URLs (pdf/docx, URL only, max 50)
--requirements
,
-c
Writing requirements text
--model
,
-m
NoModel name (default:
glm-4.6v
)
--system-prompt
,
-s
NoCustom system prompt (default: professional HR assistant)
--temperature
,
-t
NoSampling temperature 0-1 (default: 0.6)
--max-tokens
NoMax output tokens (default: 10000)
--output
,
-o
NoSave result to file (
.md
for markdown,
.json
for JSON)
--pretty
NoPretty-print JSON output
python scripts/doc_based_writing.py --files FILE [FILE...] --requirements REQUIREMENTS [OPTIONS]
参数是否必填描述
--files
,
-f
文档文件URL(支持pdf/docx,仅支持URL,最多50个)
--requirements
,
-c
写作要求文本
--model
,
-m
模型名称(默认:
glm-4.6v
--system-prompt
,
-s
自定义系统提示词(默认:专业HR助理)
--temperature
,
-t
采样温度,取值范围0-1(默认:0.6)
--max-tokens
最大输出token数(默认:10000)
--output
,
-o
将结果保存到文件(
.md
为Markdown格式,
.json
为JSON格式)
--pretty
格式化输出JSON内容

Error Handling

错误处理

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
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
warning
字段 → 内容被安全审查拦截
请求超时: → 文档过大或数量过多 → 减少文件数量