Wewrite Wechat AI Publishing

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:

export WECHAT_APPID="wx1234567890abcdef"
export WECHAT_SECRET="your_secret_here"
export DOUBAO_API_KEY="your_doubao_key"
export OPENAI_API_KEY="sk-..."

Triggering the Full Pipeline

Once installed as a Claude Code skill, simply say:

用 demo 的配置写一篇公众号文章

Claude will execute all steps automatically using clients/demo/style.yaml as the client profile.

You can also specify a client:

用 clients/tech-blog 的风格，围绕今日热点写一篇公众号文章，发布到草稿箱

Pipeline Steps & Scripts

1. Fetch Hotspots

Scrapes real-time trending topics from Weibo, Toutiao, and Baidu.

python3 scripts/fetch_hotspots.py --limit 20
python3 scripts/fetch_hotspots.py --limit 10 --json   # JSON output

Output example:

[
  {"rank": 1, "title": "DeepSeek R2 发布", "source": "weibo", "heat": 98200},
  {"rank": 2, "title": "A股科技板块大涨", "source": "baidu", "heat": 75300}
]

2. SEO Keyword Analysis

Queries Baidu and 360 search suggestions to score keywords.

python3 scripts/seo_keywords.py "AI大模型" "科技股"
python3 scripts/seo_keywords.py --json "ChatGPT" "人工智能"

Python usage:

from scripts.seo_keywords import analyze_keywords

results = analyze_keywords(["AI大模型", "大语言模型", "GPT-5"])
for kw in results:
    print(f"{kw['keyword']}: score={kw['score']}, volume={kw['estimated_volume']}")

3. Topic Selection

Claude reads references/topic-selection.md and generates 10 candidate topics scored on:

• 热度 (trending heat)
• 契合度 (client fit)
• 差异化 (differentiation)

4. Framework & Writing

Claude reads references/frameworks.md (5 frameworks) and references/writing-guide.md (de-AI style rules), then writes the article adapted to the client's tone.

5. AI Image Generation

# Cover image (recommended 900×383)
python3 toolkit/image_gen.py \
  --prompt "科技感封面，蓝色光线，未来感" \
  --output output/cover.png \
  --size cover

# Inline content image
python3 toolkit/image_gen.py \
  --prompt "程序员在办公室工作，现代风格插画" \
  --output output/img1.png \
  --provider openai

Python usage:

from toolkit.image_gen import generate_image

path = generate_image(
    prompt="AI机器人与人类握手，科技感插画",
    output_path="output/cover.png",
    size="cover",          # "cover" (900x383) or "content" (800x600)
    provider="doubao"      # "doubao" or "openai"
)
print(f"Generated: {path}")

6. Formatting — Markdown → WeChat HTML

WeChat requires inline styles. The converter handles this automatically.

# Preview in browser
python3 toolkit/cli.py preview article.md --theme professional-clean

# Available themes
python3 toolkit/cli.py themes

Python usage:

from toolkit.converter import MarkdownConverter
from toolkit.theme import load_theme

theme = load_theme("tech-modern")
converter = MarkdownConverter(theme=theme)

with open("article.md") as f:
    markdown_content = f.read()

html = converter.convert(markdown_content)
# html is WeChat-ready with all inline styles

7. Publish to WeChat Draft Box

python3 toolkit/cli.py publish article.md \
  --cover output/cover.png \
  --title "2026年AI大模型最新进展" \
  --author "科技观察"

Python usage:

from toolkit.publisher import WeChatPublisher
from toolkit.wechat_api import WeChatAPI

api = WeChatAPI(appid=os.environ["WECHAT_APPID"], secret=os.environ["WECHAT_SECRET"])
publisher = WeChatPublisher(api=api)

# Upload cover image first
media_id = api.upload_image("output/cover.png")

# Push to draft box
draft_id = publisher.create_draft(
    title="2026年AI大模型最新进展",
    content=html_content,          # inline-styled HTML from converter
    cover_media_id=media_id,
    author="科技观察",
    digest="本文盘点2026年大模型最新进展..."   # summary/excerpt
)
print(f"Draft created: {draft_id}")

8. Fetch Article Stats (回填数据)

python3 scripts/fetch_stats.py --article-id "your_article_id"

9. Learn from Manual Edits

python3 scripts/learn_edits.py \
  --original output/draft.md \
  --edited output/final.md \
  --client demo

Extracts style rules from diffs and appends them to the client's playbook.

Client Configuration

Each client lives in clients/{name}/style.yaml:

# clients/my-tech-blog/style.yaml
name: "我的科技博客"
industry: "科技/AI"
topics:
  - "人工智能"
  - "大模型应用"
  - "编程技术"
tone: "专业严谨，偶尔幽默，面向中级开发者"
theme: "tech-modern"
avoid:
  - "过度营销语言"
  - "绝对化表述"
wechat:
  appid: "${WECHAT_APPID}"
  secret: "${WECHAT_SECRET}"

Create a new client:

mkdir clients/my-client
cp clients/demo/style.yaml clients/my-client/style.yaml
# Edit style.yaml for your client

Themes

python3 toolkit/cli.py themes          # list all themes with previews
python3 toolkit/cli.py preview article.md --theme warm-editorial

Custom theme (YAML):

# toolkit/themes/my-theme.yaml
name: my-theme
body:
  font-family: "'PingFang SC', sans-serif"
  font-size: "16px"
  color: "#333"
  line-height: "1.8"
h2:
  color: "#1a73e8"
  font-weight: "bold"
  border-left: "4px solid #1a73e8"
  padding-left: "10px"
blockquote:
  background: "#f0f4ff"
  border-left: "3px solid #4285f4"
  padding: "12px 16px"
  color: "#555"

Full Pipeline — Python Orchestration

import subprocess
import json
import os
from toolkit.converter import MarkdownConverter
from toolkit.theme import load_theme
from toolkit.publisher import WeChatPublisher
from toolkit.wechat_api import WeChatAPI
from toolkit.image_gen import generate_image

# 1. Fetch hotspots
result = subprocess.run(
    ["python3", "scripts/fetch_hotspots.py", "--limit", "20", "--json"],
    capture_output=True, text=True
)
hotspots = json.loads(result.stdout)

# 2. SEO analysis on top topics
from scripts.seo_keywords import analyze_keywords
top_titles = [h["title"] for h in hotspots[:5]]
seo_scores = analyze_keywords(top_titles)

# 3. (Claude selects topic, writes article — handled by SKILL.md)
# After Claude produces article.md:

# 4. Generate cover
cover_path = generate_image(
    prompt="科技感封面图，蓝色渐变，数字化未来",
    output_path="output/cover.png",
    size="cover",
    provider=os.environ.get("IMAGE_PROVIDER", "doubao")
)

# 5. Convert Markdown → WeChat HTML
theme = load_theme("tech-modern")
converter = MarkdownConverter(theme=theme)
with open("output/article.md") as f:
    html = converter.convert(f.read())

# 6. Publish to draft box
api = WeChatAPI(
    appid=os.environ["WECHAT_APPID"],
    secret=os.environ["WECHAT_SECRET"]
)
publisher = WeChatPublisher(api=api)
media_id = api.upload_image(cover_path)
draft_id = publisher.create_draft(
    title="选定标题",