Wewrite Wechat Ai Publishing

A complete pipeline for publishing WeChat Official Account articles, from scraping trending topics on Weibo and Baidu to pushing formatted drafts live. It handles SEO keyword analysis, generates cover images via Doubao or OpenAI, converts Markdown to WeChat's inline-styled HTML, and uploads directly to your draft box. The interesting part is the learning loop: feed it your manual edits and it extracts style rules into client-specific playbooks. Each client gets their own tone config and theme (tech-modern, warm-editorial, minimal). If you're running a Chinese content operation and tired of the copy-paste-format-upload grind, this automates the entire thing. Built by ara.so as part of their Daily 2026 collection.

skills.sh installs: 836
GitHub stars: 61
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill wewrite-wechat-ai-publishing --agent claude-code

Installs into .claude/skills of the current project.

Files

WeWrite — WeChat AI Publishing Skill

Skill by ara.so — Daily 2026 Skills collection.

WeWrite is a full-pipeline AI skill for producing WeChat Official Account (公众号) articles end-to-end: hotspot fetching → topic selection → writing → SEO → AI image generation → formatting → draft box publishing. It runs as a Claude Code skill (via SKILL.md) but every component also works standalone.

Installation

As a Claude Code Skill

# Clone the repo
git clone https://github.com/oaker-io/wewrite.git ~/.claude/skills/wewrite

# Or copy into an existing project
cp -r wewrite ~/.claude/skills/wewrite

Python Dependencies

cd wewrite
pip install -r requirements.txt

Configuration

cp config.example.yaml config.yaml

Edit config.yaml:

wechat:
  appid: "${WECHAT_APPID}"         # WeChat Official Account App ID
  secret: "${WECHAT_SECRET}"       # WeChat Official Account Secret

image_gen:
  provider: "doubao"               # "doubao" or "openai"
  doubao_api_key: "${DOUBAO_API_KEY}"
  openai_api_key: "${OPENAI_API_KEY}"

output_dir: "./output"

Set environment variables instead of hardcoding secrets:

SKILL.md on GitHub