Token导航 LogoToken导航TokenDH.com
待分类敏感数据unknown未标认证来源可访问许可证需确认审计未展示

newsmcpnewsmcp 日程管理

Agent Skill

newsmcp 用于补充待分类相关能力,适合在 Local Agent 中需要让 Agent 承接待分类相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

188

周安装

8

下载量

66
Local Agent

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:newsmcp(newsmcp 日程管理)
来源仓库:https://skills.volces.com
仓库路径:newsmcp
安装命令:
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。当前暂无明确安装命令,请以来源页面说明为准。

简介

newsmcp 用于补充待分类相关能力。

  • 适合在 Local Agent 中让 Agent 承接待分类相关任务时使用。
  • 可结合来源仓库和原始 README 核验具体用法,建议确认权限与维护状态。
  • 安装前需评估是否会触发联网、命令执行或文件读写操作。
  • 当前分类为待分类,适用宿主为 Local Agent,安装方式未知。

SKILL.md

World News Skill

Get real-time world news from an AI-powered news aggregation service. Stories are clustered into events (deduplicated across multiple sources), summarized, classified by topic, and tagged by geography.

No API key required. No authentication. Just call the API.

Why This Is Different

  • Events, not articles — individual articles are clustered into stories, so you get one summary per story instead of 20 duplicates
  • Pre-summarized — every event has an AI-generated summary, no need to read full articles
  • Classified — 12 topic categories and 100+ geographic regions
  • Importance signalssources_count (how many outlets covered it) and impact_score (AI-assessed significance)
  • Multi-source — each event lists all source articles with titles, URLs, and domains

API Base URL

https://newsmcp.io/v1

Endpoints

1. Get News Events

curl -s "https://newsmcp.io/v1/news/?hours=24&per_page=10&order_by=-sources_count"

Parameters:

ParameterTypeDefaultDescription
hoursint24Time window (1-168, i.e. up to 7 days)
topicsstringComma-separated topic slugs (e.g. politics,military)
geostringComma-separated geo slugs (e.g. europe,united-states)
pageint1Page number
per_pageint20Results per page (max 50)
order_bystring-sources_countSort field. Options: sources_count, entries_count, impact_score, first_seen_at, last_seen_at (prefix - for descending)

Response shape:

{
  "events": [
    {
      "id": "uuid",
      "summary": "AI-generated event summary",
      "topics": ["politics", "military"],
      "geo": ["europe", "ukraine"],
      "entries_count": 15,
      "sources_count": 8,
      "first_seen_at": "2026-03-03T10:00:00Z",
      "last_seen_at": "2026-03-03T14:00:00Z",
      "impact_score": 4,
      "entries": [
        {
          "title": "Article headline",
          "url": "https://example.com/article",
          "domain": "example.com",
          "published_at": "2026-03-03T12:00:00Z"
        }
      ]
    }
  ],
  "total": 42,
  "page": 1,
  "per_page": 10
}

2. Get Event Detail

curl -s "https://newsmcp.io/v1/news/{event_id}/"

Returns the same fields as the list, plus context — extended background and analysis of the event.

3. List Available Topics

curl -s "https://newsmcp.io/v1/news/topics/"

Returns: politics, economy, technology, science, health, environment, sports, culture, crime, military, education, society

4. List Available Regions

curl -s "https://newsmcp.io/v1/news/regions/"

Returns continents (europe, asia, africa, north-america, south-america, oceania) and countries (e.g. united-states, ukraine, china, lithuania, etc.). Each region has a type field: "continent" or "country".

How to Use This Skill

When the user asks for news, headlines, or current events:

  1. Default briefing — Fetch top events from the last 24 hours sorted by importance: curl -s "https://newsmcp.io/v1/news/?hours=24&per_page=10&order_by=-sources_count"
  2. Topic-specific — If the user asks about a specific topic (e.g. "tech news", "sports"), use the topics parameter: curl -s "https://newsmcp.io/v1/news/?topics=technology&hours=24"
  3. Region-specific — If the user asks about a region (e.g. "European news", "what's happening in Asia"), use the geo parameter: curl -s "https://newsmcp.io/v1/news/?geo=europe&hours=24"
  4. Combined filters — Topics and geo can be combined: curl -s "https://newsmcp.io/v1/news/?topics=politics,military&geo=europe&hours=48"
  5. Deep dive — For more detail on a specific event, fetch the event detail: curl -s "https://newsmcp.io/v1/news/{event_id}/"

Formatting the Briefing

Present results as a multi-story news briefing covering the top events — not just one.

Rules:

  • List each event separately — 1-2 lines per event with its summary, source count, and 1-2 links
  • Lead with the most important events (highest sources_count or impact_score)
  • Related events can be grouped under a shared heading, but don't collapse everything into a single narrative
  • Mention the time window and total number of events found
  • If topics or geo arrays are present, use them to add context tags

Output template:

Here are today's top stories ({N} events in the last {hours}h):

1. **{Event summary}** — {sources_count} sources · [Source Title](url)
2. **{Event summary}** — {sources_count} sources · [Source Title](url)
3. **{Event summary}** — {sources_count} sources · [Source Title](url)
...

What NOT to do:

  • Do NOT present only 1 story when the API returned multiple events (unless the user asked for a single topic)
  • Do NOT write a long essay about one event and ignore the rest
  • Do NOT merge all events into a single combined narrative

Topic Slugs Reference

politics economy technology science health environment sports culture crime military education society

Example Interaction

User: "What's happening in the world today?"

Action: Fetch https://newsmcp.io/v1/news/?hours=24&per_page=10&order_by=-sources_count

Expected output format:

Here are today's top stories (42 events in the last 24h):

1. **US Senate passes infrastructure bill after marathon session** — 34 sources · [Reuters](url) · [AP News](url)
2. **Earthquake strikes eastern Turkey, at least 12 dead** — 28 sources · [BBC](url)
3. **OpenAI announces new reasoning model** — 22 sources · [The Verge](url)
4. **EU imposes new sanctions on Russian energy sector** — 19 sources · [FT](url)
5. **Wildfire in California forces thousands to evacuate** — 15 sources · [LA Times](url)

Want more detail on any of these stories?

User: "Give me the latest on Ukraine"

Action: Fetch https://newsmcp.io/v1/news/?geo=ukraine&hours=48&order_by=-last_seen_at

User: "Any tech news this week?"

Action: Fetch https://newsmcp.io/v1/news/?topics=technology&hours=168&order_by=-sources_count

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Local Agent

76.89%
按下载量换算51

安全审计

暂无安全审计结果可展示。

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills