Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
← Back to list

md2wechat Publishing Assistant

A runtime protocol that drives the md2wechat CLI to turn Markdown into WeChat Official Account HTML, with previews, covers, image posts, and gated draft creation.

Content & WritingIntermediate★ 3,681⑂ 414AI score 8/10Last updated: Sep 24, 2026

What it does

  • Converts Markdown articles into WeChat Official Account HTML, plus preview files and structured metadata inspection.
  • Enforces a confirm-first pipeline (inspect → preview → convert) and treats data.readiness.targets/blockers as the publish gate before any upload or draft.
  • Requires live CLI discovery (themes list, layout show, providers show, prompts list) instead of guessing theme names, layout modules, or image providers.
  • Routes distinct intents correctly: article covers, infographics, image-first posts (create_image_post), title suggestions, AI-trace removal (humanize), and style-based drafting (write).
  • Handles unpublished drafts for Zhihu, CSDN, Toutiao, and Tencent Cloud Developer Community via a browser-operated workflow.

Who it's for

  • Creators and marketers who run a WeChat Official Account and write in Markdown.
  • Tech bloggers distributing to Chinese content platforms.
  • Users who already have (or will install) the md2wechat CLI and can manage an API key plus WeChat credentials.

Examples

  1. "Format article.md for WeChat" → discovers themes/layout modules, writes a temporary formatted Markdown artifact, runs layout validate, then converts.
  2. "Generate a cover and push it as a draft" → generate_cover, verify data.readiness.targets.draft, then convert --draft --cover.
  3. "Give me title options for this post" → title suggest article.md --json returns a title-generation request; the skill proposes candidates without rewriting the file.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/geekjourneyx/md2wechat-skill/HEAD/skills/md2wechat/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/md2wechat folder from the GitHub repo geekjourneyx/md2wechat-skill into my ~/.claude/skills/geekjourneyx-md2wechat/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/geekjourneyx/md2wechat-skill.git /tmp/md2wechat-skill && mkdir -p ~/.claude/skills && cp -r /tmp/md2wechat-skill/skills/md2wechat ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS/Linux, WSL or Git Bash on Windows).
  2. Verify the CLI exists: md2wechat version --json. If the command is missing, install the md2wechat CLI first per the project docs.
  3. Clone the skill repo: git clone https://github.com/geekjourneyx/md2wechat-skill.git /tmp/md2wechat-skill
  4. Copy the skill into Claude Code: mkdir -p ~/.claude/skills && cp -r /tmp/md2wechat-skill/skills/md2wechat ~/.claude/skills/
  5. Export your API key: export MD2WECHAT_API_KEY=your_key (add it to ~/.zshrc or ~/.bashrc to persist).
  6. For uploads and draft creation, configure WeChat Official Account credentials, then run md2wechat doctor --json to confirm local readiness.
  7. Restart Claude Code and try a prompt like "convert this Markdown into WeChat HTML" to trigger the skill.
View source on GitHub ↗License: NOASSERTION