News Aggregator Skill
A skill that collects fresh news from dozens of tech, finance and AI sources with no API keys and prepares a digest in Chinese.
- 1,318 ★ on the repository
- Last commit
Extended access
Why this level
- The skill runs Python scripts and a Playwright browser, visits dozens of external sites and writes reports to disk.
- The `--deep` mode works around bot protection, which may breach the terms of use of sites.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/news-aggregator-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill runs Python scripts and a Playwright browser, visits dozens of external sites and writes reports to disk.
- The `--deep` mode works around bot protection, which may breach the terms of use of sites.
This is third-party code. Review the repository files before installing.
What it does
The skill polls more than forty sources: Hacker News, GitHub Trending, Product Hunt, V2EX, 36Kr, Weibo, arXiv, Hugging Face Papers, AI newsletters, podcasts and the sites of BBC, The Guardian, Al Jazeera and France 24. The script `scripts/fetch_news.py` takes sources separated by commas, an item limit, filter words and the `--deep` flag. With that flag the skill opens the article through Playwright and takes the full text for analysis. The agent formats each item in one template: title, source, time, popularity figure, short summary and analysis. Reports are written in Chinese and saved to `reports/DATE/`. Ready-made briefings cover general news, finance, tech, entertainment and an AI digest. Your own RSS feeds connect through an OPML file.
Who it is for. Chinese-reading analysts and editors who want a morning briefing on tech, markets and AI without visiting dozens of sites by hand.
Good fit when
- In the morning you want a quick look at what appeared on Hacker News, GitHub Trending and Product Hunt.
- A weekly digest needs fresh arXiv and Hugging Face Papers items with commentary.
- A finance briefing is built from 华尔街见闻 and international agency feeds for the last day.
- Subscriptions from Feedly or Inoreader should be merged into one report through an OPML export.
Not a fit when
- The report must be in Russian or English: the skill template demands translation into Simplified Chinese.
- Sites forbid automated collection and their terms of use matter to you.
- You must track one company: the skill reads only general feeds.
Example request
Take 10 items each from Hacker News and GitHub Trending, switch on deep mode and compile a tech briefing.Limitations
Python 3.10 or newer, the dependencies from `requirements.txt` and Chromium for Playwright are required, installed with `playwright install chromium`. The `--deep` mode works around bot protection and may breach the terms of use of sites. By its instructions, reports are translated into Chinese. The Reuters source works through a Google News fallback rather than an official channel. The repository has no license file, although the README names the MIT license. The last commit was made in May 2026.
How to disable. Delete the `news-aggregator-skill` folder from the agent's skills directory. Saved reports are in `reports/` and a personal OPML file in `~/.config/news-aggregator/`; clear them separately.
FAQ
Does the skill need API keys?
No, sources are read without keys or environment variables. Python, the dependencies and Chromium for `--deep` mode are enough.
How do I request a briefing from several sources at once?
List the keys separated by commas: `python3 scripts/fetch_news.py --source hackernews,github,wallstreetcn --no-save`. The value `all` polls every source and `--limit` sets the items per source, 15 by default.
How do I connect my own RSS feeds?
Put a `user_sources.opml` file in `~/.config/news-aggregator/` or the skill root, using `user_sources.opml.example` as a model, and run `python3 scripts/fetch_news.py --source user --limit 15`.
What does the `--deep` flag do?
The skill downloads the full article text instead of the title and abstract from the feed. For InfoQ China and Import AI the authors advise always using it, otherwise the feed gives only a title or the start of the text.
What is the phrase «如意如意» in the README?
It is a trigger for the interactive menu: after `news-aggregator-skill 如意如意` the agent shows a list of 53 options and a number is enough as an answer.
Discussion
No questions or reviews yet.
Related
SkillsThe news-extractor skill pulls the title, text, images and metadata from a link on 12 news platforms and returns JSON or Markdown, with no browser
A skill that turns a link into clean Markdown via Scrapling with a Jina Reader fallback, incl. WeChat, Juejin and CSDN articles
Three skills and four utilities that let an agent search the web, read pages, pull video subtitles and process media
A skill that gathers 30 days of discussion on eight Chinese platforms, ranks it and writes a cited report, and can also show the cross-platform hot lists
A skill that builds a German-language report on a topic over recent days: sources, a relevance score and flagged uncertainties.
A skill that reads a link and hands the agent the full text as Markdown, picking a separate route for WeChat pages, Feishu docs, PDFs and arXiv papers
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| News Aggregator Skill (this card) | no | 1,318 | ||
| NewsCrawler | no | 639 | extracts the text of one article by link from 12 sites; News Aggregator Skill polls feeds and builds a combined report | |
| Google News Scraper | no | not required | 385 | searches only Google News; News Aggregator Skill merges tech, finance and international feeds |
README in short
The project presents itself as a neutral news collector for agents and lists sources by group: technology, open source, finance, AI and international media. Installation takes two steps: add the skill and install dependencies. Plain-language requests and extending the source set follow.
README badge
Original SKILL.md
--- name: news-aggregator-skill description: "Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub, arXiv, Hugging Face Papers, AIHOT, TLDR AI, Import AI, BBC, The Guardian, Al Jazeera, France 24, Reuters fallback, AI Newsletters, WallStreetCN, Weibo, 少数派, InfoQ 中文, Podcasts, and user-defined OPML feeds. Use when user requests 'daily scans', 'tech news', 'finance updates', 'AI briefings', 'international news', 'deep analysis', or says '如意如意' to open the interactive menu." --- # News Aggregator Skill Fetch real-time hot news from 44+ sources (including international news + AI curated aggregators + user-defined OPML feeds), generate deep analysis reports in Chinese. --- ## 🔄 Universal Workflow (3 Steps) **Every** news request follows the same workflow, regardless of source or combination: ### Step 1: Fetch Data ```bash # Single source python3 scripts/fetch_news.py --source <source_key> --no-save # Multiple sources (comma-separated) python3 scripts/fetch_news.py --source hackernews,github,wallstreetcn --no-save # All sources (broad scan) python3 scripts/fetch_news.py --source all --limit 15 --deep --no-save # With keyword filter (auto-expand: "AI" → "AI,LLM,GPT,Claude,Agent,RAG") python3 scripts/fetch_news.py --source hackernews --keyword "AI,LLM,GPT" --deep --no-save ``` ### Step 2: Generate Report Read the output JSON and format **every** item using the **Unified Report Template** below. Translate all content to **Simplified Chinese**. ### Step 3: Save & Present Save the report to `reports/YYYY-MM-DD/<source>_report.md`, then display the full content to the user. --- ## 📰 Unified Report Template **All sources use this single template.** Show/hide optional fields based on data availability. ```markdown #### N. [标题 (中文翻译)](https://original-url.com) - **Source**: 源名 | **Time**: 时间 | **Heat**: 🔥 热度值