researching-ai-news
Research and compile the latest AI news from across the industry. Use this skill when asked to find AI news, get AI updates, research what's happening in AI, check for AI announcements, or gather intelligence on AI companies. Triggers include requests for "AI news", "latest AI developments", "what's new in AI", "AI industry updates", or news about specific AI companies (OpenAI, Anthropic, Google, Microsoft, Meta, Amazon, Nvidia, xAI, Mistral, Cohere, Apple, Salesforce).
- Installs
- 202
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/jamesgray007/hoai-course --skill researching-ai-news- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads researching-ai-news automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Researching AI News
Research and compile AI news from across the industry, covering major companies and emerging trends.
Companies to Track
Frontier Labs:
- OpenAI
- Anthropic
- Google DeepMind / Google AI
- Meta AI / FAIR
- xAI
Tech Giants:
- Microsoft AI
- Amazon AWS AI / Bedrock
- Nvidia
- Apple (Apple Intelligence)
- Salesforce (Einstein AI)
- IBM (watsonx)
AI Startups & Specialists:
- Mistral AI
- Cohere
- Stability AI
- Runway
- Hugging Face
- Perplexity AI
- Other emerging labs
Topics to Cover
- Product launches & updates - New models, features, API changes
- Research breakthroughs - Papers, benchmarks, capabilities
- Regulations & policy - Government actions, safety initiatives, legal developments
- Industry trends - Funding, partnerships, acquisitions, market moves
- Enterprise AI adoption - Real-world implementations, case studies, ROI reports
Research Workflow
Step 1: Run Perplexity Searches
Use the Perplexity MCP tools for comprehensive, citation-rich results:
Primary tool: mcp__perplexity__perplexity_search
- Best for quick, targeted queries with ranked results
- Returns titles, URLs, snippets, and metadata
- Use
max_results: 10for comprehensive coverage
Deep research: mcp__perplexity__perplexity_research
- Use for complex topics requiring synthesis across sources
- Returns comprehensive analysis with citations
- Best for industry trends and regulatory developments
Search Queries
Run these searches in parallel using mcp__perplexity__perplexity_search:
Company news (run in parallel):
- "OpenAI announcement news December 2024"
- "Anthropic Claude news December 2024"
- "Google Gemini AI news December 2024"
- "Microsoft AI Copilot news December 2024"
- "Meta Llama AI news December 2024"
- "Nvidia AI news December 2024"
- "xAI Grok news December 2024"
- "Amazon AWS Bedrock AI news December 2024"
- "Mistral AI news December 2024"
- "Apple Intelligence news December 2024"
Industry topics (run in parallel):
- "AI regulation policy news December 2024"
- "AI research breakthrough news December 2024"
- "AI startup funding investment news December 2024"
- "enterprise AI deployment case study 2024"
For deeper analysis, use mcp__perplexity__perplexity_research with:
{
"messages": [
{"role": "user", "content": "What are the most significant AI industry developments in the last 48 hours? Include product launches, research breakthroughs, regulatory changes, and major funding announcements. Focus on verified announcements from official sources."}
]
}
Step 2: Filter for Recency
Include stories from the last 24-48 hours. Use 24 hours for daily briefings; extend to 48 hours on Mondays or slow news days to capture weekend developments.
Step 3: Deduplicate Results
Before compiling output:
- Identify stories appearing across multiple searches
- Consolidate duplicate stories into a single entry
- Use the most authoritative source (official blog > news outlet > aggregator)
- Note if multiple sources are covering the same story (indicates higher significance)
Step 4: Verify Major Claims
For significant announcements:
- Cross-reference against official company blogs, press releases, or verified social accounts
- Check if the story has been confirmed by multiple reputable sources
- Flag unverified or single-source stories as "Developing" or "Unconfirmed"
Step 5: Compile Results
Format output as bullet points with source links:
## AI News - [Date]
### Company Updates
- **[Company]**: [Brief summary of news] ([Source](url))
- **[Company]**: [Brief summary of news] ([Source](url))
### Product Launches
- [Product/feature description] ([Source](url))
### Research & Breakthroughs
- [Research summary] ([Source](url))
### Regulation & Policy
- [Policy development] ([Source](url))
### Enterprise Adoption
- [Company/industry implementation story] ([Source](url))
### Industry Trends
- [Trend/funding/partnership] ([Source](url))
Step 6: Prioritize
Order stories by significance:
- Major model releases or capabilities
- Significant policy/regulatory changes
- Large funding rounds or acquisitions
- Research breakthroughs
- Enterprise adoption stories with measurable outcomes
- Product updates and features
Output Guidelines
- Keep summaries to 1-2 sentences per story
- Always include source links
- Group related stories together
- Note if a category has no news ("No significant updates")
- Flag breaking/developing stories with "[DEVELOPING]" prefix
- Flag unverified stories with "[UNCONFIRMED]" prefix
- Prefer official sources over secondary coverage
Perplexity MCP Tools Reference
| Tool | Use Case |
|---|---|
mcp__perplexity__perplexity_search | Quick searches, specific company news, targeted queries |
mcp__perplexity__perplexity_research | Deep analysis, trend synthesis, comprehensive reports |
mcp__perplexity__perplexity_ask | Follow-up questions, clarifications, verification |
Search Tips
- Use company + product names for precision ("Claude 3.5", "GPT-4o", "Gemini 2.0")
- Include current month/year in queries for better recency filtering
- Run company searches in parallel for efficiency
- Use
perplexity_researchfor synthesizing trends across multiple sources - Perplexity automatically includes citations - preserve these in output
- For verification, use
perplexity_askto confirm details from official sources
FAQ
What does the researching-ai-news skill do?
Research and compile the latest AI news from across the industry. Use this skill when asked to find AI news, get AI updates, research what's happening in AI, check for AI announcements, or gather intelligence on AI companies. Triggers include requests for "AI news", "latest AI developments", "what's new in AI", "AI industry updates", or news about specific AI companies (OpenAI, Anthropic, Google, Microsoft, Meta, Amazon, Nvidia, xAI, Mistral, Cohere, Apple, Salesforce).
How do I install researching-ai-news?
Run npx skills add https://github.com/jamesgray007/hoai-course --skill researching-ai-news in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/researching-ai-news/ (personal) or .claude/skills/researching-ai-news/ (project).
Which AI agents can use researching-ai-news?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is researching-ai-news safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains researching-ai-news?
It is published by jamesgray007 in jamesgray007/hoai-course. It has 202 recorded installs.
More from jamesgray007/hoai-course
writing-linkedin-posts
jamesgray007/hoai-course
Create engaging, authentic LinkedIn posts like a Top Voice. Use this skill when asked to write LinkedIn content, social media posts for LinkedIn, professional thought leadership content, or help with LinkedIn engagement strategy. Triggers include requests for LinkedIn posts, professional social content, thought leadership pieces, or viral/engaging LinkedIn content.
writing-x-posts
jamesgray007/hoai-course
Open the skill to read its SKILL.md instructions.
writing-substack
jamesgray007/hoai-course
Open the skill to read its SKILL.md instructions.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available