This aggregates AI news from sources like VentureBeat, TechCrunch, and MIT Tech Review, then organizes everything into categories like major announcements, research papers, industry news, tools, and policy updates. It fetches full articles, filters out duplicates and old stories, and presents summaries with direct links in a structured briefing format. Use it when you want a daily AI news roundup without manually checking multiple sites. The workflow is thorough, maybe overly so, with four distinct phases for gathering and categorizing content. It covers both English and Chinese trigger phrases and offers customization for focus areas and detail level. Good for keeping up with the AI landscape without drowning in noise, though the template feels a bit rigid.

skills.sh installs
2.6K
GitHub stars
286
last updated
Aug 21, 2026

Install

$ npx -y skills add yyh211/claude-meta-skill --skill daily-ai-news --agent claude-code

Installs into .claude/skills of the current project.

Files

Daily AI News Briefing

Aggregates the latest AI news from multiple sources and delivers concise summaries with direct links

When to Use This Skill

Activate this skill when the user:

  • Asks for today's AI news or latest AI developments
  • Requests a daily AI briefing or updates
  • Mentions wanting to know what's happening in AI
  • Asks for AI industry news, trends, or breakthroughs
  • Wants a summary of recent AI announcements
  • Says: "给我今天的AI资讯" (Give me today's AI news)
  • Says: "AI有什么新动态" (What's new in AI)

Workflow Overview

This skill uses a 4-phase workflow to gather, filter, categorize, and present AI news:

Phase 1: Information Gathering
  ├─ Direct website fetching (3-5 major AI news sites)
  └─ Web search with date filters
      ↓
Phase 2: Content Filtering
  ├─ Keep: Last 24-48 hours, major announcements
  └─ Remove: Duplicates, minor updates, old content
      ↓
Phase 3: Categorization
  └─ Organize into 5 categories
      ↓
Phase 4: Output Formatting
  └─ Present with links and structure

Phase 1: Information Gathering

Step 1.1: Fetch from Primary AI News Sources

Sponsors

Details

Repository
github.com/yyh211/claude-meta-skill
Category
AI & Agent Building
1yanhongxi-openclaw avatarproactive-self-improving-agentyanhongxi-openclaw/proactive-self-improving-agentproactive self improving agent2.6Kskills.sh installs
2nvidia avatarrag-evalnvidia/skillsFilesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or eva2.5Kskills.sh installs
3huggingface avatarhuggingface-llm-trainerhuggingface/skillsTrain or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, 2.4Kskills.sh installs
4modelcontextprotocol avatarcreate-mcp-appmodelcontextprotocol/ext-appsThis skill should be used when the user asks to "create an MCP App", "add a UI to an MCP tool", "build an interactive MCP View", "scaffold an MCP App", or needs2.3Kskills.sh installs
5okx avatarokx-agent-identityokx/onchainos-skillsERC-8004 on-chain Agent identity on XLayer: register / create / update / activate / deactivate / search agents; view ratings; list agent services; set avatar. R2.3Kskills.sh installs
6okx avatarokx-agent-taskokx/onchainos-skillsMUST ACTIVATE on inbound envelopes: (1) {agentId, message:{source:"system", event, jobId, ...}} — system event; (2) {msgType:"a2a-agent-chat", jobId, sender:{ro2.3Kskills.sh installs