Most people fix a bad ChatGPT answer by rewriting the whole question. There's a faster way. Type one word. Answer ran too long? Type `TLDR` Want it compared properly? Type `TABLE` Want it to argue against you instead of agreeing with everything? Type `/steelman` Question is a mess and you know it? Type `/autoprompt` and let it write the better prompt first. These are command codes. Nothing to install, no plugins, no custom instructions. They work because one clear word describes what you want better than a paragraph of explanation does. I put 98 of them into a clean PDF for you. Ten categories: ✅ Writing and style ✅ Explanation depth (ELI5 all the way up to ELIPhD) ✅ Format and output ✅ Learning and study ✅ Ideas and brainstorming ✅ Creative and content ✅ Analysis and decisions ✅ Thinking systems ✅ Utility and power commands ✅ Coding Inside you also get the three ways to use a code, the ten worth memorising first, and the combos that work well stacked together. The one I use most: `SECONDORDER` It asks what happens after the obvious consequence. Most decisions look great at step one and fall apart at step two. PDF is attached 👇 Print it or keep it open in a second tab. **Got a code you use every day that isn't in there? Drop it in the comments and I'll add it to version 2.**

Catch the AI in your writing. There's a specific way AI writes that no person ever does: fake-profound, self-narrating, allergic to a plain sentence. The "not X — it's Y" reframe. The mic-drop closing line. "Worth naming." Calling everything "load-bearing." Once you see it, you can't unsee it, and it's showing up in emails, posts, and blogs everywhere. SlopCheck names those patterns and strips them out. It's a writing skill you can install, and a set of rules you can paste into any tool. What it does Three modes: - Guide — the model loads the rules before it writes, so the slop never shows up. - Detect — paste a draft, get every tic flagged by name and a 0–100 "human score." - Rewrite — get a plain-English version back, with a one-line note on what was cut.

Have a logo you made in ChatGPT, but can't use it big because it goes blurry? Need one for cheap, that also scales with however your business shows up in real life? It's just a few clicks and about 20 bucks away to get a graphic-designer quality logo. I would know because I'm a professional brand designer and I've used this workflow for real clients with amazing results. Best of all? Don't bother reading this handy guide. Feed it into your favourite AI to work with, and let IT take you through the process. It's that easy.

The setup guide for building your own AI executive assistant has been rebuilt, and the new version is attached to this post. The old one had two problems. It was written to follow along with a call, so the sections had video timestamps in them and it read strangely on its own. And the most important part, the big setup prompt, lived on my site as a link. If you came across the guide later, or forwarded it to someone, that link was easy to miss and the guide stopped working without it. Both are fixed. It is now one self-contained document. The full setup prompt is Appendix A at the back, so you copy it straight out of the PDF and paste it into Claude Code. Nothing to go hunting for. I also stripped it down so it is not branded to me or to this group. No logos, no references to our calls, and the examples are generic business examples instead of listing appointments and showings. That was deliberate. Several of you run teams, and a few of you have people who would use this. You can now hand this PDF to an assistant, a partner, or another agent, and it will not look like you passed along somebody else's marketing. What is inside: - Parts 1 to 3: install Claude Code, create your project, run the interview that teaches it your business - Part 4: your first skill (a daily brief) and your first sub-agent (call prep) - Part 5: how to keep it useful over months instead of abandoning it in week two - Part 6: connecting Gmail, Calendar, and Drive so it can actually send the email, not just draft it Set aside 30 minutes for Parts 1 through 3. That is enough to have something working. Part 6 is the technical one. It involves a few Google settings pages you have probably never opened. Every step is written out and every error I have watched people hit is in the troubleshooting section at the end of it. Take it slowly and it is fine. One suggestion. Do not skim the interview in Part 3. That is the part that decides whether this thing is useful to you or generic. The more real detail you give it about your business, your team, and what you are actually working on, the better everything downstream gets.