Agent Safety is a Box - Marc's Blog
LLMs
Agent Skill — Build Composable AI Capabilities for Claude
Create structured knowledge packages that extend Claude with domain-specific expertise using Agent Skills.
Claude Agent Skills: A First Principles Deep Dive
Technical deep dive into Claude Agent Skills' prompt-based meta-tool architecture. Learn how context injection design, two-message patterns, LLM-based routing, and runtime context modification enable sophisticated AI agent behaviors. Complete implementation guide covering SKILL.md structure, execution lifecycle, permission scoping, and design patterns for building LLM tool systems. Essential for AI engineers, prompt engineers, and technical architects building agentic applications.
Agent Skills Marketplace - Claude, Codex & ChatGPT Skills | SkillsMP
Browse 200000+ agent skills compatible with Claude Code, Codex CLI and ChatGPT. The open standard SKILL.md format for AI coding assistants.
Agent Skills
Agent Skills are modular capabilities that extend Claude's functionality. Each Skill packages instructions, metadata, and optional resources (scripts, templates) that Claude uses automatically when relevant.
The Agent Skills Directory
Discover and install skills for AI agents.
Why MCP’s Disregard for 40 Years of RPC Best Practices Will Burn Enterprises
Fool me once, shame on you; fool me twice, shame on me.
How to Set Up and Use Claude Code Agent Teams (And Actually Get Great Results)
If you’ve been using Claude Code for a while, you’ve probably hit the moment where one AI session just isn’t enough. Maybe you’re staring…
Orchestrate teams of Claude Code sessions - Claude Code Docs
Coordinate multiple Claude Code instances working together as a team, with shared tasks, inter-agent messaging, and centralized management.
My AI Development Environment
This site contains thoughts and experiences of Jeff Cheezy Morgan that he thought worth sharing.
The four modes of AI-augmented technical writing
I like cooking recipes. They’re clean, serene documents where, at some point, one or more utensils enter the stage to perform a task. If you were to write one on how to use AI to augment your work as a technical writer, though, you would have a hard time deciding when and where LLMs come out of the toolbox to aid you. The variety of flavors in which AI presents itself doesn’t help. This is why I’ve come up with a framework that describes applications of the different AI tools at our disposal.
I use the 'unicorn prompt' with every chatbot — it instantly fixes the worst AI problem
A universal solution to better chatbot responses
The Levels of Agentic Coding
How to Facilitate Effective AI Programming | Towards Data Science
How to ensure your coding agent has the same context as you
From Single-Shot Prompting to Recursive Prompt Control
Learn how to steer an LLM step by step instead of hoping a single prompt gets it right.
Authorization Before Retrieval: Making RAG Safe by Construction
Retrieval-augmented generation makes language models far more useful by grounding them in real data, But it also raises a hard question: who is allowed to see what? This post shows how authorization can be enforced before retrieval, ensuring that RAG systems remain powerful without becoming dangerous.
Generative AI hype distracts us from AI’s more important breakthroughs
It's a seductive distraction from the advances in AI that are most likely to improve or even save your life
DoAnything Blog
Learn about AI agents, automation, productivity, and how to get more done.
DoAnything - AI Agent That Does Your Tasks Autonomously
Meet DoAnything, the AI agent that handles your most stressful tasks. Start a business, plan events, apply to jobs, and more.
Systemic co-design with agentic engineers
Weeknotes 371 - The real shift is not from human coders to AI agents—it's from coding to engineering the environment where agents are co-designers. And other news on AI companion devices and robots as CES.
Welcome to Gas Town
Happy New Year, and Welcome to Gas Town!
The Future of Coding Agents
It has been three days since I launched Gas Town! 🔥⛽💥🛢️🔥 Woohoo!
Manus
Manus is the action engine that goes beyond answers to execute tasks, automate workflows, and extend your human reach.
Lovable - Build Apps & Websites with AI, Fast | No Code App Builder
Lovable is an AI app and website builder that turns ideas into production-ready software without coding. Launch faster with AI.
HumanLayer - Close your editor forever.
Deploy fleets of AI coding agents with the world's best UX for managing and collaborating on agent workloads. Fully open source CLI and local desktop orchestration, or use cloud sync and remote agents to scale to your whole team and all your devices.
Blog
How Coding Agents Actually Work: Inside OpenCode
A hands-on exploration of OpenCode, an open-source coding agent built with a client/server architecture. Learn how AI tools, LLMs, and real-world constraints come together to create a powerful developer experience.
Is Agentic Metadata the Next Infrastructure Layer?
If you're building AI agents, you're probably sitting on a lot of untapped data. Experts share how to put it to use.
Agent OS | The system for spec-driven development with AI coding agents
Agent OS is a popular system spec-driven development with AI coding agents. It's a free open-source framework from Builder Methods, created by Brian Casel.
Design OS | The product planning and design tool for AI-powered development
Design OS is a product planning and design tool that guides you from product vision to production-ready components. Free and open source.