I just published a new article on the 7 types of AI agents you can build in Claude Code.It breaks each one down in a simple way, explains how they work, and shows where they can actually be useful in real workflows. I also shared practical examples, why these agent patterns matter, and how they can help you move from simple demos to more real and useful AI systems. The full PDF guide is also attached. https://elshadk.substack.com/p/the-7-types-of-ai-agents-you-can

3 Claude Tools. 3 Types of People. Which One Are You Missing?

Not a ranking. Just what I keep coming back to: 𝗳𝗿𝗼𝗻𝘁𝗲𝗻𝗱-𝗱𝗲𝘀𝗶𝗴𝗻: stops every landing page from looking the same (Inter, purple gradient, grid cards). Forces real design direction before code gets written. 𝘀𝗶𝗺𝗽𝗹𝗶𝗳𝘆: run it after working code exists. Finds everything unnecessary and returns a cleaner version. I use it as a final pass on almost everything. 𝗯𝗿𝗼𝘄𝘀𝗲𝗿-𝘂𝘀𝗲: lets Claude control a real browser. Clicks, fills forms, takes screenshots, runs parallel sessions. Useful when there's no clean API. 𝘀𝗵𝗮𝗻𝗻𝗼𝗻: real pen tests on your staging environment. Confirmed vulnerabilities only, proof of concept included. No false positives. (systems you own, obviously) 𝘁𝗲𝘀𝘁-𝗱𝗿𝗶𝘃𝗲𝗻-𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁: activates before implementation. Enforces TDD discipline instead of writing random tests after the fact. 𝗰𝗼𝗺𝗽𝗼𝘀𝗶𝗼: Claude plus external services (Gmail, Slack, GitHub, Notion, 100+ more). Handles all OAuth and credential management. 𝗮𝗻𝘁𝗶𝗴𝗿𝗮𝘃𝗶𝘁𝘆 𝗮𝘄𝗲𝘀𝗼𝗺𝗲-𝘀𝗸𝗶𝗹𝗹𝘀: 1,200+ community skills by category. Install a bundle, keep what works, remove what doesn't. How skills work: Claude scans installed skills at startup using about 100 tokens each. Full instructions only load when relevant. You can have dozens without blowing through context. The best skill you'll install? One you build yourself. If you keep re-explaining the same workflow across sessions, that's a skill waiting to be made.

I just published a new article on how to set up Claude Computer easily. It walks through the setup process in a simple way and shows how to get started without unnecessary confusion. I also shared why this matters, how it can fit into real AI workflows, and why tools like this are becoming more practical for everyday use. https://elshadk.substack.com/p/claude-can-now-run-your-computer