360 Secure SkillHub
360 安全技能中心

Yuanzi Image Generator

该技能通过 Python 脚本把标题、对比文本或数据填入预制 HTML/CSS 模板，再由浏览器渲染并自动截图，输出公众号文章用的封面图、对比图和数据图。强调零 Token 消耗，模板可自行修改。

golikegod
golikegod
热度 11.03
最近更新 2026-07-04 19:33:16
分类：创作依赖：代码执行 / 联网浏览搜索 / 读写文件应用场景：图像生成 / 社交媒体 / 品牌素材

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add yuanzi-image-generator
Metadata
name
wechat-image-generator
description
元子公众号图文系列之『配图帆』。Generate beautiful images for WeChat articles (covers, comparisons, charts) with zero token cost. Triggers include "生成封面图", "对比图", "配图", "公众号图片".
version
1.0.3
tags
["yuanzi","gzh","articles","wechat","image","suite:yuanzi-wechat-series"]
homepage
https://github.com/jingyu525/wechat-image-generator
metadata
{"openclaw":{"emoji":"🎨","requires":{"bins":["python3"]}},"series":"yuanzi-wechat-series","series-position":"配图帆","fork-of":"wechat-image-generator@1.0.2 (jingyu525)"}

WeChat Image Generator

Generate beautiful images for WeChat articles with zero token cost and auto-screenshot.

Quick Start

1. Cover Image (封面图)

python3 scripts/generate.py cover \
  --title "我的第一个开源项目" \
  --subtitle "Token 成本降低 90%" \
  --output output/cover.png

2. Comparison Image (对比图)

python3 scripts/generate.py compare \
  --left "# Markdown\n**Bold** text" \
  --right "HTML 渲染结果" \
  --label "1 秒转换" \
  --output output/compare.png

3. Chart Image (数据图)

python3 scripts/generate.py chart \
  --data "Token消耗:8000,650|生成耗时:20,1" \
  --labels "AI生成,预制模板" \
  --output output/chart.png

Workflow

  1. Run generator script with parameters
  2. Script creates HTML with embedded data
  3. Opens in browser via OpenClaw browser tool
  4. Auto-screenshot and save to output folder

Design Philosophy

Zero token cost: All templates are pre-built HTML/CSS Auto-screenshot: Integrated with OpenClaw browser tool Customizable: Easy to modify templates for different styles

Token Cost Analysis

Per image generation:

  • Read SKILL.md: ~500 tokens (first time only)
  • Execute script: ~100 tokens
  • Browser screenshot: ~50 tokens

Total: ~650 tokens vs DALL-E/Midjourney ~1000-5000 tokens per image.

Requirements

  • Python 3
  • OpenClaw browser tool (for auto-screenshot)

📦 元子公众号图文系列

🦞 yuanzi-wechat-series · 第 3/4 站「配图帆」

本技能属于「元子公众号图文系列」4 件套之一：

  1. 写作舵 — wechat-article-master
  2. 读稿锚 — wechat-article-extractor-skill
  3. 配图帆 — wechat-image-generator（本技能）
  4. 发布桨 — wechat-article-publisher

推荐工作流：读稿 → 写作 → 配图 → 发布。

v1.0.3 元子系列升级：归 jingyu525 v1.0.2，加入元子系列 tag + 导航。

🦞 元子公众号图文系列 v1.0.3 · 2026-07-04 · 元子系列首发