news-aggregator-skill
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseNews Aggregator Skill
新闻聚合器Skill
Fetch real-time hot news from multiple sources.
从多个来源获取实时热点新闻。
Tools
工具
fetch_news.py
fetch_news.py
Usage:
bash
undefined使用方法:
bash
undefinedSingle Source (Limit 10)
Single Source (Limit 10)
bash
undefined```bashGlobal Scan (Option 12) - Broad Fetch Strategy
全局扫描(选项12)- 广谱抓取策略
NOTE: This strategy is specifically for the "Global Scan" scenario where we want to catch all trends.
bash
undefined注意:该策略专门适用于需要捕获所有趋势的「全局扫描」场景。
bash
undefined1. Fetch broadly (Massive pool for Semantic Filtering)
1. 广谱抓取(为语义过滤提供海量候选池)
python3 scripts/fetch_news.py --source all --limit 15 --deep
python3 scripts/fetch_news.py --source all --limit 15 --deep
2. SEMANTIC FILTERING:
2. 语义过滤:
Agent manually filters the broad list (approx 120 items) for user's topics.
Agent手动对广谱抓取的列表(约120条)按照用户关注的主题进行筛选。
undefinedundefinedSingle Source & Combinations (Smart Keyword Expansion)
单来源&组合来源(智能关键词扩展)
CRITICAL: You MUST automatically expand the user's simple keywords to cover the entire domain field.
- User: "AI" -> Agent uses:
--keyword "AI,LLM,GPT,Claude,Generative,Machine Learning,RAG,Agent" - User: "Android" -> Agent uses:
--keyword "Android,Kotlin,Google,Mobile,App" - User: "Finance" -> Agent uses:
--keyword "Finance,Stock,Market,Economy,Crypto,Gold"
bash
undefined重要提示:你必须自动扩展用户输入的简单关键词,覆盖整个领域范围。
- 用户输入:"AI" -> Agent使用:
--keyword "AI,LLM,GPT,Claude,Generative,Machine Learning,RAG,Agent" - 用户输入:"Android" -> Agent使用:
--keyword "Android,Kotlin,Google,Mobile,App" - 用户输入:"Finance" -> Agent使用:
--keyword "Finance,Stock,Market,Economy,Crypto,Gold"
bash
undefinedExample: User asked for "AI news from HN" (Note the expanded keywords)
示例:用户需要「来自HN的AI新闻」(注意扩展后的关键词)
python3 scripts/fetch_news.py --source hackernews --limit 20 --keyword "AI,LLM,GPT,DeepSeek,Agent" --deep
undefinedpython3 scripts/fetch_news.py --source hackernews --limit 20 --keyword "AI,LLM,GPT,DeepSeek,Agent" --deep
undefinedSpecific Keyword Search
特定关键词搜索
Only use for very specific, unique terms (e.g., "DeepSeek", "OpenAI").
--keywordbash
python3 scripts/fetch_news.py --source all --limit 10 --keyword "DeepSeek" --deepArguments:
- : One of
--source,hackernews,weibo,github,36kr,producthunt,v2ex,tencent,wallstreetcn.all - : Max items per source (default 10).
--limit - : Comma-separated filters (e.g. "AI,GPT").
--keyword - : [NEW] Enable deep fetching. Downloads and extracts the main text content of the articles.
--deep
Output:
JSON array. If is used, items will contain a field associated with the article text.
--deepcontent仅在搜索非常具体的唯一术语时使用(例如"DeepSeek"、"OpenAI")。
--keywordbash
python3 scripts/fetch_news.py --source all --limit 10 --keyword "DeepSeek" --deep参数说明:
- :可选值为
--source,hackernews,weibo,github,36kr,producthunt,v2ex,tencent,wallstreetcn中的一个。all - :每个来源最多返回的条目数(默认10)。
--limit - :逗号分隔的过滤关键词(例如 "AI,GPT")。
--keyword - :[新功能] 开启深度抓取,下载并提取文章的正文内容。
--deep
输出:
JSON数组。如果使用了参数,返回的条目会包含对应文章文本的字段。
--deepcontentInteractive Menu
交互菜单
When the user says "news-aggregator-skill 如意如意" (or similar "menu/help" triggers):
- READ the content of in the skill directory.
templates.md - DISPLAY the list of available commands to the user exactly as they appear in the file.
- GUIDE the user to select a number or copy the command to execute.
当用户说出 "news-aggregator-skill 如意如意"(或类似的「菜单/帮助」触发词)时:
- 读取该Skill目录下的内容。
templates.md - 完全按照文件中的原样向用户展示可用命令列表。
- 引导用户选择编号或复制命令执行。
Smart Time Filtering & Reporting (CRITICAL)
智能时间过滤与报告(重要)
If the user requests a specific time window (e.g., "past X hours") and the results are sparse (< 5 items):
- Prioritize User Window: First, list all items that strictly fall within the user's requested time (Time < X).
- Smart Fill: If the list is short, you MUST include high-value/high-heat items from a wider range (e.g. past 24h) to ensure the report provides at least 5 meaningful insights.
- Annotation: Clearly mark these older items (e.g., "⚠️ 18h ago", "🔥 24h Hot") so the user knows they are supplementary.
- High Value: Always prioritize "SOTA", "Major Release", or "High Heat" items even if they slightly exceed the time window.
- GitHub Trending Exception: For purely list-based sources like GitHub Trending, strictly return the valid items from the fetched list (e.g. Top 10). List ALL fetched items. Do NOT perform "Smart Fill".
- Deep Analysis (Required): For EACH item, you MUST leverage your AI capabilities to analyze:
- Core Value (核心价值): What specific problem does it solve? Why is it trending?
- Inspiration (启发思考): What technical or product insights can be drawn?
- Scenarios (场景标签): 3-5 keywords (e.g. ).
#RAG #LocalFirst #Rust
- Deep Analysis (Required): For EACH item, you MUST leverage your AI capabilities to analyze:
如果用户指定了时间窗口(例如「过去X小时」)且返回结果较少(< 5条):
- 优先满足用户时间窗口:首先列出严格符合用户请求时间范围的所有条目(时间 < X)。
- 智能补全:如果列表过短,你必须纳入更大时间范围(例如过去24小时)的高价值/高热度条目,确保报告至少提供5条有意义的内容。
- 标注说明:明确标记这些超出时间范围的旧条目(例如「⚠️ 18h ago」、「🔥 24h Hot」),让用户知晓这些是补充内容。
- 高价值优先:始终优先展示「SOTA」「重大发布」或「高热度」条目,即使它们略微超出时间窗口。
- GitHub Trending例外:对于像GitHub Trending这类纯列表类来源,严格返回抓取列表中的有效条目(例如Top 10)。列出所有抓取到的条目,不要执行「智能补全」。
- 深度分析(必填):对于每个条目,你必须利用你的AI能力分析以下内容:
- 核心价值 (核心价值):它解决了什么具体问题?为什么会成为热点?
- 启发思考 (启发思考):可以从中得到哪些技术或产品层面的洞察?
- 场景标签 (场景标签):3-5个关键词(例如 )。
#RAG #LocalFirst #Rust
- 深度分析(必填):对于每个条目,你必须利用你的AI能力分析以下内容:
6. Response Guidelines (CRITICAL)
6. 响应规范(重要)
Format & Style:
- Language: Simplified Chinese (简体中文).
- Style: Magazine/Newsletter style (e.g., "The Economist" or "Morning Brew" vibe). Professional, concise, yet engaging.
- Structure:
- Global Headlines: Top 3-5 most critical stories across all domains.
- Tech & AI: Specific section for AI, LLM, and Tech items.
- Finance / Social: Other strong categories if relevant.
- Item Format:
- Title: MUST be a Markdown Link to the original URL.
- ✅ Correct:
### 1. [OpenAI Releases GPT-5](https://...) - ❌ Incorrect:
### 1. OpenAI Releases GPT-5
- ✅ Correct:
- Metadata Line: Must include Source, Time/Date, and Heat/Score.
- 1-Liner Summary: A punchy, "so what?" summary.
- Deep Interpretation (Bulleted): 2-3 bullet points explaining why this matters, technical details, or context. (Required for "Deep Scan").
- Title: MUST be a Markdown Link to the original URL.
Output Artifact:
- Always save the full report to directory with a timestamped filename (e.g.,
reports/).reports/hn_news_YYYYMMDD_HHMM.md - Present the full report content to the user in the chat.
格式与风格:
- 语言:简体中文。
- 风格:杂志/通讯风格(类似《The Economist》或《Morning Brew》的调性),专业、简洁且有吸引力。
- 结构:
- 全球头条:全领域最关键的3-5条要闻。
- 科技与AI:AI、LLM、科技类条目的专属板块。
- 财经/社会:其他相关的重要分类。
- 条目格式:
- 标题:必须是指向原始URL的Markdown链接。
- ✅ 正确:
### 1. [OpenAI Releases GPT-5](https://...) - ❌ 错误:
### 1. OpenAI Releases GPT-5
- ✅ 正确:
- 元数据行:必须包含来源、时间/日期和热度/评分。
- 一句话摘要:简洁有力的「价值点」摘要。
- 深度解读(列表形式):2-3个要点说明该事件的重要性、技术细节或背景信息(「深度扫描」场景下必填)。
- 标题:必须是指向原始URL的Markdown链接。
输出产物:
- 始终将完整报告保存到目录下,文件名附带时间戳(例如
reports/)。reports/hn_news_YYYYMMDD_HHMM.md - 在聊天窗口中向用户展示完整的报告内容。