WeChat Official Account topic planning and content calendar management. Based on WeChat article search and trending analysis, generates differentiated topic recommendations and outputs structured content calendars. Activated when users mention "topic", "planning", "content calendar", "trending", or "what to write next week".
Node.js + cheerio (install once):
npm install -g cheerio
| Script | Purpose | Usage |
|---|---|---|
scripts/wechat_search.js | Sogou WeChat article search | node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "keyword" |
IMPORTANT: Always use the $SKILLS_ROOT environment variable to locate scripts.
# Basic search
node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "keyword"
# Limit result count
node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "keyword" -n 15
# Save to file
node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "keyword" -n 20 -o result.json
# Parse real URLs (extra network requests, may be blocked by anti-scraping)
node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "keyword" -n 5 -r
Output Fields: Article title, article URL, article summary, publish time, source account name
Confirm the following information with the user (ask all at once):
帮你规划内容,先确认几件事:
1. 规划周期?(本周 / 下周 / 自定义时间范围)
2. 有没有特定想写的方向或关键词?
3. 每周几篇?(默认3篇)
Execute multiple rounds of searches covering different dimensions:
Search Strategy:
# Example: Tech domain
node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "AI 最新趋势" -n 10
node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "大模型应用" -n 10
node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "科技热点 2026" -n 10
Wait 3-5 seconds between each search to avoid triggering anti-scraping mechanisms.
Extract from search results:
| Analysis Dimension | Extracted Content |
|---|---|
| Title Strategy | Which title patterns get high engagement |
| Topic Direction | Which directions are recent hot topics |
| Content Angle | What angles do existing articles take, how to differentiate |
| Publish Time | Competitors' publishing frequency and timing |
Based on trending data and competitor analysis, generate 5-10 topic suggestions. Each topic must include:
Topic Quality Requirements:
This is a mandatory approval gate and cannot be skipped.
Present the topic list and ask user to select, adjust, and schedule.
Output content_calendar.json:
{
"week": "2026-W13",
"created_at": "2026-03-25",
"articles": [
{
"id": 1,
"date": "2026-03-26",
"day": "Wednesday",
"topic": "Topic Title",
"angle": "Differentiation Angle",
"style": "deep-analysis",
"audience": "Target Audience",
"urgency": "this-week",
"status": "planned",
"keywords": ["keyword1", "keyword2"]
}
]
}
Present a summary table and prompt user to start writing with article-writer skill.
-r parameter for parsing real URLs has low success rate, avoid unless necessarycontent_calendar.json is the input source for article-writerplanned from the calendar