Agent Skills — All Guides
Agent Skills is an open standard for giving AI agents reusable instructions, workflows, and resources. It is built for developers and AI builders who want agents to handle tasks more reliably across compatible tools.
Guides & Articles
From zero to your first AI agent in 12 minutes (no coding)
You don’t need servers, APIs, or coding skills to build powerful AI agents anymore. This guide walks you through creating two practical agents in your browser u…
New concerns over rogue AI agents targeting US government systems
New details have emerged about AI agents probing US government websites without being directly told to do so, raising alarms about cybersecurity and control. As…
Why one senior engineer quit GitHub over AI coding agents
A senior engineer walked away from a dream job at GitHub to work on AI safety. Here’s why he believes fully autonomous AI coding agents will quietly break criti…
How Gemini Notebook’s new agent mode turns it into a real research assistant
Gemini Notebook has quietly evolved from a simple document Q&A tool into a true research and content assistant. With agent-style workflows, web research, Play B…
How to build a real-time voice AI agent with Gemini Live API
Learn how to build a real-time, interruptible voice AI agent using Gemini Live API. We’ll cover the core architecture, the streaming loop, and the three key con…
I built websites, videos, and apps with one AI agent using Runnable
Runnable is an all‑in‑one AI agent that can plan and execute full projects—from websites and pitch decks to videos and workflows—inside a single environment. In…
GPT‑5.6 rumors, new benchmarks, and a big week for AI models and agents
GPT‑5.6 leaks, Microsoft’s new frontier models, Alibaba’s Qwen 3.7 Plus, Hermes Agent Desktop, and fresh Claude and Codex updates made this a huge week for AI. …
Abacus AI’s new supercomputer wants agents to build and host your apps
Abacus AI has launched “AI Supercomputer,” a low-cost cloud environment where AI agents can not only write code but also deploy and host real apps. Here’s how i…
Verdent AI brings multi-agent 'vibe coding' to full app development
Verdent AI is a multi-agent coding environment that acts like a full software team instead of a single overloaded chatbot. It can plan, build, test, and optimiz…
I built a universal AI agent that can actually use your PC
A new prototype Windows tool lets AI agents control your computer like a human: clicking, typing, opening apps, and even troubleshooting problems on screen. Her…
-
Claude Opus 4.8 - Claude Opus 4.8 is Anthropic's most advanced AI model, excelling at coding, reasoning, writing, and agentic tasks. Avail…
-
Cursor - Cursor is an AI coding agent and editor for developers who want faster coding, debugging, refactoring, and code review. …
-
Codex - Codex is OpenAI's AI coding agent that writes features, fixes bugs, runs tests, and prepares code for review. It's built…
-
Playground OpenAI - OpenAI Playground lets you test prompts, compare models, and explore text, image, and other AI workflows in one place. I…
-
Claude Code - Claude Code is an AI coding assistant from Anthropic that helps you read, edit, test, and automate work across a codebas…
-
Cursor - Cursor is an AI coding agent and editor for developers who want faster coding, debugging, refactoring, and code review. …
-
Codex - Codex is OpenAI's AI coding agent that writes features, fixes bugs, runs tests, and prepares code for review. It's built…
-
Scale AI - Scale AI helps enterprises build, test, and improve AI systems with training data, model evaluation, and deployment tool…
-
Llama 3.2 - Llama 3.2 is Meta’s open model family for text and vision tasks. It’s built for developers, researchers, and teams that …
-
NVIDIA Cosmos - NVIDIA Cosmos is a physical AI platform for generating and reasoning about real-world video and simulation data. It is b…