News Aggregator Skill
Pull real-time tech, finance, AI, and international headlines from 44+ sources and produce deep Chinese analysis reports for daily scans.
Overview
news-aggregator-skill is an agent skill most often used in Idea (also Grow, Launch) that fetches and analyzes real-time news from 44+ sources into deep Chinese briefing reports.
Install
npx skills add https://github.com/cclank/news-aggregator-skill --skill news-aggregator-skillWhat is this skill?
- 44+ sources: Hacker News, GitHub, arXiv, Hugging Face Papers, BBC, Reuters fallback, Weibo, 少数派, OPML feeds, and more
- Universal 3-step workflow: fetch via fetch_news.py → read JSON → unified report formatting for every request
- Single, multi-source, or all-source scans with --limit, --deep, and keyword auto-expand (e.g. AI → AI,LLM,GPT,Claude,Age
- Interactive menu trigger phrase 如意如意 plus daily scans, tech news, finance updates, and AI briefings
- Deep analysis reports in Chinese from aggregated JSON output
- 44+ configured news sources
- Universal 3-step workflow (fetch → JSON → unified report)
- Keyword auto-expand example: AI → AI,LLM,GPT,Claude,Agent,RAG
Adoption & trust: 5.5k installs on skills.sh; 1.1k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need a single daily scan across tech, AI, finance, and world news but hopping between HN, arXiv, newsletters, and regional feeds wastes hours.
Who is it for?
Solo builders who want scripted multi-source news pulls and Chinese narrative briefings for market and tech awareness.
Skip if: Builders who need a hosted dashboard with guaranteed SLA uptime or English-only one-line digests with no local Python dependency.
When should I use this skill?
User requests daily scans, tech news, finance updates, AI briefings, international news, deep analysis, or says 如意如意 for the interactive menu.
What do I get? / Deliverables
JSON-backed fetch runs complete and the agent produces a unified deep analysis report covering every returned item for your chosen sources and keywords.
- Fetch JSON from selected sources
- Deep analysis report in Chinese covering all items
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Research is the canonical shelf because the skill’s primary job is aggregating external signals for discovery and briefings, though teams also use it for grow content ideation and launch trend watching. Research fits multi-source news fetches and keyword-expanded scans that inform what to build or write next, not shipping or deploy work.
Where it fits
Run an all-source --deep scan with AI keyword expansion before choosing a product niche.
Aggregate Dev.to and newsletter hits to draft a weekly builder-facing summary post.
Monitor Hacker News and GitHub trending items around your launch week keywords.
Pull finance and tech headlines to sanity-check timing and narrative for a scoped MVP announcement.
How it compares
Agent-orchestrated fetch plus templated report skill, not a subscribed SaaS newsreader or MCP news server by default.
Common Questions / FAQ
Who is news-aggregator-skill for?
Indie developers and operators who want agent-driven aggregation from 44+ configured sources with optional OPML extensions.
When should I use news-aggregator-skill?
In idea research for competitor and trend scans, in grow content planning for briefing material, or at launch when tracking distribution and AI news; say daily scans, tech news, or 如意如意 for the menu.
Is news-aggregator-skill safe to install?
The skill runs local Python fetch scripts with network access to third-party feeds; review script behavior in the repo and the Security Audits panel on this Prism page before installing.
SKILL.md
READMESKILL.md - News Aggregator Skill
# 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 - **Links**: [Discussion](hn_url) | [GitHub](gh_url) ← 仅在数据存在时显示 - **Summary**: 一句话中文摘要。 - **Deep Dive**: 💡 **Insight**: 深度分析（背景、影响、技术价值）。 ``` ### Source-Specific Adaptations Only the **differences** from the universal template: | Source | Adaptation | |---|---| | **Hacker News** | **MUST** include `[Discussion](hn_url)` link | | **GitHub** | Use `🌟 Stars` for Heat, add `Lang` field, add `#Tags` in Deep Dive | | **Hugging Face** | Use `🔥 +N` upvotes for Heat, include `[GitHub](url)` if present, write **深度解读** (not just translate abstract) | | **Weibo** | Preserve exact heat text (e.g. "108万") | | **AIHOT** | `summary` 已是中文编辑稿，**直接引用**不要再翻译；Heat 字段为空也别造数据；保留 `推荐理由` 风格的一句话点评 | | **TLDR AI** | 单条标题往往是多主题混合（`Topic A 💻, Topic B ⚡, Topic C ⛪`），**拆成 bullet 列出每个主题**；`summary` 是 HTML 段落，需要拆出每个主题对应的一两句概述 | | **Import AI** | 周刊长文，标题形如 `Import AI 458: 主题1; 主题2; 主题3`。**建议默认配 `--deep`**，否则 RSS summary 只是开头几句；Deep Dive 直接提炼 Jack Clark 的核心观点而非平铺事实 | | **International News** | **MUST** use the Unified Report Template for every item；只使用最近 24h RSS 条目，不用更早新闻 Smart Fill；英文标题与摘要翻译成简体中文，保留原始媒体名与链接；同一事件多家媒体重复时可合并观点但不能合并链接 | | **Reuters** | `reuters` 使用 Google News RSS 的 `site:reuters.com` fallback；报告里保留 `Reuters (Google News fallback)` source，不要写成官方公开 RSS | --- ## 🛠️ Tools ### fetch_news.py | Arg | Description | Default | |---|---|---| | `--source` | Source key(s), comma-separated. See table below. | `all` | | `--limit` | Max items per source | `15` | | `--keyword` | Comma-separated keyword filter | None | | `--deep` | Download article text for richer analysis | Off | | `--save` | Force save to reports dir | Auto for single source | | `--outdir` | Custom output directory | `reports/YYYY-MM-DD/` | ### Available Sources (44+ with user OPML) | Category | Key | Name | |---|---|---| | **Global News** | `hackernews` | Hacker News | | | `36kr` | 36氪 | | | `wallstreetcn` | 华尔街见闻 | | | `tencent` | 腾讯新闻 | | | `weibo` | 微博热搜 | | | `v2ex` | V2EX | | | `producthunt` | Product Hunt | | | `github` | GitHub Trending | | **Tech Community**