Md2wechat

MD to WeChat

Converts Markdown articles to WeChat Official Account formatted HTML with inline CSS and optionally uploads to draft box. Supports two modes:

• API Mode: Fast conversion using md2wechat.cn API
• AI Mode: Generate themed AI requests / prompts for external models such as Claude Code

Quick Start

# Preview HTML (API mode, fast)
md2wechat convert article.md --preview

# Generate AI request / prompt (AI mode, themed)
md2wechat convert article.md --mode ai --theme autumn-warm --preview

# Upload to WeChat draft box
md2wechat convert article.md --draft --cover cover.jpg

Config Location

Before asking the user to edit configuration, check these in order:

1. ~/.config/md2wechat/config.yaml (default and recommended)
2. Environment variables such as MD2WECHAT_BASE_URL
3. Project-local md2wechat.yaml / md2wechat.yml / md2wechat.json

If the user asks how to switch the API domain, change:

• api.md2wechat_base_url in the config file, or
• MD2WECHAT_BASE_URL in the environment

Default API domain:

https://www.md2wechat.cn

Backup domain:

https://md2wechat.app

Default conversion mode:

• If the user does not explicitly pass --mode, convert should be treated as api
• Only use AI mode when the user explicitly asks for --mode ai or clearly requests AI themed conversion

Built-in assets:

• Default themes and the default writer style are bundled with the binary
• Prefer MD2WECHAT_THEMES_DIR / MD2WECHAT_WRITERS_DIR for explicit overrides
• Then check the project-local themes/ / writers/ directories
• Then check ~/.config/md2wechat/themes/ / ~/.config/md2wechat/writers/
• Do not assume the repository directory exists on the agent host

Prompt catalog:

• Before guessing supported providers, themes, or prompt templates, inspect the CLI first
• Use capabilities --json as the first discovery step
• Use providers list --json, themes list --json, and prompts list --json before picking resources
• Prompt overrides use: MD2WECHAT_PROMPTS_DIR → project-local prompts/ → ~/.config/md2wechat/prompts/ → bundled prompts
• Do not assume prompt YAML files exist on disk outside these locations
• Treat CLI discovery output as the source of truth; use repository references only as workflow help or style examples

Recommended discovery flow:

md2wechat capabilities --json
md2wechat providers list --json
md2wechat themes list --json
md2wechat prompts list --json
md2wechat prompts list --kind image --archetype cover --json

For image presets, do not assume archetype is the only truth. Some infographic presets can also be used as covers. Inspect primary_use_case, compatible_use_cases, recommended_aspect_ratios, and default_aspect_ratio from prompts show --json before choosing a preset.

When a task depends on a specific template, inspect it first:

md2wechat prompts show cover-default --kind image --json
md2wechat prompts show cover-hero --kind image --archetype cover --tag hero --json
md2wechat prompts show infographic-dark-ticket-cn --kind image --archetype infographic --tag ticket --json
md2wechat prompts show infographic-handdrawn-sketchnote --kind image --archetype infographic --tag sketchnote --json
md2wechat prompts show infographic-apple-keynote-premium --kind image --archetype infographic --tag apple --json
md2wechat prompts show infographic-victorian-engraving-banner --kind image --archetype infographic --tag victorian --json
md2wechat prompts render cover-default --kind image --var article_title='Example' --json
md2wechat generate_cover --article article.md
md2wechat generate_infographic --article article.md --preset infographic-comparison
md2wechat generate_infographic --article article.md --preset infographic-dark-ticket-cn --aspect 21:9
md2wechat generate_infographic --article article.md --preset infographic-handdrawn-sketchnote
md2wechat generate_infographic --article article.md --preset infographic-apple-keynote-premium
md2wechat generate_infographic --article article.md --preset infographic-victorian-engraving-banner --aspect 21:9
md2wechat generate_image --preset cover-hero --article article.md --model gemini-3-pro-image-preview

Natural Language Image Generation

You can also ask me to generate images using natural language:

Generate Image for Article (Insert into Markdown)

"Help me generate a product concept image at the beginning of article.md"
"Add an image showing the product features after the second paragraph"
"Create a diagram for the comparison section in article.md"

I will:

1. Read the article to understand the context
2. Insert the AI image generation syntax at the appropriate location
3. Call the conversion command to generate and upload the image

Generate Standalone Image (Not for Article)

"Generate an image of a cute cat sitting on a windowsill"
"Create a product concept image: modern smart home device, white design"
"Make a diagram showing the user flow"

I will:

1. Call the image generation command directly
2. Return the generated image URL and WeChat material ID

Natural Language Writing Assistance

You can also ask me to help write articles using creator styles:

Write Article from Idea

"Write an article about self-discipline using Dan Koe style"
"Help me write a post about productivity with a sharp, grounded tone"
"Create a story-style article about my travel experience"

I will:

1. Understand your idea or topic
2. Use the appropriate writing style (default: Dan Koe)
3. Generate article structure and content
4. Extract memorable quotes
5. Optionally generate matching cover image

Refine Existing Content

"Rewrite this article with a more engaging style"
"Polish my article.md with Dan Koe's writing style"
"Make this content more profound and sharp"

I will:

1. Read your existing content
2. Apply the selected writing style
3. Maintain original meaning while improving expression

Generate Cover Only

"Generate a cover image for my article about self-discipline"
"Create a Victorian woodcut style cover for my philosophy piece"

AI Writing Trace Removal (Humanizer)

"Remove AI traces from this article: article.md"
"Humanize this text to make it sound more natural"
"Remove AI writing traces with gentle intensity"
"Rewrite this to sound less like AI generated"

I will:

1. Read the text to identify AI writing patterns (24 types)
2. Remove or rewrite problematic phrases
3. Inject natural human-like expressions
4. Preserve core meaning and tone
5. Return quality score (5 dimensions, /50)

Humanizer can be combined with writing styles:

"Write with Dan Koe style and remove AI traces"
"Use dan-koe style, then humanize the result"

List Available Styles

"Show me all available writing styles"
"What writing styles can I use?"

Available Writing Styles:

• Dan Koe (default): Profound, sharp, grounded - great for personal growth and opinion pieces

Users can add custom styles in writers/ directory. See writers/README.md for details.

Discovery-first Rule

When working as an Agent:

1. Check capabilities --json before assuming a feature exists
2. Check providers list --json before selecting an image provider
3. Check themes list --json before selecting a theme
4. Check prompts list --json before selecting or rendering a prompt template
5. Only fall back to repository references when the CLI discovery output is insufficient

Workflow Checklist

Copy this checklist to track progress:

Progress:
- [ ] Step 1: Analyze Markdown structure and images
- [ ] Step 2: Confirm conversion mode (API/AI) and theme
- [ ] Step 3: Generate HTML with inline CSS
- [ ] Step 4: Process images (upload to WeChat)
- [ ] Step 5: Replace image URLs in HTML
- [ ] Step 6: Preview or upload to draft

Step 1: Analyze Markdown

Read the markdown file and extract:

Image Reference Types:

Step 2: Confirm Mode and Theme

Conversion Mode

Before picking a theme, inspect the live CLI result:

md2wechat themes list --json

AI Themes

These are common built-in examples, not the source of truth:

API Themes (Fast)

These are representative examples. The authoritative list is themes list --json.

Ask the user: "Which mode and theme would you like?" - Only ask if the user doesn't specify in their request.

• API mode (fast): default, bytedance, apple, sports, chinese, cyber
• AI mode (themed): autumn-warm, spring-fresh, ocean-calm

Default: Use API mode if user doesn't specify.

Read references/themes.md for visual intent and prompt examples only. Do not treat it as the authoritative theme inventory.

Step 3: Generate HTML

API Mode

Call md2wechat CLI:

md2wechat convert article.md --mode api

AI Mode

Read the selected style prompt from references/themes.md and generate an AI request / prompt for an external model to continue into WeChat-safe HTML with inline CSS.

Important Rules:

1. All CSS must be inline (in style attributes)
2. No external stylesheets or scripts
3. Use WeChat-safe HTML tags only
4. Image placeholder format: <!-- IMG:0 -->, <!-- IMG:1 -->, etc.

Safe HTML Tags:

• <p>, <br>, <strong>, <em>, <u>, <a>
• <h1> to <h6>
• <ul>, <ol>, <li>
• <blockquote>, <pre>, <code>
• <table>, <thead>, <tbody>, <tr>, <th>, <td>
• <section>, <span> (with inline styles)

Avoid:

• <script>, <iframe>, <form>
• External CSS/JS references
• Complex positioning (fixed, absolute)

Critical for WeChat:

• Create a main <div> container immediately after <body> to hold all global styles
• Specify color explicitly for each <p> tag (WeChat resets to black otherwise)
• Use two <span> tags for heading symbols: one with color+text-shadow, one with solid color

Step 4: Process Images

Image Generation Methods

There are three ways to generate AI images:

Method 1: Natural Language - For Article (Recommended)

Simply describe what you want in plain language:

User: "Generate a product concept image at the beginning of article.md"

User: "Add a comparison chart after the third paragraph"

User: "Create an image showing the workflow diagram in article.md"

How I process natural language requests:

1. Understand the intent - Identify where to insert the image
2. Read the article - Analyze context to create an appropriate prompt
3. Insert the syntax - Add ![alt](__generate:prompt__) at the correct location
4. Show the prompt - Display the generated prompt for transparency
5. Generate and upload - Call the conversion command to complete

Note: Proceed directly with generation. Only ask for confirmation if the prompt is complex or ambiguous.

Example conversation:

User: "Add a product image at the start of my article"
Claude: "I'll add a product concept image at the beginning of article.md.
Based on your article about 'Smart Home Hub', I'll use this prompt:
'A modern smart home hub device, sleek white design with LED indicator
lights, minimalist product photography on a clean white background'
I'll proceed with generating the image."

Method 2: Natural Language - Standalone Image

Generate an image without any article:

User: "Generate an image of a cute cat sitting on a windowsill"
User: "Create a product concept: modern smart home device"
User: "Make a diagram showing user signup flow"

I will:

1. Create an appropriate prompt based on your description
2. Prefer a bundled preset when the image is a cover or infographic
3. Otherwise call: md2wechat generate_image "prompt"
4. Return the WeChat URL and media ID

Use when: You just need an image, not for any article.

Method 3: Manual Syntax

Write the image generation syntax directly in Markdown:

![Product Concept](__generate:A futuristic smart home hub device, sleek design__)

Syntax format: ![alt text](__generate:prompt__)

Processing Images by Type

For each image reference in order:

Local Image

md2wechat upload_image "/path/to/image.png"

Response:

{"success": true, "wechat_url": "https://mmbiz.qpic.cn/...", "media_id": "xxx"}

Online Image

md2wechat download_and_upload "https://example.com/image.png"

AI Generated Image (via CLI)

# Generate with default size (2048x2048 square)
md2wechat generate_image "A cute cat sitting on a windowsill"

# Generate a cover image from bundled prompt presets
md2wechat generate_cover --article article.md

# Generate an infographic from bundled prompt presets
md2wechat generate_infographic --article article.md --preset infographic-process

# Generate with 16:9 ratio for WeChat cover (recommended)
md2wechat generate_image --preset cover-hero --article article.md --size 2560x1440

WeChat Cover Images: For article covers, use 16:9 horizontal ratio (2560x1440 recommended) as it displays better in WeChat's feed and article list. Square images (2048x2048) are cropped in preview.

Note: AI image generation requires IMAGE_API_KEY environment variable.

Image Processing Pipeline:

1. If AI generation: Call image API → get URL
2. If online: Download image to temp
3. If local: Read file
4. Compress if width > 1920px (configurable)
5. Upload to WeChat material API
6. Return wechat_url and media_id
7. Store result for HTML replacement

Step 5: Replace Image URLs

Replace placeholders in HTML:

<!-- Before -->
<!-- IMG:0 -->
<!-- IMG:1 -->

<!-- After -->
<img src="https://mmbiz.qpic.cn/..." />
<img src="https://mmbiz.qpic.cn/..." />

Use the WeChat URLs returned from image processing.

Step 6: Preview or Upload

Ask user:

1. Preview only - Show HTML for review
2. Upload to draft - Create WeChat draft article

Preview Mode

Display HTML in markdown code block for user to copy.

Upload Mode

Create draft and run:

md2wechat convert article.md --draft --cover cover.jpg

Required for draft:

• WECHAT_APPID environment variable
• WECHAT_SECRET environment variable
• Cover image (use --cover or first image in content)

Response:

{"success": true, "media_id": "draft_media_id", "draft_url": "https://mp.weixin.qq.com/..."}

Configuration

Required for WeChat API

Optional for AI Features

How to Get AppID and Secret

1. Visit WeChat Developer Platform
2. Login and select your Official Account
3. Go to Settings & Development → Basic Configuration
4. Find in Developer ID section:
   • Developer ID (AppID): Copy directly
   • Developer Password (AppSecret): Click "Reset" to get
5. Add these values to environment variables or config file

Warning: AppSecret is very important, keep it secure!

Config File Location

~/.config/md2wechat/config.yaml    # Global config
./md2wechat.yaml                    # Project config (higher priority)

Error Handling

Complete Examples

Example 1: Simple Article (No Images)

Input: simple.md

# My First Article

This is a simple article with no images.

Process:

1. Generate HTML with API mode
2. Skip image processing
3. Ask: preview or upload?
4. If upload → create draft

Example 2: Article with Local Images

Input: with-images.md

# Travel Diary

Day 1 in Paris:

![Eiffel Tower](./photos/eiffel.jpg)

Process:

1. Analyze: 1 local image
2. Generate HTML with <!-- IMG:0 --> placeholder
3. Run: upload_image "./photos/eiffel.jpg"
4. Replace placeholder with WeChat URL
5. Preview or upload

Example 3: AI Mode with Theme

Input: story.md

# The Old Library

A story about memories...

Process:

1. User selects AI mode + autumn-warm theme
2. Read theme prompt from references/themes.md
3. Generate themed AI request / prompt
4. Continue in Claude Code or another compatible AI environment to produce HTML

Example 4: AI Image Generation via Natural Language

User Request:

"Help me add a product concept image at the beginning of article.md"

Process:

1. Read article.md to understand the product
2. Create an appropriate image prompt based on context
3. Confirm with user: "I'll use this prompt: '...'"
4. Insert ![Product Concept](__generate:...) at line 2
5. Run conversion command to generate and upload

Result: Image generated and uploaded to WeChat

Example 5: Article with Pre-written Image Syntax

Input: mixed.md

# Tech Review

![Product Photo](./product.jpg)

![Comparison Chart](https://example.com/chart.png)

![Concept Art](__generate:Futuristic gadget design__)

Process:

1. Process 3 images in order
2. Each returns WeChat URL
3. Replace all placeholders
4. Final HTML with all WeChat-hosted images

References

• Style Themes - Detailed style prompts for AI themes
• HTML Guide - WeChat HTML constraints and best practices
• Image Syntax - Image reference syntax and generation
• Writing Guide - Writer style assistant documentation
• Humanizer - AI writing trace removal documentation 🆕
• WeChat API - API reference

Troubleshooting

Configuration Issues

Q: "AppID not configured" error A: Set WECHAT_APPID and WECHAT_SECRET environment variables, or run:

md2wechat config init

Q: Config file not working A: Check config file location. Supported locations:

• ./md2wechat.yaml (current directory, highest priority)
• ~/.md2wechat.yaml
• ~/.config/md2wechat/config.yaml

Image Issues

Q: Image upload fails with "invalid filetype" A: WeChat supports JPG, PNG, GIF. Ensure image is in correct format:

# Convert using ImageMagick
convert input.tiff output.jpg

Q: Images not showing in draft A: Images must use WeChat-hosted URLs (mmbiz.qpic.cn), not external URLs.

Q: AI image generation fails A: Check IMAGE_API_KEY is set and API base URL is correct.

WeChat API Issues

Q: "IP not in whitelist" error A: Add your server IP to WeChat whitelist:

1. Get your public IP:

curl ifconfig.me
# or
curl ip.sb

2. Add IP to WeChat:
   • Visit WeChat Developer Platform
   • Go to Settings & Development → Basic Configuration
   • Find IP Whitelist section
   • Click "Set" and add your IP
   • Wait a few minutes for changes to take effect

Q: "access_token expired" error A: Program auto-refreshes tokens. If persists:

# Check config
md2wechat config show

# Re-init if needed
md2wechat config init

Q: "create draft failed" error A: Possible causes:

1. Insufficient permissions - ensure account is verified
2. Sensitive content - check article content
3. Draft limit reached - check existing drafts
4. Content size out of limit (errcode=45002) - article content exceeds WeChat API limit

Q: "content size out of limit" error (errcode=45002) A: WeChat draft API has content limits:

• Characters: < 20,000 characters (中文算1个字符)
• Size: < 1 MB

If you encounter this error:

1. Shorten your article content
2. Reduce unnecessary formatting (inline CSS adds size)
3. Consider splitting into multiple articles
4. Use simpler themes with less inline styling

API mode generates more inline CSS which increases content size. For very long articles, consider manual editing or splitting.

Q: API rate limit exceeded A: WeChat has API limits. Wait and retry:

# Wait 60 seconds
sleep 60
# Retry
md2wechat convert article.md --draft

HTML/Style Issues

Q: Styles not working in WeChat editor A: Check:

1. CSS uses inline style attributes (not <style> tags)
2. CSS properties are in allowed list (see HTML Guide)
3. No syntax errors (unclosed tags, etc.)

Q: Background color lost in WeChat A: WeChat strips <body> styles. Use main container:

<div style="background-color: #faf9f5; padding: 40px 10px;">
  <!-- All content here -->
</div>

Q: Text color not as expected A: WeChat resets <p> color to black. Always specify:

<p style="color: #4a413d;">Your text here</p>

Command Issues

Q: "command not found: md2wechat" A: Coding-agent skill 默认要求 md2wechat 已经安装到 PATH，不再自带 runtime wrapper 或执行时下载逻辑。

Install the CLI first, then rerun the skill:

curl -fsSL https://github.com/geekjourneyx/md2wechat-skill/releases/download/v2.0.3/install.sh | bash
npx skills add https://github.com/geekjourneyx/md2wechat-skill --skill md2wechat

If the installer finished but the current shell still cannot find md2wechat, run:

export PATH="$HOME/.local/bin:$PATH"
md2wechat version --json

Q: AI mode very slow A: AI mode requires Claude API call and takes 10-30 seconds. For faster results, use API mode.

CLI Commands Reference

This skill assumes the md2wechat CLI is already installed and available on PATH:

# Show help
md2wechat --help

# Convert and preview
md2wechat convert article.md --preview

# Convert with AI theme
md2wechat convert article.md --mode ai --theme autumn-warm --preview

# Convert and upload to draft
md2wechat convert article.md --draft --cover cover.jpg

# Upload single image
md2wechat upload_image photo.jpg

# Download and upload online image
md2wechat download_and_upload https://example.com/image.jpg

# Generate AI image (requires IMAGE_API_KEY)
md2wechat generate_image "A cute cat sitting on a windowsill"

# Generate cover image from bundled presets
md2wechat generate_cover --article article.md

# Generate infographic image from bundled presets
md2wechat generate_infographic --article article.md --preset infographic-comparison

# Generate with 16:9 ratio for WeChat cover via preset (recommended)
md2wechat generate_image --preset cover-hero --article article.md --size 2560x1440

# Initialize config
md2wechat config init

# Show config
md2wechat config show

# List available writing styles
md2wechat write --list

# Write with creator style (interactive)
md2wechat write

# Write with specific style (via stdin/piped)
echo "你的想法或内容" | md2wechat write --style dan-koe

# Write with title and heredoc
md2wechat write --style dan-koe --title "文章标题" <<EOF
你的内容
EOF

# Write with specific style
md2wechat write --style dan-koe

# Generate cover prompt only
md2wechat write --style dan-koe --cover-only

# Remove AI writing traces (humanize)
md2wechat humanize article.md

# Humanize with intensity
md2wechat humanize article.md --intensity aggressive

# Write with humanize
md2wechat write --style dan-koe --humanize

# Create image post (小绿书/newspic)
md2wechat create_image_post -t "Title" --images photo1.jpg,photo2.jpg

# Extract images from Markdown
md2wechat create_image_post -t "Title" -m article.md

# With description and comments
md2wechat create_image_post -t "Title" -c "Description" --images photo.jpg --open-comment

# Preview mode (dry-run)
md2wechat create_image_post -t "Test" --images a.jpg,b.jpg --dry-run

Image Posts (小绿书/Newspic)

Create WeChat image-only posts (小绿书/图片消息) with up to 20 images.

Natural Language

"Create an image post titled 'Weekend Trip' with photos from ./photos/"
"Make a 小绿书 post with travel.md images"
"Upload these images as an image post: a.jpg, b.jpg, c.jpg"

Command Options

Examples

# Basic image post
md2wechat create_image_post \
  -t "Weekend Trip" \
  --images photo1.jpg,photo2.jpg,photo3.jpg

# Extract images from article
md2wechat create_image_post \
  -t "Travel Diary" \
  -m article.md

# With description and comments enabled
md2wechat create_image_post \
  -t "Food Blog" \
  -c "Today's lunch" \
  --images food.jpg \
  --open-comment

# Read description from stdin
echo "Daily check-in" | md2wechat create_image_post \
  -t "Daily" \
  --images pic.jpg

# Preview mode
md2wechat create_image_post \
  -t "Test" \
  --images a.jpg,b.jpg \
  --dry-run

Notes

• Image limit: Maximum 20 images per post
• Image format: JPG, PNG, GIF (same as regular articles)
• Content: Plain text only, not HTML
• Requires: WECHAT_APPID and WECHAT_SECRET for upload