# Content Planner

WeChat Official Account topic planning and content calendar management.

- Repository: https://github.com/netease-youdao/LobsterAI (6161 stars)
- Category: Writing
- License: MIT
- Last updated: 2026-10-31
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add netease-youdao/LobsterAI --skill content-planner -g -a claude-code -y`
Codex: `npx skills add netease-youdao/LobsterAI --skill content-planner -g -a codex -y`
Cursor: `npx skills add netease-youdao/LobsterAI --skill content-planner -g -a cursor -y`
Gemini CLI: `npx skills add netease-youdao/LobsterAI --skill content-planner -g -a gemini-cli -y`

## Description

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".

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Topic Planning + Content Calendar

## Use Cases

- User says "帮我规划下周公众号内容"
- User says "最近有什么热门选题可以写"
- User says "帮我做一份内容日历"
- User wants to know what competitor accounts are writing about
- Need to make topic decisions based on data

## Dependencies

Node.js + cheerio (install once):

```bash
npm install -g cheerio
```

## Script Directory

| Script | Purpose | Usage |
|--------|---------|-------|
| `scripts/wechat_search.js` | Sogou WeChat article search | `node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "keyword"` |

### Search Script Parameters

**IMPORTANT:** Always use the `$SKILLS_ROOT` environment variable to locate scripts.

```bash
# 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

## Workflow

### Step 1: Clarify Planning Scope

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）
```

### Step 2: Trending Scan

Execute multiple rounds of searches covering different dimensions:

**Search Strategy:**

1. **Core domain keyword search**, Search with 2-3 core keywords related to the account's field
2. **User-specified keyword search**, If user has specific directions
3. **General trending search**, Search with combinations of "热点", "热门", "最新" with domain keywords

The rest: https://github.com/netease-youdao/LobsterAI/blob/HEAD/SKILLs/content-planner/SKILL.md