Skip to content
Agentmart
Submit a tool

news-aggregator

Use when aggregating, validating, and organizing news material for Article Pool drafts, including morning news, evening news, weekly/monthly reports, topic…

Skill by shunzenga-prog

IndexedMIT
Write a review

Chalk Labs

Need help deploying news-aggregator?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/shunzenga-prog-news-aggregator

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when aggregating, validating, and organizing news material for Article Pool drafts, including morning news, evening news, weekly/monthly reports, topic briefs, and knowledge-sharing articles.

Use cases: writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/news-aggregator

What's inside

Skill name
news-aggregator
Description
Use when aggregating, validating, and organizing news material for Article Pool drafts, including morning news, evening news, weekly/monthly reports, topic briefs, and knowledge-sharing articles.
License
MIT
Instructions
233 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: scripts/scrape-aibase-v2.py, scripts/scrape-36kr-fixed.py, scripts/scrape-news-sources.py, scripts/verify-news-date.py

Files (1)

  • SKILL.md

SKILL.md (first lines)

---
name: news-aggregator
description: Use when aggregating, validating, and organizing news material for Article Pool drafts, including morning news, evening news, weekly/monthly reports, topic briefs, and knowledge-sharing articles.
---

# 资讯整合 Agent

为创作Agent提供验证后的新闻素材。

## ⚠️ 重要:搜索方式变更

**Brave Search 时间过滤参数不生效!**

- `date_after` 参数无效
- `freshness` 参数效果不稳定
- 必须使用直接抓取新闻源的方式

## 核心原则

1. **直接抓取新闻源** - 不依赖搜索引擎时间过滤
2. **验证时效性** - 确认每条新闻的发布日期
3. **来源可靠** - 优先官方/主流媒体
4. **场景适配** - 根据场景选择数据源

---

## 使用场景

### 场景1:早报(获取昨天新闻)

```bash
# 直接抓取36氪等科技媒体最新文章
python scripts/scrape-36kr-fixed.py > reports/materials/36kr-latest.json

# 或抓取多个源
python scripts/scrape-news-sources.py reports/materials/news-latest.json
```

### 场景2:晚报(获取今天新闻)

```bash
# 同早报,抓取最新文章即可
python scripts/scrape-36kr-fixed.py
```

### 场景3:周报(过去7天)

```python
# 方案1:抓取新闻后按日期过滤
articles = scrape_news_sources()
recent_articles = [a for a in articles if is_within_days(a, 7)]

# 方案2:RSS Feed 订阅
import feedparser
feed = feedparser.parse("https://36kr.com/feed")
```

### 场景4:月报(过去30天)

```python
# 同周报,按日期过滤
articles = scrape_news_sources()
recent_articles = [a for a in articles if is_within_days(a, 30)]
```

### 场景5:指定主题创作(不限制时间)

```python
# 使用 Brave Search 搜索主题(不过滤时间)
web_search(query="指定主题关键词", count=15)

# 验证每条内容的发布日期
for result in results:
    verify_publish_date(result.url)
```

### 场景6:知识/技术/工具分享(不限制时间)

```python
# 使用 Brave Search 搜索技术教程
web_search(query="技术关键词 教程", count=10)

# 验证内容时效性和准确性
```

---

## 工作流程

### 输入参数

```python
{
  "scene": "morning|evening|weekly|monthly|topic|knowledge",
  "topic": "可选,指定主题",
  "sources": ["36kr", "qbitai", "jiqizhixin"],  # 新闻源
  "count": 10  # 每个源的数量
}
```

### 执行步骤

```
1. 确定场景 → 选择数据源
2. 直接抓取新闻源 → 获取最新文章
3. 文章本身即最新 → 无需时间过滤
4. 去重、排序 → 按重要性排序
5. 输出素材文件
```

### 新闻源优先级

| 优先级 | 来源 | 类型 | 抓取方式 | 脚本 |
|--------|------|------|----------|------|
| ⭐⭐⭐⭐⭐ | AI Base | AI资讯 | Playwright | `scrape-aibase-v2.py` |
| ⭐⭐⭐⭐⭐ | 36氪 | 科技媒体 | Playwright | `scrape-36kr-fixed.py` |
| ⭐⭐⭐⭐ | 量子位 | AI媒体 | Playwright | 待开发 |
| ⭐⭐⭐⭐ | 机器之心 | AI媒体 | Playwright | 待开发 |
| ⭐⭐⭐ | 微软官方 | 官方公告 | web_fetch | - |
| ⭐⭐⭐ | OpenAI Blog | 官方公告 | web_fetch | - |

From shunzenga-prog/article-pool, MIT.

Signals

Stars
0
Forks
1
Open issues
0
Last commit (this folder)
May 26, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get news-aggregator running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying news-aggregator?

CallGet help
Cite this page

news-aggregator skill. Agent Mart. https://agentmart.dev/skills/shunzenga-prog-news-aggregator (last updated 2026-10-24)