xiaohuihui-dify-tech-article

Original🇨🇳 Chinese
Translated
1 scriptsChecked / no sensitive code detected

A WeChat Official Account article generator designed specifically for Dify workflow case sharing, which follows the writing specifications of Xiaohuihui's official account, automatically generates complete Dify case articles including preface, workflow production, and summary, with detailed node configuration, plugin installation steps, code examples, and supports uploading automatically generated images to Tencent Cloud COS image hosting.

3installs
Added on

NPX Install

npx skill4agent add wwwzhouhui/skills_collection xiaohuihui-dify-tech-article

Tags

Translated version includes tags in frontmatter

SKILL.md Content (Chinese)

View Translation Comparison →

Xiaohuihui Dify Case Article Generator

A professional creation assistant for Dify workflow case sharing, fully complying with the writing style of Xiaohuihui's WeChat Official Account and Dify's characteristic structural specifications.

Core Features

  • Dify exclusive structure: Preface → Workflow production → Summary
  • Detailed workflow node explanation: Start, LLM, Agent, code execution, plugin configuration, etc.
  • Plugin installation guide: Steps for searching, installing, and authorizing third-party plugins
  • MCP tool integration: Instructions for MCP server deployment and configuration
  • Effect display first: Show the workflow effect first, then introduce the production process
  • Colloquial technical articles: Friendly expressions such as "without further ado", "step-by-step construction", "much better"
  • ModelScope community recommendation: Prioritize using free models provided by ModelScope community
  • Real image generation: Automatically generate supporting images and upload them to Tencent Cloud COS image hosting

Usage

Basic Usage

用小灰灰公众号风格写一篇 Dify [工作流功能] 的案例分享文章

Detailed Usage

帮我写一篇小灰灰风格的 Dify 案例文章:
- 功能: [工作流实现的功能]
- 涉及插件: [需要安装的插件]
- 核心节点: [主要使用的节点类型]
- 技术栈: [MCP、第三方API等]

Image Generation Workflow

Image Generation Strategy

When generating Dify case articles, real images must be included instead of placeholders. Follow the workflow below:

1. Plan image requirements

Plan the type and quantity of images required according to the article content:
✅ Required image types for Dify workflow:
  • Overall workflow diagram (1 piece): Node connection diagram of the complete workflow
  • Node configuration screenshots (6-10 pieces): Detailed configuration of each key node
  • Plugin installation screenshots (2-3 pieces): Plugin market search, installation, and authorization interfaces
  • Effect demonstration diagrams (2-3 pieces): Workflow operation effect and generated result display
  • Code configuration diagrams (1-2 pieces): Code content of code execution nodes
  • Model configuration diagrams (1-2 pieces): LLM model selection and parameter configuration
❌ Images requiring actual operation:
  • Actual workflow screenshot: Need to be actually built on the Dify platform
  • Plugin authorization interface: Need to be screenshot after actually installing the plugin
  • Operation log: Need to be screenshot after actually running the workflow
  • Effect display: Need to actually test the workflow effect
Recommended number of images:
  • Workflow configuration screenshots: 8-12 pieces
  • Plugin installation screenshots: 2-3 pieces
  • Effect demonstration: 2-3 pieces
  • Qualification standard: Total >= 10 pieces
  • Excellent standard: Total >= 15 pieces

2. Upload images to COS

Use the provided
scripts/upload_to_cos.py
script to upload images.
Prerequisites: Create a
.env
file in the project root directory and configure Tencent Cloud COS information:
bash
# .env 文件内容
COS_SECRET_ID=your-secret-id
COS_SECRET_KEY=your-secret-key
COS_BUCKET=your-bucket-name
COS_REGION=your-region
Upload command:
bash
# 基础上传(自动生成文件名)
python scripts/upload_to_cos.py /path/to/image.png

# 自定义文件名
python scripts/upload_to_cos.py /path/to/image.png --name workflow-20251122.png

# 静默模式(只输出 URL)
python scripts/upload_to_cos.py /path/to/image.png --quiet

3. Use real URL

After successful upload, use the returned complete COS URL in the article:
markdown
![工作流全局图](https://your-bucket.cos.your-region.myqcloud.com/image-20251122-143025.png)

Image Naming Specification

  • Auto-generated:
    image-YYYYMMDD-HHMMSS.extension
  • Semantic:
    workflow-20251122.png
    ,
    plugin-install-20251122.png
    ,
    node-config-20251122.png

Image Quality Requirements

  • Size: 1200x800 or 16:9 ratio (landscape)
  • Format: PNG (screenshot/UI)
  • File size: < 500KB per image
  • Clarity: Text is clear and readable

Article Structure Template

Chapter 1: Preface (about 300-400 words)

First paragraph: Technical background introduction (100-150 words)

Introduce relevant technical concepts or application scenarios and explain their importance.
Example:
RSS(Really Simple Syndication)是一种基于XML的网络内容分发格式,
主要用于将新闻、博客、论坛等频繁更新的内容以订阅的方式提供给用户。
它允许用户通过RSS阅读器在一个界面中跟踪多个网站的更新,
而无需手动访问每个网站。

Second paragraph: Problem or demand introduction (100-150 words)

Describe user pain points or requirements, and lead to the problem to be solved in this article.
Example:
之前给大家做过一期文生视频的dify工作流的案例,
使用的是智普提供文生视频功能。
之前的这个文生视频效果一般般,用户体验不是太好。
有没有办法实现调用即梦AI实现文生视频功能,而且还免费呢?

Third paragraph: Solution and effect display (100-150 words)

Introduce the Dify workflow solution of this article and display the effect diagram.
Fixed sentence pattern:
今天给大家带来一个基于dify工作流的[功能名称]。
下面大家看看一下工作流以及工作流生成[功能]的效果。

![工作流全局图](图片URL)

生成的效果如下:

![效果展示](图片URL)

那么这样的基于dify工作流的[功能]是如何制作的呢?话不多说,下面开始干活。

Chapter 2: Workflow Production (about 1500-2500 words)

2.1 Preparations (if needed)

Plugin installation template:
markdown
## [插件名称]安装

我们在dify的插件市场中查找名称"[插件名称]"

![插件搜索](图片URL)

搜索到这个插件后,点击"安装"按钮完成插件的安装。

![插件安装](图片URL)

安装完成后,我们可以在已经安装的插件列表中查询到

![插件列表](图片URL)

## [插件名称]授权

插件安装完成后,我们打开[插件名称]点击"授权"按钮

![插件授权](图片URL)

这里[填写授权参数说明],我们点击保存就可以了

![授权完成](图片URL)
MCP Server deployment template:
markdown
## MCP Server 部署

这个工作流核心是一个基于[mcp-server名称]的开源项目。
项目地址: https://github.com/xxx/xxx

![项目地址](图片URL)

我们要使用这个mcp-server功能,所以我们需要把这个项目部署起来。
目前这个项目比较完整支持docker和源码部署。

部署命令:
```bash
# Docker 部署
docker run -d \
  --name mcp-server \
  -p 8005:8005 \
  image:latest
```

部署完成后,访问地址: http://your-server:8005/mcp

2.2 Workflow construction

Start node template:
markdown
## 开始

我们首先在工作流平台上创建一个 chatflow/workflow。

![创建工作流](图片URL)

创建完成后,我们就可以设置一下开始节点。
这个开始节点需要设置一个[参数名称],用于[参数用途]。

![开始节点配置](图片URL)

我们这里提供[选项列表]供用户选择。

![参数选项](图片URL)

上面我们就完成了开始节点的配置。
LLM node template:
markdown
## LLM大语言模型

大语言模型这块我们选择魔搭社区提供的免费[模型名称]模型。
关于这个模型大家可以在魔搭社区广场找到。

![模型选择](图片URL)

目前魔搭社区提供每天2000次的模型调用,个人测试使用基本上是够用了。

![免费额度](图片URL)

系统提示词内容如下:

```
你是一个[角色定义],用户输入[输入描述],
通过[处理方式]生成[输出描述]。

举例:
输入:[示例输入]
输出:[示例输出]
```

模型其他参数:
- 模型: [模型名称]
- 温度: 0.7
- 最大token: 2000

![LLM配置](图片URL)
Agent node template:
markdown
## Agent策略

这个工作流用到Agent策略,如果dify平台上没有安装Agent策略插件的可以先安装一下。

我们可以在插件市场-Agent策略找到这个插件。

![Agent插件](图片URL)

插件安装完成后,我们可以在已安装插件上查找到

![插件列表](图片URL)

Agent配置:
- 推理模型: [模型名称]
- MCP工具: [工具名称]
- 最大迭代: 5

![Agent配置](图片URL)
Code execution node template:
markdown
## 代码执行

这个代码执行节点主要是通过代码的方式处理[处理内容]。

输入参数:
- arg1: [参数描述]
- arg2: [参数描述]

![输入参数](图片URL)

输出变量:
- result: [返回描述],返回类型是 string/object

中间处理的代码如下:

```python
import json

def main(arg1: str, arg2: str) -> dict:
    # 处理逻辑
    result = process_data(arg1, arg2)
    return {
        "result": result
    }
```

![代码内容](图片URL)
HTTP request node template:
markdown
## HTTP请求

这里我们需要一个HTTP请求,调用[API名称]接口。

请求配置:
- 方法: POST
- URL: https://api.example.com/v1/generate
- Headers:
  ```json
  {
    "Authorization": "Bearer {{auth_token}}",
    "Content-Type": "application/json"
  }
  ```
- Body:
  ```json
  {
    "prompt": "{{prompt}}",
    "model": "gpt-4"
  }
  ```

![HTTP配置](图片URL)

返回数据格式:
```json
{
  "status": "success",
  "data": {
    "result": "生成的内容"
  }
}
```

2.3 Test verification

Template:
markdown
## 测试验证

配置完成后,我们点击"运行"按钮测试工作流。

![运行测试](图片URL)

输入测试内容:
[测试输入示例]

查看运行日志:

![运行日志](图片URL)

查看生成结果:

![生成结果](图片URL)

通过对比来看效果不错,基本达到预期。话不多说,是不是很简单?

Chapter 3: Summary (single paragraph of 300-400 words, no paragraph breaks allowed)

Standard template (must be strictly followed):
今天主要带大家了解并实现了基于Dify工作流的[功能全称]完整流程,
该工作流以"[核心技术1 + 核心技术2]"为核心,
结合[应用场景]需求,
通过[节点1]、[节点2]、[节点3]等关键节点,
配合[插件名称]插件和[工具名称]工具,
形成了一套从[起点]到[终点]的完整解决方案。
通过这套Dify工作流,[用户群体]能够高效实现[核心价值] ——
借助[具体操作](包括[步骤1]、[步骤2]、[步骤3]),
无需[传统障碍],
就能快速[核心功能](如本次演示的"[案例名称]")。
无论是[功能1]、[功能2],还是[功能3]、[功能4],
都能通过简单的节点配置完成,
极大[提升维度]。
在实际应用中,该工作流不仅[优势1],还[优势2],
适配性远优于[传统方案];
特别是通过[关键技术点],有效解决了[具体问题]的难题。
同时,工作流具备良好的扩展性 ——
小伙伴们可以基于此扩展更多[应用场景],
如[场景1]、[场景2]、[场景3]等,
进一步发挥Dify工作流在[领域1]、[领域2]等领域的应用价值。
感兴趣的小伙伴可以按照文中提供的步骤进行实践,
根据实际[需求类型]调整[可调整项]。
今天的分享就到这里结束了,我们下一篇文章见。
Checklist:
  • Single paragraph without breaks
  • 300-400 words
  • Emphasize Dify workflow
  • List 4+ functions/nodes
  • Compare with traditional solutions
  • 3+ extended scenarios
  • Fixed closing remarks

Chapter 4: Additional Resources (optional)

markdown
## 项目资源

**工作流DSL**:
提供工作流的DSL文件供下载导入。

**相关链接**:
- Dify官网: https://dify.ai
- 插件市场: https://marketplace.dify.ai
- 魔搭社区: https://modelscope.cn

**在线体验**:
如果提供了在线体验地址,可以添加。

**附件代码**:
网盘分享: dify-workflow.zip
链接: https://pan.baidu.com/s/xxx 提取码: abcd

#首发于魔搭研习社

Dify Characteristic Language Style

Dify Special Vocabulary

Workflow related:
  • "工作流节点", "chatflow", "workflow"
  • "开始节点", "LLM节点", "Agent节点", "代码执行节点"
  • "条件分支", "变量聚合器", "直接回复"
  • "上下文变量", "系统变量"
Plugin related:
  • "插件市场", "第三方插件", "插件授权"
  • "已安装插件", "插件升级"
Model related:
  • "魔搭社区", "免费额度", "每天2000次调用"
  • "大语言模型", "系统提示词"
MCP related:
  • "MCP server", "MCP工具", "streamable-http"
  • "MCP协议", "双向MCP"

Colloquial Expression

Required vocabulary:
  • Greetings: "小伙伴们", "大家", "给大家"
  • Modal particles: "话不多说", "下面开始干活", "好很多"
  • Question guidance: "是不是很简单?", "效果不错吧?"
  • Sense of dialogue: "我们接下来...", "手把手搭建"
Timeliness tags:
  • "今天给大家带来"
  • "最新推出"
  • "下面介绍一下..."

Dify Characteristic Visual Elements

Image Format

Must use real Tencent Cloud COS URL:
markdown
![图片描述](https://your-bucket.cos.your-region.myqcloud.com/image-20251122-143025.png)
Dify characteristic image types:
  • Overall workflow diagram
  • Node configuration screenshots
  • Plugin market screenshots
  • Authorization interface screenshots
  • Code execution screenshots
  • Operation log screenshots
  • Effect display diagrams

Code Block Specification

Python code:
markdown
```python
import json

def main(arg1: str) -> dict:
    # 处理逻辑
    data = json.loads(arg1)
    result = process(data)
    return {"result": result}
```
System prompt:
markdown
```
你是一个[角色],用户输入[内容],
生成[结果]。

举例:
输入:[示例]
输出:[示例]
```
HTTP request:
markdown
```json
{
  "method": "POST",
  "url": "https://api.example.com",
  "body": {
    "prompt": "{{prompt}}"
  }
}
```
Workflow DSL:
markdown
```yaml
version: "1.0"
nodes:
  - id: start
    type: start
    config:
      variables:
        - name: query
          type: string
```

Quality Standards

Qualification Standards (must be met)

  • ✅ Total word count > 1800 words
  • ✅ Title format: "dify案例分享-[功能名称]"
  • ✅ Workflow screenshots >= 10
  • ✅ Node configuration descriptions >= 5
  • ✅ Code blocks >= 3
  • ✅ Summary single paragraph 300-400 words
  • ✅ Fixed closing remarks
  • ✅ Emphasize ModelScope community free models

Excellent Standards (recommended)

  • 🌟 Total word count > 2500 words
  • 🌟 Workflow screenshots >= 15
  • 🌟 Node configuration descriptions >= 8
  • 🌟 Code blocks >= 5
  • 🌟 Include plugin installation steps
  • 🌟 Include MCP integration instructions
  • 🌟 Provide online experience or DSL download

Error Avoidance

❌ Prohibited

  1. Summary with paragraph breaks
  2. Missing overall workflow diagram
  3. Unclear node configuration description
  4. Omit plugin installation steps
  5. Missing effect display
  6. Do not mention ModelScope community
  7. Use placeholder images

✅ Correct

  1. Colloquial and professional
  2. Complete workflow steps
  3. Detailed node configuration
  4. Sufficient and clear screenshots
  5. Code can be used directly
  6. Prioritize recommending ModelScope free models
  7. In-depth single paragraph summary

Dify Case Classification

Common Workflow Types

Text processing category:
  • Text generation, text conversion, text summarization
  • Translation, grammar check, content optimization
Image processing category:
  • Text to image, image to image, image recognition
  • OCR recognition, image to video
Video processing category:
  • Text to video, image to video
  • Video summarization, subtitle generation
Data processing category:
  • Data crawling, data cleaning
  • Data visualization, chart generation
Integrated application category:
  • Feishu integration, WeCom integration
  • Database query, API call
MCP tool category:
  • MCP server integration
  • Two-way MCP protocol application

Trigger Method

Automatic trigger keywords:
  • "Dify" + "工作流"
  • "Dify" + "案例"
  • "魔搭" + "Dify"
  • "插件" + "Dify"

Changelog

v1.0.0 (2025-11-22)

  • ✅ Initial version
  • ✅ Dify exclusive structure
  • ✅ Detailed workflow node explanation
  • ✅ Plugin installation guide
  • ✅ MCP tool integration
  • ✅ Colloquial style
  • ✅ Quality standards

Technical Support

Reference documents:
  • xiaohuihui-dify-tech-article2/ - Dify case example article collection
  • xiaohuihui-tech-article/ - General technical article template reference