Wechat Article Formatter

WeChat Article Formatter & Publisher

Format markdown articles with bm.md styling and publish directly to WeChat Official Account drafts via the official API.

Overview

1. Read markdown file (typically wechat.md from article directory)
2. Upload local images to WeChat CDN via media/uploadimg API
3. Replace local image paths with WeChat CDN URLs in markdown
4. Render markdown to styled HTML via bm.md API with custom CSS
5. Publish to WeChat draft via official draft/add API

CRITICAL: Do NOT use third-party publishing APIs (e.g. 微绿 wechat-publish). They strip inline CSS styles. Always use WeChat's official draft/add API directly.

Credentials

Read from ~/.env:

If not found, prompt the user to provide them and save to ~/.env.

Workflow

Step 1: Identify Input

The user provides a markdown file path (e.g. wechat.md in an article directory).

Detect the article directory to find:

• promotion.md → extract digest/summary
• _attachments/ → local images
• Brand config from the conversation context → author name

Step 2: Get WeChat Access Token

params = urlencode({
    'grant_type': 'client_credential',
    'appid': WECHAT_APP_ID,
    'secret': WECHAT_APP_SECRET
})
# GET https://api.weixin.qq.com/cgi-bin/token?{params}

If error 40164 (IP not in whitelist), instruct user to add the IP at: mp.weixin.qq.com → 设置与开发 → 基本配置 → IP白名单.

Step 3: Upload Images to WeChat CDN

CRITICAL: Upload ALL images in the SAME session. WeChat CDN URLs from previous sessions may expire.

Use media/uploadimg API for inline content images:

# POST https://api.weixin.qq.com/cgi-bin/media/uploadimg?access_token={token}
# Content-Type: multipart/form-data
# Body: media=@image_file
# Response: {"url": "http://mmbiz.qpic.cn/..."}

Use material/add_material API for cover/thumb image:

# POST https://api.weixin.qq.com/cgi-bin/material/add_material?access_token={token}&type=image
# Content-Type: multipart/form-data
# Body: media=@cover_image
# Response: {"media_id": "...", "url": "..."}

For remote images (e.g. https://i.ibb.co/...), download first, then upload to WeChat CDN.

After uploading, replace all local/remote image paths in the markdown with WeChat CDN URLs before rendering.

Step 4: Render with bm.md

Read custom CSS from {{SKILL_DIR}}/styles/custom.css.

IMPORTANT: Write the JSON payload to a temp file and use curl -d @file to avoid shell escaping issues.

payload = json.dumps({
    "markdown": md_content,
    "markdownStyle": "green-simple",
    "codeTheme": "kimbie-light",
    "customCss": css_content,
    "enableFootnoteLinks": True,
    "openLinksInNewWindow": True,
    "platform": "wechat"
}, ensure_ascii=False)

# Write to /tmp/bm-payload.json, then:
# curl -s -X POST https://bm.md/api/markdown/render \
#   -H "Content-Type: application/json" \
#   -d @/tmp/bm-payload.json

The ensure_ascii=False is critical — without it, Chinese characters become \uXXXX escape sequences.

Step 5: Publish to WeChat Draft

draft_payload = json.dumps({
    "articles": [{
        "title": title,
        "author": author,                    # e.g. "在悉尼和稀泥"
        "thumb_media_id": thumb_media_id,     # from Step 3 material upload
        "content": html,                      # from Step 4 bm.md render
        "digest": digest,                     # from promotion.md, max ~60 Chinese chars
        "need_open_comment": 1,               # enable comments
        "only_fans_can_comment": 0,           # allow all users to comment
        "original_article_type": 1,           # declare as original content
        "reward_wording": "喜欢这篇文章，请我喝杯咖啡",  # enable tipping
        "creation_source_type": 1             # 个人观点，仅供参考
    }]
}, ensure_ascii=False).encode('utf-8')

# POST https://api.weixin.qq.com/cgi-bin/draft/add?access_token={token}

Default publish settings:

Digest extraction from promotion.md:

Look for ## 文章摘要 section, extract text, truncate to ~60 Chinese characters (WeChat limit is 120 bytes).

Author resolution (first match wins):

1. User explicitly specified
2. Brand config author field
3. Brand config 品牌名称 field

Step 6: Report Result

WeChat Publishing Complete!

Title: {title}
Author: {author}
Digest: {digest}
Original: ✓ declared
Tipping: ✓ enabled
Comments: ✓ open to all
Images: {N} uploaded to WeChat CDN
media_id: {media_id}

→ Preview at: https://mp.weixin.qq.com (内容管理 → 草稿箱)

Markdown Content Order for WeChat

When building the WeChat markdown, elements should appear in this order:

1. 关注引导文字 (e.g. 👆 「关注」加「星标」...)
2. 封面图 (cover image)
3. --- 分隔线
4. 正文内容 (article body with inline images)
5. --- 分隔线
6. 作者介绍 (about author section)
7. --- 分隔线
8. 推广区块 (promo blockquote with image)
9. --- 分隔线
10. 互动引导 (engagement CTA)

The H1 title should be REMOVED from markdown — WeChat displays its own title from the title field.

Common Pitfalls

bm.md API Reference

Render: POST https://bm.md/api/markdown/render

Available styles: ayu-light, bauhaus, blueprint, botanical, green-simple, maximalism, neo-brutalism, newsprint, organic, playful-geometric, professional, retro, sketch, terminal

Styling Features

The custom CSS (styles/custom.css) provides:

• Optima/Microsoft YaHei fonts
• Green accent color (rgb(53, 179, 120))
• H2 headings: white text on black background
• Bold text: green color
• Blockquotes: green left border
• Responsive tables with alternating row colors
• Code blocks with dark background

Dependencies

• WeChat Official Account API credentials (~/.env)
• bm.md rendering service (no auth required)
• Custom CSS at {{SKILL_DIR}}/styles/custom.css

新手上路（用户不知道该输入什么时，走这里）

触发：/公众号排版 新手、「这个怎么用」「第一次用」「能干嘛」「带我走一遍」， 以及用户输入了技能名却没有给任何任务的时候。

这个模式的铁律：不假设、不索取。用户可能什么都没准备， 不要一上来就问他要文件、要 API key、要具体需求。按下面四步走：

一、先说清楚这是什么（三句话以内）

一句话：把 Markdown 排成公众号能直接用的样式。 公众号编辑器不认 Markdown，手动调格式很费时间， 这个技能把排版做完，还能换主题。

二、给编号选项，让他按回车就能继续

不要问开放式问题（「你想做什么？」对新手是负担）。给 3 个选项加一个默认：

想先看哪个？（直接回车 = 1）
  1. 先看看排出来长什么样（示例）
  2. 排我的这篇 Markdown
  3. 有哪些主题可以选

三、直接演示一遍，边做边解释

选完立刻做给他看，用示例数据，不需要他提供任何东西。 每做完一步，加一行「💡 刚才发生了什么」，一句话说明这步的意义。

四、毕业

演示完只问一个是非题：「要不要用你自己的文章真跑一遍？」 答是就进正常流程；答否就告诉他随时回来输 /公众号排版 新手。