Back to Details

daily-ai-news

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Daily AI News Briefing

每日AI新闻简报

Aggregates the latest AI news from multiple sources and delivers concise summaries with direct links
聚合来自多渠道的最新AI资讯，提供附带直达链接的简洁摘要

When to Use This Skill

何时使用该功能

Activate this skill when the user:
  • Asks for today's AI news or latest AI developments
  • Requests a daily AI briefing or updates
  • Mentions wanting to know what's happening in AI
  • Asks for AI industry news, trends, or breakthroughs
  • Wants a summary of recent AI announcements
  • Says: "给我今天的AI资讯" (Give me today's AI news)
  • Says: "AI有什么新动态" (What's new in AI)
当用户出现以下需求时，激活该功能：
  • 询问今日AI新闻或AI最新进展
  • 请求每日AI简报或AI动态更新
  • 表示想了解AI领域的最新动向
  • 询问AI行业新闻、趋势或突破
  • 想要近期AI相关公告的摘要
  • 说："给我今天的AI资讯"
  • 说："AI有什么新动态"

Workflow Overview

工作流概述

This skill uses a 4-phase workflow to gather, filter, categorize, and present AI news:
Phase 1: Information Gathering
  ├─ Direct website fetching (3-5 major AI news sites)
  └─ Web search with date filters
      ↓
Phase 2: Content Filtering
  ├─ Keep: Last 24-48 hours, major announcements
  └─ Remove: Duplicates, minor updates, old content
      ↓
Phase 3: Categorization
  └─ Organize into 5 categories
      ↓
Phase 4: Output Formatting
  └─ Present with links and structure
该功能采用四阶段工作流来收集、筛选、分类并呈现AI新闻：
Phase 1: Information Gathering
  ├─ Direct website fetching (3-5 major AI news sites)
  └─ Web search with date filters
      ↓
Phase 2: Content Filtering
  ├─ Keep: Last 24-48 hours, major announcements
  └─ Remove: Duplicates, minor updates, old content
      ↓
Phase 3: Categorization
  └─ Organize into 5 categories
      ↓
Phase 4: Output Formatting
  └─ Present with links and structure

Phase 1: Information Gathering

阶段1：信息收集

Step 1.1: Fetch from Primary AI News Sources

步骤1.1：从主流AI新闻源获取内容

Use 
mcp__web_reader__webReader
to fetch content from 3-5 major AI news websites:
Recommended Primary Sources (choose 3-5 per session):
Parameters:
  • return_format
    : markdown
  • with_images_summary
    : false (focus on text content)
  • timeout
    : 20 seconds per source
使用
mcp__web_reader__webReader
从3-5个主流AI新闻网站获取内容：
推荐主流新闻源（每次会话选择3-5个）：
参数设置:
  • return_format
    : markdown
  • with_images_summary
    : false (聚焦文本内容)
  • timeout
    : 每个源20秒

Step 1.2: Execute Web Search Queries

步骤1.2：执行带日期过滤的网络搜索

Use 
WebSearch
with date-filtered queries to discover additional news:
Query Template (adjust dates dynamically):
General: "AI news today" OR "artificial intelligence breakthrough" after:[2025-12-23]
Research: "AI research paper" OR "machine learning breakthrough" after:[2025-12-23]
Industry: "AI startup funding" OR "AI company news" after:[2025-12-23]
Products: "AI application launch" OR "new AI tool" after:[2025-12-23]
Best Practices:
  • Always use current date or yesterday's date in filters
  • Execute 2-3 queries across different categories
  • Limit to top 10-15 results per query
  • Prioritize sources from last 24-48 hours
使用
WebSearch
和带日期过滤的查询语句来发现更多资讯：
查询模板（动态调整日期）:
General: "AI news today" OR "artificial intelligence breakthrough" after:[2025-12-23]
Research: "AI research paper" OR "machine learning breakthrough" after:[2025-12-23]
Industry: "AI startup funding" OR "AI company news" after:[2025-12-23]
Products: "AI application launch" OR "new AI tool" after:[2025-12-23]
最佳实践:
  • 始终使用当前日期或昨日日期作为过滤条件
  • 在不同分类下执行2-3个查询
  • 每个查询限制返回10-15条结果
  • 优先选择过去24-48小时内的内容源

Step 1.3: Fetch Full Articles

步骤1.3：获取完整文章内容

For the top 10-15 most relevant stories from search results:
  • Extract URLs from search results
  • Use 
    mcp__web_reader__webReader
    to fetch full article content
  • This ensures accurate summarization vs. just using snippets
针对搜索结果中最相关的10-15条资讯：
  • 从搜索结果中提取URL
  • 使用
    mcp__web_reader__webReader
    获取完整文章内容
  • 相比仅使用摘要片段，这能确保总结的准确性

Phase 2: Content Filtering

阶段2：内容筛选

Filter Criteria

筛选标准

Keep:
  • News from last 24-48 hours (preferably today)
  • Major announcements (product launches, model releases, research breakthroughs)
  • Industry developments (funding, partnerships, regulations, acquisitions)
  • Technical advances (new models, techniques, benchmarks)
  • Significant company updates (OpenAI, Google, Anthropic, etc.)
Remove:
  • Duplicate stories (same news across multiple sources)
  • Minor updates or marketing fluff
  • Content older than 3 days unless highly significant
  • Non-AI content or tangentially related articles
保留:
  • 过去24-48小时内的资讯（优先今日内容）
  • 重大公告（产品发布、模型更新、研究突破）
  • 行业动态（融资、合作、监管、收购）
  • 技术进展（新模型、新技术、基准测试成果）
  • 头部企业重要更新（OpenAI、Google、Anthropic等）
剔除:
  • 重复资讯（同一新闻出现在多个渠道）
  • 微小更新或营销软文
  • 超过3天的内容（极具重要性的除外）
  • 非AI内容或关联性极低的文章

Deduplication Strategy

去重策略

When the same story appears in multiple sources:
  • Keep the most comprehensive version
  • Note alternative sources in the summary
  • Prioritize authoritative sources (company blogs > news aggregators)
当同一资讯出现在多个渠道时：
  • 保留最全面的版本
  • 在摘要中注明其他来源
  • 优先选择权威来源（企业博客 > 新闻聚合平台）

Phase 3: Categorization

阶段3：内容分类

Organize news into 5 categories:
将资讯分为5个类别：

🔥 Major Announcements

🔥 重大公告

  • Product launches (new AI tools, services, features)
  • Model releases (GPT updates, Claude features, Gemini capabilities)
  • Major company announcements (OpenAI, Google, Anthropic, Microsoft, Meta)
  • 产品发布（新AI工具、服务、功能）
  • 模型更新（GPT升级、Claude新功能、Gemini能力迭代）
  • 头部企业重要公告（OpenAI、Google、Anthropic、Microsoft、Meta）

🔬 Research & Papers

🔬 研究与论文

  • Academic breakthroughs
  • New research papers from top conferences
  • Novel techniques or methodologies
  • Benchmark achievements
  • 学术突破
  • 顶级会议发布的新研究论文
  • 创新技术或方法论
  • 基准测试成果

💰 Industry & Business

💰 行业与商业

  • Funding rounds and investments
  • Mergers and acquisitions
  • Partnerships and collaborations
  • Market trends and analysis
  • 融资轮次与投资
  • 兼并与收购
  • 合作与协作
  • 市场趋势与分析

🛠️ Tools & Applications

🛠️ 工具与应用

  • New AI tools and frameworks
  • Practical AI applications
  • Open source releases
  • Developer resources
  • 新AI工具与框架
  • 实用AI应用场景
  • 开源项目发布
  • 开发者资源

🌍 Policy & Ethics

🌍 政策与伦理

  • AI regulations and policies
  • Safety and ethics discussions
  • Social impact studies
  • Government initiatives
  • AI监管政策
  • 安全与伦理讨论
  • 社会影响研究
  • 政府举措

Phase 4: Output Formatting

阶段4：输出格式

Use the following template for consistent output:
markdown
undefined
使用以下模板确保输出一致性：
markdown
undefined

📰 Daily AI News Briefing

📰 每日AI新闻简报

Date: [Current Date, e.g., December 24, 2025] Sources: [X] articles from [Y] sources Coverage: Last 24 hours
日期: [当前日期，例如：2025年12月24日] 来源: 来自[Y]个渠道的[X]篇文章 覆盖范围: 过去24小时

🔥 Major Announcements

🔥 重大公告

[Headline 1]

[标题1]

Summary: [One-sentence overview of the news]
Key Points:
  • [Important detail 1]
  • [Important detail 2]
  • [Important detail 3]
Impact: [Why this matters - 1 sentence]
📅 Source: [Publication Name] • [Publication Date] 🔗 Link: [URL to original article]
摘要: [资讯的一句话概述]
关键点:
  • [重要细节1]
  • [重要细节2]
  • [重要细节3]
影响: [该资讯的重要性说明 - 一句话]
📅 来源: [发布平台名称] • [发布日期] 🔗 链接: [原文URL]

[Headline 2]

[标题2]

[Same format as above]
[与上述格式一致]

🔬 Research & Papers

🔬 研究与论文

[Headline 3]

[标题3]

[Same format as above]
[与上述格式一致]

💰 Industry & Business

💰 行业与商业

[Headline 4]

[标题4]

[Same format as above]
[与上述格式一致]

🛠️ Tools & Applications

🛠️ 工具与应用

[Headline 5]

[标题5]

[Same format as above]
[与上述格式一致]

🌍 Policy & Ethics

🌍 政策与伦理

[Headline 6]

[标题6]

[Same format as above]
[与上述格式一致]

🎯 Key Takeaways

🎯 核心要点

  1. [The biggest news of the day - 1 sentence]
  2. [Second most important development - 1 sentence]
  3. [An emerging trend worth watching - 1 sentence]
Generated on: [Timestamp] Next update: Check back tomorrow for the latest AI news
undefined
  1. [当日最重大资讯 - 一句话]
  2. [第二重要的进展 - 一句话]
  3. [值得关注的新兴趋势 - 一句话]
生成时间: [时间戳] 下次更新: 明日查看最新AI资讯
undefined

Customization Options

定制选项

After providing the initial briefing, offer customization:
在提供初始简报后，可提供以下定制选择：

1. Focus Areas

1. 聚焦领域

"Would you like me to focus on specific topics?"
  • Research papers only
  • Product launches and tools
  • Industry news and funding
  • Specific companies (OpenAI/Google/Anthropic)
  • Technical tutorials and guides
"是否需要我聚焦特定主题？"
  • 仅展示研究论文
  • 产品发布与工具
  • 行业新闻与融资
  • 特定企业（OpenAI/Google/Anthropic）
  • 技术教程与指南

2. Depth Level

2. 内容深度

"How detailed should I go?"
  • Brief: Headlines only (2-3 bullet points per story)
  • Standard: Summaries + key points (default)
  • Deep: Include analysis and implications
"需要多详细的内容？"
  • 精简: 仅标题（每条资讯配2-3个要点）
  • 标准: 摘要+关键点（默认）
  • 深度: 包含分析与影响解读

3. Time Range

3. 时间范围

"What timeframe?"
  • Last 24 hours (default)
  • Last 3 days
  • Last week
  • Custom range
"需要哪个时间段的内容？"
  • 过去24小时（默认）
  • 过去3天
  • 过去一周
  • 自定义范围

4. Format Preference

4. 组织格式

"How would you like this organized?"
  • By category (default)
  • Chronological
  • By company
  • By significance
"希望以何种方式呈现？"
  • 按分类（默认）
  • 按时间顺序
  • 按企业
  • 按重要性

Follow-up Interactions

后续交互

User: "Tell me more about [story X]"

用户："给我讲讲[资讯X]的更多内容"

Action: Use 
mcp__web_reader__webReader
to fetch the full article, provide detailed summary + analysis
操作: 使用
mcp__web_reader__webReader
获取完整文章，提供详细摘要+分析

User: "What are experts saying about [topic Y]?"

用户："专家们对[主题Y]有什么看法？"

Action: Search for expert opinions, Twitter reactions, analysis pieces
操作: 搜索专家观点、推特反应、分析文章

User: "Find similar stories to [story Z]"

用户："找一些和[资讯Z]类似的内容"

Action: Search related topics, provide comparative summary
操作: 搜索相关主题，提供对比摘要

User: "Only show research papers"

用户："只展示研究论文"

Action: Filter and reorganize output, exclude industry news
操作: 筛选并重组输出内容，剔除行业新闻

Quality Standards

质量标准

Validation Checklist

验证清单

  • All links are valid and accessible
  • No duplicate stories across categories
  • All items have timestamps (preferably today)
  • Summaries are accurate (not hallucinated)
  • Links lead to original sources, not aggregators
  • Mix of sources (not all from one publication)
  • Balance between hype and substance
  • 所有链接有效且可访问
  • 不同分类间无重复资讯
  • 所有内容均带时间戳（优先今日）
  • 摘要准确无误（无幻觉内容）
  • 链接指向原文来源，而非聚合平台
  • 内容源多样化（不局限于单一发布平台）
  • 在炒作与实质内容间保持平衡

Error Handling

错误处理

  • If 
    webReader
    fails for a URL → Skip and try next source
  • If search returns no results → Expand date range or try different query
  • If too many results → Increase threshold for significance
  • If content is paywalled → Use available excerpt and note limitation
  • 若
    webReader
    获取某URL失败 → 跳过并尝试下一个来源
  • 若搜索无结果 → 扩大日期范围或更换查询语句
  • 若结果过多 → 提高内容重要性筛选阈值
  • 若内容需付费阅读 → 使用可用摘要并注明限制

Examples

示例

Example 1: Basic Request

示例1：基础请求

User: "给我今天的AI资讯"
AI Response: [Executes 4-phase workflow and presents formatted briefing with 5-10 stories across categories]
用户: "给我今天的AI资讯"
AI回复: [执行四阶段工作流，呈现包含5-10条跨分类资讯的格式化简报]

Example 2: Time-specific Request

示例2：特定时间范围请求

User: "What's new in AI this week?"
AI Response: [Adjusts date filters to last 7 days, presents weekly summary]
用户: "What's new in AI this week?"
AI回复: [调整日期过滤为过去7天，呈现每周摘要]

Example 3: Category-specific Request

示例3：特定分类请求

User: "Any updates on AI research?"
AI Response: [Focuses on Research & Papers category, includes recent papers and breakthroughs]
用户: "Any updates on AI research?"
AI回复: [聚焦研究与论文分类，包含近期论文与突破]

Example 4: Follow-up Deep Dive

示例4：后续深度挖掘请求

User: "Tell me more about the GPT-5 announcement"
AI Response: [Fetches full article, provides detailed summary, offers to find expert reactions]
用户: "Tell me more about the GPT-5 announcement"
AI回复: [获取完整文章，提供详细摘要，并可查找专家反应]

Additional Resources

额外资源

For comprehensive lists of news sources, search queries, and output templates, refer to:
  • references/news_sources.md
    - Complete database of AI news sources
  • references/search_queries.md
    - Search query templates by category
  • references/output_templates.md
    - Alternative output format templates
如需获取完整的新闻源列表、搜索查询语句和输出模板，请参考：
  • references/news_sources.md
    - AI新闻源完整数据库
  • references/search_queries.md
    - 按分类划分的搜索查询模板
  • references/output_templates.md
    - 备选输出格式模板