-
How to Handle a Skill That Runs in the Background
Most of the time, triggering a skill feels instant. You type a name, or your request matches one closely enough, and the instructions load right into the conversation you’re already having. Same chat, same reply, just with better instructions behind it. Some skills don’t work that way. Trigger one of those, and instead of an…
-
A Tattoo You Can’t See and Can’t Check
Anthropic announced this month that Claude now embeds an invisible watermark in the text it generates. Every response, quietly tagged. Not visible to you, not visible to the reader, but detectable to anyone holding Anthropic’s key. Files get a lighter version of the same idea: a signed C2PA credential tucked into the metadata of any…
-
Not All Subagents Are the Same
Ask Claude to track down where a function lives somewhere in a sprawling codebase, and it won’t dig through the files itself. It spins up a separate agent, hands over the question, and waits for the answer. That part of the story is familiar by now. What’s easy to miss is that the agent it…
-
The Workstation With Its Own Rulebook
One CLAUDE.md file sounds efficient right up until it has to hold “match the formality of whoever I’m replying to” and “avoid anything that trips an AI-content detector” at the same time. Those are both real rules. They just have nothing to do with each other, and stapling them into one document means Claude is…
-
The Agent That Goes Shopping For Tools
Ask Claude to pull something from Canva and, if you’ve never connected Canva, you’d expect one of two answers. Either it tells you it can’t, full stop, or it opens a browser and starts clicking around like an intern with no login. It does neither. First it checks whether there’s an actual connector for Canva,…
-
A Plugin Is a Skill With Friends
Install one skill and you’ve taught Claude a single habit. Install a plugin and you’ve handed it a whole job description. That’s the short version of what’s different here, but it’s worth slowing down, because “plugin” gets used loosely enough that people assume it’s just a bigger skill, or a fancier connector. It’s neither. It’s…
-
Doing Three Things at Once
Ask an agent to check the weather, pull tomorrow’s calendar, and look up a flight status, and there are two ways it can go. It can check the weather, wait for the answer, then check the calendar, wait for that answer, then look up the flight, wait again. Or it can fire all three at…
-
How to Set Up a Recurring Task in Claude Cowork
Every Saturday, Monday, and Wednesday at 8 in the morning, a session wakes up on its own, reads through this blog’s back catalog so it doesn’t repeat itself, brainstorms five new post ideas, writes them into a log file, and drops a reminder in a Gmail draft that a post is due the next day.…
-
How to Turn a Repeated Prompt Into a Reusable Skill
If you’ve typed some version of the same paragraph into Claude three times this month, that paragraph wants to be a skill. Here’s the pattern that usually gives it away. You’ve got a task you do often enough to have opinions about it: draft a weekly status update in a certain format, review a pull…
-
The Trust Ladder
The first task I ever handed an agent was “summarize this email thread.” Low stakes. If it got the summary wrong, I’d catch it in five seconds by just reading the thread myself. A year later, the same kind of tool is drafting replies, labeling an inbox, and running scheduled tasks that operate while I’m…
-
Letting AI Drive the Mouse
The first time you watch an AI agent move a cursor across your screen on its own, it’s a little unnerving. It clicks a button, waits, scrolls, types into a field, all without your hand anywhere near the keyboard. That’s “computer use”: an agent operating a screen the same way you would, instead of calling…
-
The Difference Between a Chatbot and an Agent
If you’ve only ever used AI as a chat box, you’ve only seen about a third of what it can do. That’s not a knock on chatbots. Typing a question and getting a good answer back is genuinely useful. It’s probably what most people picture when they hear “AI” at all. But it’s the most…
-
CLAUDE.md and MEMORY.md: The Two Files That Stop You From Repeating Yourself
I spent about three weeks re-explaining the same things to Claude at the start of every chat before it occurred to me there might be a better way. My tone preferences, my build commands, the fact that I use Proton instead of Gmail – all of it, retyped, every session, because a new chat starts…
-
Unlocking the True Potential of AI: Moving Beyond Simple Queries
Introduction Most users of AI tools like Claude often approach them as just another search box. However, it’s time to dive deeper and recognize the real power these systems can offer when utilized effectively. The Limitations of Basic Search Queries Using AI solely to pose questions and receive answers can be limiting. Here are a…
