Agent Skills › ymx10086/ResearchClaw › news

news

GitHub

用于获取并总结来自政治、财经、社会等领域的最新新闻。当用户询问新闻或特定类别资讯时，通过browser_use工具访问指定源页面，提取标题和要点进行回复。

src/researchclaw/agents/skills/news/SKILL.md ymx10086/ResearchClaw

Trigger Scenarios

用户请求查看最新新闻用户询问今日头条用户查询特定类别的新闻

Install

npx skills add ymx10086/ResearchClaw --skill news -g -y

More Options

Non-standard path

npx skills add https://github.com/ymx10086/ResearchClaw/tree/main/src/researchclaw/agents/skills/news -g -y

Use without installing

npx skills use ymx10086/ResearchClaw@news

指定 Agent (Claude Code)

npx skills add ymx10086/ResearchClaw --skill news -a claude-code -g -y

安装 repo 全部 skill

npx skills add ymx10086/ResearchClaw --all -g -y

预览 repo 内 skill

npx skills add ymx10086/ResearchClaw --list

SKILL.md

Frontmatter

{
    "name": "news",
    "emoji": "📰",
    "requires": [],
    "description": "Fetch and summarize the latest news from trusted sources across politics, finance, society, world, tech, sports, and entertainment. Use when the user asks for latest news, headlines, or news in a specific category."
}

News Reference

When the user asks for "latest news", "what's in the news today", or "news in category X", use the browser_use tool with the categories and URLs below: open the page, take a snapshot, then extract headlines and key points from the page content and reply to the user.

Categories and Sources

Category	Source	URL
Politics	People's Daily · CPC News	https://cpc.people.com.cn/
Finance	China Economic Net	http://www.ce.cn/
Society	China News · Society	https://www.chinanews.com/society/
World	CGTN	https://www.cgtn.com/
Tech	Science and Technology Daily	https://www.stdaily.com/
Sports	CCTV Sports	https://sports.cctv.com/
Entertainment	Sina Entertainment	https://ent.sina.com.cn/

How to Use (browser_use)

Clarify the user's need: Determine which category or categories (politics / finance / society / world / tech / sports / entertainment), or pick 1–2 to fetch.
Pick the URL: Use the URL from the table for that category; for multiple categories, repeat the steps below for each URL.
Open the page: Call browser_use with:
```
{"action": "open", "url": "https://www.chinanews.com/society/"}
```
Replace url with the corresponding URL from the table.
Take a snapshot: In the same session, call browser_use again:
```
{"action": "snapshot"}
```
Extract headlines, dates, and summaries from the returned page content.
Summarize the reply: Organize a short list (headline + one or two sentences + source) by time or importance; if a site is unreachable or times out, say so and suggest another source.

Notes

Page structure may change when sites are updated; if extraction fails, say so and suggest the user open the link directly.
When visiting multiple categories, run open for each URL, then snapshot, to avoid mixing content from different pages.
You may include the original link in the reply so the user can open it.