TypingMindTypingMindThe best frontend for AI
Wechat Publish Template logo

Wechat Publish Template

Community
limin112
wechat-publish-template

把 Markdown 文章转成"个人技术风"公众号 HTML（橙黑赛博朋克风格）。用户提供 .md 文件路径，或贴一段 Markdown，并说"转成公众号"/"做成公众号排版"/"套公众号模板"时触发。产物是单一 HTML 文件，全 inline style，可直接在浏览器打开后全选复制粘贴到微信公众号编辑器。不要在用户只是问"如何写公众号"或"公众号选题"这类非排版问题时触发。

Overview

Publisherlimin112
Repositorymin-skill
Skill namewechat-publish-template
Stars
507
Forks
71
Bundled files
4
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by limin112 on GitHub. Read the source before you install it.

Installation

Install the Wechat Publish Template AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/limin112/min-skill/tree/main/skills/wechat-publish-template
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/limin112/min-skill.git /tmp/min-skill
mkdir -p .claude/skills
cp -r /tmp/min-skill/skills/wechat-publish-template .claude/skills/wechat-publish-template
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wechat Publish Template in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wechat Publish Template on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wechat Publish Template is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

wechat-publish-template

把 Markdown 草稿转成可直接粘贴进微信公众号编辑器的 HTML，使用统一的"个人技术风"视觉系统（主橙 #FF5722 + 深黑 #0A0A0A + 浅灰 #F5F5F5）。

何时触发

✅ 触发：

  • 用户给一个 .md 路径并说"转公众号 / 转成公众号 HTML / 套模板 / 排版"
  • 用户贴一段 Markdown 文本并说"做成公众号文章"
  • 用户说"用我的公众号模板"且当前 skill 已装

❌ 不要触发：

  • 用户问"公众号选题怎么选"——这是写作建议，不是排版
  • 用户问"公众号怎么涨粉"——同上
  • 用户要求别的视觉风格（极简、Notion 风等）——本 skill 只输出橙黑赛博朋克风
  • 用户要求把公众号文章反向转成 MD

工作流

Step 1：读输入

  • 如果给了文件路径：Read 该 .md 文件
  • 如果直接贴的文本：直接用
  • 同时 Read references/wechat-html-constraints.md 了解可用/不可用 HTML 特性
  • Read assets/template.html 拿到所有 block 的标准写法

Step 2：拆 MD 结构 → 选 block

按下表把 MD 结构映射到模板 block：

MD 模式对应 block说明
文档第一个 # 标题cover大标题封面，副标题用 tagline
紧跟在标题后的 1-3 句开场intro套"导语"标签
## 二级标题numbered-heading自动编号 01/02/03…，编号取章节顺序
普通段落paragraph默认正文
> 引用块quote套"引用块"装饰
段落中含"结论 / 重点 / 一句话"等关键词callout-key升级成"重点结论"卡片
```代码 ```code行号 + 深色配色
数字列表 + "第一步/第二步" 或 1-3 步骤steps三列卡片，最多 3 个；超过则降级为 ordered list
![alt](url) 图片figure提醒用户在公众号编辑器里手动替换为上传后 URL
- [x] 任务列表 或 项目数 ≥ 4 的并列短句checklist双列勾选
文末"## 总结 / 最后 / 写在最后"summary套"总结"卡片
文末关注引导cta-follow黑底关注 CTA，二维码占位

Step 3：拼装

按 MD 章节顺序把 block 拼起来，包在最外层 <section style="max-width:677px;margin:0 auto;..."> 里。max-width:677px 是公众号正文宽度的最佳值。

Step 4：输出

  • 默认输出到 MD 同目录，文件名 <原文件名>.wechat.html
  • 如果用户没给文件路径，输出到 ./output.wechat.html
  • 输出后告诉用户三件事：
    1. HTML 文件路径
    2. 使用流程：浏览器打开 → 全选复制 → 公众号编辑器粘贴
    3. 图片需要在公众号编辑器里手动重新上传

同步到微信公众号（wechatsync CLI）

排版好的 HTML 可以用 wechatsync CLI 直接同步到公众号草稿箱，免去手动复制粘贴。

⚠️ 平台 key 是 weixin，不是 wechat。 wechatsync 体系里微信公众号的 driver 名就叫 weixin，用 wechat 会报「找不到平台」。而且 sync 不写 -p 时默认发去 zhihu,juejin，所以发公众号必须显式 -p weixin。

bash
wechatsync sync "<文件名>.wechatsync.html" -p weixin --timeout 60000

前提（缺一不可）：

  • 常用 Chrome 里装了扩展「文章同步助手」(Wechatsync)，且已登录公众号后台
  • 扩展的「同步桥接」开关打开
  • CLI ↔ 扩展走 WebSocket 9527 端口：CLI 是监听方、扩展是连接方——必须先跑 wechatsync sync（它才起 9527 监听），扩展再自动连上来。光点扩展图标不会同步本地 HTML。命令一直卡住不返回 = 扩展没连上（没装 / 没开桥接 / 常用 Chrome 没开）。

.wechatsync.html vs .wechat.html：

  • .wechat.html：<img src> 留空，走"浏览器打开 → 全选复制 → 编辑器粘贴"的手动流（见 Step 4）
  • .wechatsync.html：<img src> 填本地绝对路径，交给扩展自动上传到素材库。要走 CLI 同步就额外生成这个变体。

同步过去通常落在草稿箱，不会直接群发。

必守规则

  1. 全部 inline style——禁止生成 <style> 块或 class 属性
  2. 不要 JS / 不要伪元素 / 不要 transform——参见 references/wechat-html-constraints.md
  3. 保留 emoji——但装饰用的几何字符（▶ ★ ◎ ⚡）只能在 <section> 内做装饰，不要靠它承载语义
  4. 图片 src 留空或填 "REPLACE_IN_WECHAT_EDITOR"——.wechat.html（手动粘贴流）里绝不嵌入本地路径或外链。例外：要走 wechatsync CLI 同步时，另存一份 .wechatsync.html，src 填本地绝对路径供扩展上传（见上节「同步到微信公众号」）
  5. 链接保留但提示——告诉用户公众号会剥外链
  6. 色板锁死：主橙 #FF5722、深黑 #0A0A0A、文字 #1A1A1A、浅灰 #F5F5F5，不要自创颜色

调用示例

用户："把 /path/to/draft.md 转成公众号" → 读文件 → 拆结构 → 拼 block → 写到 /path/to/draft.wechat.html → 报告

用户："这段贴一下：[一段 MD]，做成公众号" → 直接拆 → 拼 → 写到 ./output.wechat.html → 报告

资源

  • assets/template.html：完整模板（所有 block 的标准写法 + HTML 注释里的 block 名）
  • references/wechat-html-constraints.md：公众号编辑器 HTML 限制速查
  • evals/evals.json：测试用例（用 Anthropic skill-creator 的评测流程跑）

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wechat Publish Template AI skill do?

把 Markdown 文章转成"个人技术风"公众号 HTML（橙黑赛博朋克风格）。用户提供 .md 文件路径，或贴一段 Markdown，并说"转成公众号"/"做成公众号排版"/"套公众号模板"时触发。产物是单一 HTML 文件，全 inline style，可直接在浏览器打开后全选复制粘贴到微信公众号编辑器。不要在用户只是问"如何写公众号"或"公众号选题"这类非排版问题时触发。

Why use Wechat Publish Template on TypingMind?

Because you install it once and use it with any model. Wechat Publish Template is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wechat Publish Template in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/limin112/min-skill/tree/main/skills/wechat-publish-template. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wechat Publish Template?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wechat Publish Template?

As many as you like. As long as a model supports skills, you can use Wechat Publish Template with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wechat Publish Template AI skill free?

It is published on GitHub by limin112. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Clawhub

openclaw
OrganizationPopular

Search ClawHub for skills when a requested capability is not already available; install, verify, update, uninstall, publish, or sync skills.

82.2K
391K
Instructions
View
obra logo

Diagnosing Superpowers

obra
CommunityPopular

Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so…

26.3K
293.5K
19 files
View
obra logo

Brainstorming

obra
CommunityPopular

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

25.8K
288.1K
7 files
View
obra logo

Executing Plans

obra
CommunityPopular

Use when you have a written implementation plan to execute in a separate session with review checkpoints

25.8K
288.1K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇