According to AlphaMoat, as of 2026-09, news-scout 热点新闻聚合简报 has 2,389 downloads and 0 stars — ranked #4,183 of 5,078 AI skills overall, and #277 of 362 in Content.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 32 | 1.2K | - | - |
| SkillHub ↗ | 264 | 2.4K | - | — |
Platforms count differently and update at different times.
Runs python3 scripts/scout.py --category ai,investing to fetch news (based on RSS and Bing News RSS, directly accessible in China; first use requires pip3 install feedparser requests); when the script is unavailable, fall back to web_search/web_fetch and note this in the output. Three core processing steps: dedup and merge (keep the most authoritative source, priority: official blogs > mainstream tech media > aggregators; P0 = OpenAI/Google/Anthropic official blogs, Federal Reserve site, Yahoo Finance; P1 = The Verge, TechCrunch, CNBC, WSJ, 机器之心, 量子位; P2 = other tech media and aggregators); heat rating (1-5 stars, major breakthroughs/multi-outlet coverage 5 stars, routine product updates 2 stars, etc.); impact analysis (1-2 objective sentences on industry or market effects). Output strictly follows the template: Investing & US Markets Top 3, Global AI Frontier Top 4, China Domestic AI Top 3 — strictly 10 items per run (3:4:3 ratio), each with star rating, a one-sentence summary (≤ 50 characters), impact analysis, and source link. Constraints: only news from the past 24-48 hours; all source URLs must be HTTPS; all communication and analysis in Chinese; sorted by stars descending within each category; paywalled sources like WSJ/FT marked "(subscription may be required)".
Profile published 2026-10-29
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 2.4K | — | - |
| 2026-08 | 2.1K | +3.8% | - |
| 2026-07 | 2.0K | +10.3% | - |
| 2026-06 | 1.8K | +5.2% | - |
| 2026-05 | 1.7K | — | - |
| 2026-03 | 1.0K | — | - |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
--- name: news-scout description: AI领域以及投资领域新闻聚合工具。当用户询问新闻相关问题时触发,如:"今日新闻" "今天有什么新闻?" "新闻简报" "获取新闻" "AI动态" "美股行情" "科技新闻" "市场走势"。AI领域新闻区分全球和中国国内,投资领域新闻主要突出影响全球投资的美股市场关键动向,每条新闻按热度排序,而且都有简要的影响分析。 --- # news-scout (新闻斥候) 🦅 自动化收集、筛选并分析全球/国内的 AI 新闻和美股市场趋势,为用户提供精炼的每日新闻简报。 ## 📋 触发关键词
当用户提到以下任意关键词时触发此技能:
- **通用**:`新闻` `简报` `今日动态` `最新消息` `有什么新闻`
- **AI 领域**:`AI新闻` `人工智能` `大模型` `科技前沿` `OpenAI` `Anthropic` `谷歌AI`
- **投资市场**:`美股` `股市` `市场行情` `投资动态` `财报` `美联储`
- **中国相关**:`中国AI` `国内科技` `A股` `中概股` `港股`
## 🛠️ 准备工作
### 依赖安装(首次使用)
```bash
# 所有环境通用(包括 OpenClaw)
pip3 install feedparser requests
```
### 备用方案
如果脚本无法运行(依赖缺失或网络问题),使用以下工具替代:
- `web_search` - 搜索最新新闻
- `web_fetch` - 抓取新闻网站内容
## 🔄 完整工作流
### 第一步:运行新闻抓取脚本(首选)
```bash
python3 scripts/scout.py --category ai,investing
```
**参数说明:**
- `--category ai` - 仅获取 AI 新闻
- `--category investing` - 仅获取投资/美股新闻
- `--category ai,investing` - 同时获取两类(默认)
**预期输出:** JSON 格式的新闻列表,包含标题、链接、来源、摘要、日期等信息。
### 第二步:分析与过滤(核心处理)
对获取的原始新闻进行以下处理:
#### 1. 去重合并 🔀
- 识别报道同一事件的多条新闻
- 保留最权威来源(优先级:官方博客 > 主流科技媒体 > 聚合平台)
- 在最终输出中标注"*(多家媒体报道)*"
**权威度参考:**
- **P0(最高)**:OpenAI/Google/Anthropic 官方博客、美联储官网、Yahoo Finance
- **P1(高)**:The Verge、TechCrunch、CNBC、WSJ、机器之心、量子位
- **P2(中)**:其他科技媒体、聚合平台
#### 2. 热度评估 ⭐(1-5 星)
| 星级 | 标准 | 示例 |
|------|------|------|
| ⭐⭐⭐⭐⭐ | 重大突破/多方报道 | OpenAI 发布新模型、美联储加息决定 |
| ⭐⭐⭐⭐ | 重要发布/病毒传播 | 谷歌 Gemini 更新、科技巨头财报超预期 |
| ⭐⭐⭐ | 实际应用突破/中等影响 | AI 产品新功能、行业合作消息 |
| ⭐⭐ | 常规产品更新 | 版本迭代、小功能发布 |
| ⭐ | 垂直领域/补充信息 | 小众技术动态、背景分析 |
#### 3. 影响分析 📊
用 1-2 句话客观总结:
- **AI 新闻**:对技术发展、行业格局、用户应用的影响
- **投资新闻**:对市场走势、板块轮动、投资决策的影响
### 第三步:格式化输出(最终呈现)
**严格遵循以下模板:**
```markdown
## 🔥 新闻斥候简报 (YYYY-MM-DD)
### 📈 投资与美股市场 (Top 3)
1. **[⭐⭐⭐⭐] [新闻标题]**
- *摘要*: [一句话摘要,不超过 50 字]
- *影响*: [简要分析对市场趋势的影响]
> 🔗 [来源名称](URL) *(多家媒体报道)*
### 🌍 全球 AI 前沿 (Top 4)
4. **[⭐⭐⭐⭐⭐] [新闻标题]**
- *摘要*: [一句话摘要,不超过 50 字]
- *影响*: [简要分析对 AI 发展的影响]
> 🔗 [来源名称](URL)
### 🇨🇳 中国国内 AI 动态 (Top 3)
8. **[⭐⭐⭐] [新闻标题]**
- *摘要*: [一句话摘要,不超过 50 字]
- *影响*: [简要分析对产业的影响]
> 🔗 [来源名称](URL)
---
📊 本次共检索 {number} 条新闻 | 更新时间:{HH:MM}
```
**数量分配(严格执行):**
- 📈 投资美股市场:**3 条**
- 🌍 全球 AI 前沿:**4 条**
- 🇨🇳 中国国内 AI 动态:**3 条**
- **总计:10 条**
## ⚠️ 约束与规则
### 必须遵守
- ✅ **数量限制**:每次严格输出 10 条新闻(3:4:3 比例)
- ✅ **时效性**:只包含过去 24-48 小时内的最新新闻
- ✅ **HTTPS**:所有新闻源 URL 必须是 HTTPS 协议
- ✅ **中文输出**:所有交流和分析使用中文
- ✅ **热度排序**:每个分类内按星级从高到低排列
### 特殊标注
- 🔒 **付费墙**:如来源为 WSJ、FT 等,标注"(可能需订阅)"
- 🔄 **多方报道**:如事件被多家媒体报道,标注"*(多家媒体报道)*"
- 🌐 **语言说明**:如来源为英文,可在来源后标注"(英文)"
### 备用方案(脚本不可用时)
如果 `scout.py` 脚本无法运行:
1. 使用 `web_search` 搜索最新新闻(设置 `freshness: "day"`)
2. 使用 `web_fetch` 抓取新闻网站内容
3. 按相同标准进行去重、评分、分析
4. 在输出末尾添加说明:"*注:本次使用备用方案获取新闻*"
## 🎯 优化建议
### 提升质量
- 优先选择有具体数据、引用的新闻
- 避免纯观点、无事实支撑的内容
- 平衡正面和负面新闻,保持客观
### 用户体验
- 保持语气客观但不生硬
- 影响分析要具体,避免空泛
- 如有重大突发新闻,可在开头单独提示
## 📁 文件结构
```
news-scout/
├── SKILL.md # 本文件(技能说明)
├── scripts/
│ └── scout.py # 新闻抓取脚本
├── resources/
│ └── news_sources.json # 新闻源配置(RSS + 搜索词)
└── README.md # 使用说明(可选)
```
## 🔧 维护与更新
### 更新新闻源
编辑 `resources/news_sources.json`:
- 添加新的 RSS 源(按优先级 P0/P1/P2 分类)
- 优化搜索查询词(覆盖更多关键词变体)
- 定期清理失效链接
### 脚本调试与网络设置
```bash
# 包含丰富调试信息的抓取测试
python3 scripts/scout.py --category ai --debug
```
*注:搜索功能基于 Bing News RSS,国内可直接访问,无需代理。若 Bing 搜索失败,程序不会崩溃,其余 RSS 抓取仍正常进行。*
Detects and removes AI writing traces so text reads more like a person wrote it.
A writing-editor skill that finds the usual marks of AI-generated text and rewrites them into more natural prose without losing the meaning.
A Chinese copy-editing skill that spots and removes the traces of AI-generated text.
wechat-search finds popular WeChat articles and organizes results by relevance, popularity and recency.
Extracts titles, descriptions, and spoken scripts from public short-video share links, with rewritten versions.
humanizer guides natural expression and style editing for Chinese and English text.
Writes web-novel chapters into files and replies in chat with summaries and pointers only.
Bundle a set of marketing playbooks into one skill and route each request to the module that fits.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.