AI Daily News Report
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_fa1d3d9e/ai-daily-report-skill.
About this skill
Problem
Daily AI news is spread across many Chinese and English outlets, and quality varies. Some sites are JavaScript-rendered SPAs, so WebFetch or plain HTTP fetches often return empty HTML. Without fixed source allowlists, parsing rules, and timeout controls, a daily-news workflow can stall on unusable pages or produce unstable output.
How it works
The skill treats news collection as a pipeline. It first fetches verified SSR or RSS sources with curl, such as 量子位, 机器之心, TechCrunch, MIT Tech Review, and Product Hunt. It then parses HTML or feeds with Python to extract titles and original links. Finally, it selects 5–10 items based on LLM releases, AI product updates, funding or regulation, conference papers, open-source projects, and robotics progress, producing a concise daily digest with source links.
Boundaries
It is better used as a traceable news digest, not as full translation, trend analysis, or deep reporting. The skill explicitly avoids SPA sources such as 虎嗅, 雷锋网, and 新智元. Each request is capped at 15 seconds; failures are skipped without infinite retries. If all sources fail, it reports failure instead of inventing news.
Use Cases
- Before a morning stand-up, filter QbitAI, Jiqizhixin, and TechCrunch AI items into a five-link digest.
- When SPA pages return no body, fetch verified RSS feeds from TechCrunch, Ars Technica, and VentureBeat.
- When adding AI industry notes to a weekly report, extract titles and links while skipping failed sources.
- When normalizing AI news into a data pipeline, parse AI News and Product Hunt Atom entries into one digest.
Best For
- ML engineers who need a fast daily AI scan with verifiable source links.
- crawler maintainers who must avoid SPA failures and rely on RSS or SSR sources.
- team leads who need AI news folded into weekly reports or morning meeting materials.
- automation engineers who require skip-on-failure behavior and no infinite retries.
Related Skills
Query Douyin creator videos, image/text posts, and short-drama series by sec_user_id or profile URL with paginated list retrieval.
Uses CDP-controlled browser screenshots of Douyin video pages and multimodal AI to extract teaching points into a Markdown report.
Query Douyin hot searches and works with SocialDataX API or MCP tools, supporting keyword, sorting, time range, duration, content type, and pagination.
Fetch the GitHub Trending leaderboard and generate fact-grounded project analysis, trend hypotheses, and directional insights.