Overview
- Skill Key
- hegangsz/news-daily
- Author
- hegangsz
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/hegangsz/news-daily
- Latest Commit SHA
- 0fd9d1e83c9cee013cdc9000957ff109db01f1f8
获取新闻热榜(国内、国际、科技、AI)并发送到飞书。不依赖本地工程,直接从 RSS 获取数据。
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
直接复制以下提示词,发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 news-daily 技能。 若已安装,则直接安装 news-daily 技能。
# 新闻日报 Skill
## 功能
- 从多个 RSS 源获取新闻(国内、国际、科技、AI)
- 格式化为飞书卡片消息(标题可点击)
- 支持定时自动发送
## 安装
```bash
cp -r ~/.openclaw/workspace/skills/news-daily /path/to/your/openclaw/workspace/skills/
```
## 配置
### 1. 创建飞书机器人 Webhook
1. 打开飞书群 → 群设置 → 群机器人 → 添加机器人
2. 选择 "自定义机器人"
3. 复制 Webhook 地址
### 2. 配置 Webhook
方式一:环境变量(推荐)
```bash
export NEWS_DAILY_WEBHOOK="你的Webhook地址"
```
方式二:配置文件
```bash
vim ~/.openclaw/workspace/skills/news-daily/scripts/config.json
```
```json
{
"webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/xxx",
"date": "today",
"categories": {
"国内": 10,
"国际": 10,
"科技": 10,
"AI": 10
}
}
```
## 使用
### 手动执行
```bash
python3 ~/.openclaw/workspace/skills/news-daily/scripts/fetch_and_send.py
```
### 配置定时任务
```bash
openclaw config set hooks.internal.entries.news-daily.enabled true
openclaw config set hooks.internal.entries.news-daily.systemEvent "news-daily"
openclaw config set hooks.internal.entries.news-daily.action.kind "exec"
openclaw config set hooks.internal.entries.news-daily.action.command "python3 ~/.openclaw/workspace/skills/news-daily/scripts/fetch_and_send.py"
openclaw gateway restart
```
## RSS 源
| 分类 | 来源 |
|------|------|
| 国内 | 中国新闻网、人民日报 |
| 国际 | 纽约时报、BBC、卫报 |
| 科技 | 36氪、少数派、TechCrunch、The Verge |
| AI | InfoQ、机器之心、MIT 科技评论、VentureBeat |
详细说明见 [README.md](./README.md)
# 新闻日报 (News Daily)
获取每日新闻热榜并发送到飞书群。支持国内、国际、科技、AI 四个分类。
## 功能特点
- 📰 **多源 RSS 聚合** - 自动获取多个 RSS 源
- 🎨 **飞书卡片格式** - 美观的卡片消息,带可点击链接
- ⚙️ **可配置** - 支持自定义新闻分类和数量
- 🤖 **定时自动发送** - 可配置定时任务
## 快速开始
### 1. 安装
```bash
# 克隆或下载此技能到你的 OpenClaw workspace
cp -r news-daily ~/.openclaw/workspace/skills/
```
### 2. 配置 Webhook
你需要配置一个飞书机器人 Webhook:
**创建飞书机器人:**
1. 打开飞书群设置 → 群机器人 → 添加机器人
2. 选择 "自定义机器人"
3. 设置机器人名称(如 "新闻日报")
4. 复制 Webhook 地址
**配置方式(选择一种):**
方式一:环境变量(推荐)
```bash
export NEWS_DAILY_WEBHOOK="你的飞书Webhook地址"
```
方式二:配置文件
```bash
# 编辑 config.json
vim ~/.openclaw/workspace/skills/news-daily/scripts/config.json
```
```json
{
"webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/xxxxx",
"date": "today",
"categories": {
"国内": 10,
"国际": 10,
"科技": 10,
"AI": 10
}
}
```
### 3. 手动发送测试
```bash
python3 ~/.openclaw/workspace/skills/news-daily/scripts/fetch_and_send.py
```
### 4. 配置定时任务
使用 OpenClaw cron:
```bash
# 添加每日 8 点定时任务
openclaw cron add --name "新闻日报" --cron "0 8 * * *" --system-event "news-daily" --session main
```
或者使用 OpenClaw hooks:
```bash
openclaw config set hooks.internal.entries.news-daily.enabled true
openclaw config set hooks.internal.entries.news-daily.systemEvent "news-daily"
openclaw config set hooks.internal.entries.news-daily.action.kind "exec"
openclaw config set hooks.internal.entries.news-daily.action.command "python3 ~/.openclaw/workspace/skills/news-daily/scripts/fetch_and_send.py"
openclaw gateway restart
```
## 配置说明
### config.json 完整配置
```json
{
"webhook_url": "飞书机器人 Webhook 地址",
"date": "today", // 或 yesterday,或具体日期 YYYY-MM-DD
"categories": {
"国内": 10,
"国际": 10,
"科技": 10,
"AI": 10
}
}
```
### RSS...
human-pages-ai
Search and hire real humans for tasks — photography, delivery, research, and more
zseven-w
Reusable skill templates for OpenClaw AI agents. Templates for API integration, data processing, web scraping, CLI tools, and file processing.
capt-marbles
Attio CRM integration for managing companies, people, deals, notes, tasks, and custom objects. Use when working with Attio CRM data, searching contacts, managing sales pipelines, adding notes to records, creating tasks, or syncing prospect information.
capt-marbles
Web scraping and crawling with Firecrawl API. Fetch webpage content as markdown, take screenshots, extract structured data, search the web, and crawl documentation sites. Use when the user needs to scrape a URL, get current web info, capture a screenshot, extract specific data from pages, or crawl docs for a framework/library.
caqlayan
Tweet Processor Skill
carlosarturoleon
Connect to Windsor.ai MCP for natural language access to 325+ data sources including Facebook Ads, GA4, HubSpot, Shopify, and more.