Skip to content
SkillModel-led3,192 tokens in use

md2wechat

Operates the md2wechat CLI to turn Markdown into WeChat Official Account HTML, make cover images, create drafts, and prepare drafts for Zhihu, CSDN and Toutiao.

3,819 stars on the repository Custom / Unknowngeekjourneyx/md2wechat-skill · skills/md2wechat
npm install -g @geekjourneyx/md2wechat@3.8.0
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing md2wechat costs

118tokens idle
3,192tokens in use
6,175tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources2/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 37

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

This skill tells an agent how to drive the md2wechat command line tool for Chinese publishing workflows. It routes each request to the right command family: inspect, preview and convert for WeChat articles, image commands for covers and infographics, title suggestions, writing in a creator style, and removal of AI writing traces.

It also covers unpublished drafts for Zhihu, CSDN, Toutiao and the Tencent Cloud Developer Community through a logged-in browser. The agent checks readiness first and only uploads or creates drafts when you ask.

What You Get

  • WeChat-ready HTML from Markdown, with preview and a readiness check before any upload
  • Cover images and infographics from bundled presets or a host image tool
  • Title suggestions and AI-trace removal for existing articles
  • Advanced layout modules validated before conversion
  • Prepared drafts for Zhihu, CSDN, Toutiao and Tencent Cloud Developer Community

Common Use Cases

  • Publishing a Markdown blog post as a WeChat Official Account draft
  • Generating a cover and infographic for an article
  • Rewriting a machine-written article so it reads less like AI
  • Preparing the same article as drafts on several Chinese platforms

What Makes It Unique

It is built around the CLI’s own discovery and readiness output: the agent asks the tool which themes, providers and layout modules exist and does not rely on memory. It keeps publish targets such as article drafts and image posts apart, and it will not fall back silently from API mode to AI mode. Advanced layout modules and the 48 professional themes need the paid API mode.

Under The Hood

The skill is mostly prose that sends the agent to run shell commands for the md2wechat CLI, which must already be installed. API-mode preview and conversion call the md2wechat service over the network with an API key, and uploads and drafts call the WeChat API with your WeChat credentials. Image generation calls the image provider you configure. It writes preview and converted HTML files and temporary formatted Markdown, and it can read a brand profile file in your config folder. The agent can also operate a logged-in browser for cross-platform drafts.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers