ai-newsletters
GitHub该技能用于自动化采集、去重和排序 AI 领域新闻源,生成每日精选摘要。支持缓存检查、多源合并及基于相关性和新颖性的智能排名,最终输出包含趋势分析和工具推荐的定制化内容。
触发场景
安装
npx skills add MarsZ42/OrbitOS --skill ai-newsletters -g -y
SKILL.md
Frontmatter
{
"name": "ai-newsletters",
"description": "Curate AI newsletter content with smart deduplication and ranking. Use when user invokes \/ai-newsletters or when \/start-my-day needs newsletter content."
}
AI Newsletter Curation
Fetch, deduplicate, and rank AI newsletter content into a daily digest.
RSS Sources
- TLDR AI:
https://bullrich.dev/tldr-rss/ai.rss - The Rundown AI:
https://rss.beehiiv.com/feeds/2R3C6Bt5wj.xml
Workflow
-
Check cache: Look for
50_Resources/NewsLetter/YYYY-MM/YYYY-MM-DD-Digest.md. If exists with today's date, return cached content. -
Fetch feeds: Use WebFetch on both RSS URLs. Extract title, link, pubDate, description for each item.
-
Deduplicate: Merge items with similar titles (80%+ word overlap). Keep longer description, track both sources.
-
Rank items by:
- AI relevance (LLM, GPT, Claude, agents, ML keywords)
- Productivity relevance (workflow, automation, tools, PKM)
- Recency (newer = higher)
- Novelty (check recent archives, penalize repeats)
-
Generate digest: See TEMPLATE.md for format. Include:
- Top Picks (3-5 highest scoring) with content creation angles
- AI Trends section
- Productivity Tools section
- Stats footer
-
Save files:
50_Resources/NewsLetter/YYYY-MM/YYYY-MM-DD-Digest.md(curated)50_Resources/NewsLetter/YYYY-MM/Raw/YYYY-MM-DD_TLDR-AI-Raw.md50_Resources/NewsLetter/YYYY-MM/Raw/YYYY-MM-DD_Rundown-AI-Raw.md
Output Format
Manual invocation: Display full digest with all sections.
From /start-my-day: Return condensed list:
**Content Opportunities (5):**
- [Title] - [Angle]
...
Full digest: [[YYYY-MM-DD-Digest]]
Error Handling
- One feed down: Continue with other, note in digest
- Both down: Use yesterday's archive with warning
- Empty feeds: Create minimal digest noting "No new items"
版本历史
- 921bd14 当前 2026-07-25 10:48


