Space Wechat Layout logo

Space Wechat Layout

CommunityPopular
SpaceZephyr
space-wechat-layout

微信公众号排版。Use when the user asks to turn an article, Markdown draft, longform post, essay, newsletter, review, or Chinese article into a WeChat Official Account-ready HTML layout with local preview, selectable Claude/OpenAI/Google-inspired styles, and a button to copy rich HTML for pasting into the WeChat editor.

Overview

PublisherSpaceZephyr
Repositorycreator-buddy
Skill namespace-wechat-layout
Stars
1.5K
Forks
234
Bundled files
3
Links
  • 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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Space Wechat Layout 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.
  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/SpaceZephyr/creator-buddy.git /tmp/creator-buddy
mkdir -p .claude/skills
cp -r /tmp/creator-buddy/gzh-Skills/space-wechat-layout .claude/skills/space-wechat-layout
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Space Wechat Layout 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 Space Wechat Layout 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 Space Wechat Layout 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.

微信公众号排版

Create a local HTML preview page that renders a provided article as WeChat-compatible rich HTML and includes a “复制 HTML” button. Preserve the article's meaning and content; only make light structural adjustments for layout readability.

公众号配图适配

定位:这是公众号「整篇视觉/排版」这一路——用户给文章内容,你输出可直接贴进公众号编辑器的 HTML 排版复制 HTML 一键搬运)。是本集合里配图 Skill 的搭档:space-chart-image / space-text-logic-diagram单张配图,本 Skill 出整篇排版

输出:默认 HTML(本 Skill 主路径)。需要把某个区块(如头图/金句卡)导出成图片时,对该区块截图导出 PNG,或交给 Codex/workbuddy 内置出图模型重绘。

内容不改写:只做排版层面的轻调整,保留全部事实、顺序、引用、结论。

Workflow

  1. Collect the article

    • If the user has not provided the article, ask them to paste it.
    • Detect title from the first # heading or first strong title-like line. If unclear, ask for a title.
  2. Ask for style

    • Ask which style to use unless the user already specified one:
      • Claude: warm off-white, calm editorial, restrained borders, generous whitespace.
      • OpenAI: crisp white, black/gray, utilitarian documentation feel.
      • Google: bright white, soft blue/green/yellow/red accents, modular cards.
    • If the user says “你来定”, choose based on content:
      • reflective/narrative/opinion → Claude
      • technical/tutorial/product notes → OpenAI
      • data/list/comparison/education → Google
    • Read references/style-guide.md only when implementing the chosen style or when comparing styles.
  3. Prepare the content

    • Do not rewrite the article substantially.
    • Keep all facts, order, quotes, scores, names, and conclusions intact.
    • Allow only layout-oriented optimization:
      • normalize heading levels;
      • split very long paragraphs;
      • convert obvious tables/lists into styled HTML tables/cards;
      • wrap long body sections in scrollable preview windows if the user asks or if a section is very long.
  4. Build the local preview

    • Prefer a single static index.html when possible.
    • If working inside an existing Vite/front-end app, follow the app's current structure instead of creating a separate stack.
    • Include:
      • a top toolbar;
      • a 复制 HTML button;
      • a visible status message after copying;
      • a centered WeChat content preview (max-width: 677px);
      • responsive mobile layout.
    • The copied payload must be the inner article HTML, not the whole app chrome.
  5. Copy behavior

    • Use the Clipboard API with both text/html and text/plain.
    • Fall back to selecting the preview node and document.execCommand("copy").
    • Button text must be clear: 复制 HTML or 复制到公众号.
  6. WeChat HTML constraints

    • Use inline styles inside the copied article HTML.
    • Avoid external CSS, scripts, web fonts, CSS variables, SVG-only essential content, and interactive controls inside the copied article.
    • Keep cards at border-radius: 8px or less unless the chosen style specifically needs smaller corners.
    • Use simple semantic blocks: section, h1, h2, h3, p, table, blockquote.
    • For scrollable essay/body windows, inline style the article section with max-height and overflow-y:auto; keep headings, score summaries, and conclusions outside the scroll window.
  7. Verify

    • Run the project build command if available.
    • Start or reuse a local dev server.
    • Confirm the local URL responds.
    • If Browser is available and stable, visually inspect the page; otherwise report build/server verification.

Output Shape

Create or update files in the current project. For a plain static page, use:

text
wechat-layout-output/
├── index.html
└── assets/        # only if local images are needed

For an existing app, update the app's normal entry files and keep the server URL unchanged when feasible.

Default Preview Shell

The preview page should include this behavior, adapted to the project:

js
async function copyArticleHtml(articleNode, statusNode) {
  const html = articleNode.innerHTML;
  const text = articleNode.innerText;
  try {
    await navigator.clipboard.write([
      new ClipboardItem({
        "text/html": new Blob([html], { type: "text/html" }),
        "text/plain": new Blob([text], { type: "text/plain" }),
      }),
    ]);
    statusNode.textContent = "已复制 HTML,可以粘贴到公众号正文区域。";
  } catch {
    const range = document.createRange();
    range.selectNode(articleNode);
    const selection = window.getSelection();
    selection.removeAllRanges();
    selection.addRange(range);
    document.execCommand("copy");
    selection.removeAllRanges();
    statusNode.textContent = "已用兼容模式复制当前预览内容。";
  }
}

Final Response

Tell the user:

  • the local preview URL;
  • which style was used;
  • which files were created or changed;
  • how to copy and paste into WeChat;
  • any verification that passed or could not be run.

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 Space Wechat Layout AI skill do?

微信公众号排版。Use when the user asks to turn an article, Markdown draft, longform post, essay, newsletter, review, or Chinese article into a WeChat Official Account-ready HTML layout with local preview, selectable Claude/OpenAI/Google-inspired styles, and a button to copy rich HTML for pasting into the WeChat editor.

Why use Space Wechat Layout on TypingMind?

Because you install it once and use it with any model. Space Wechat Layout 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 Space Wechat Layout in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SpaceZephyr/creator-buddy/tree/main/gzh-Skills/space-wechat-layout. 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 Space Wechat Layout?

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 Space Wechat Layout?

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

Is the Space Wechat Layout AI skill free?

It is published on GitHub by SpaceZephyr. 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.

View all

Set up your own AI workspace now

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