James Dickerson

And then they wonder like, why, why am I not getting good results?

They're skipping kind of the boring research step, uh, oftentimes.

All right.

So, uh, normally I would wait for this to like go out and load, but, um,

In the meantime, we're just going to fire up another instance here and we'll keep working as that's doing some research.

I'm going to enter in a prompt and we're going to assume we have that research.

We can come back to it and I'm going to start using some skills.

Okay, I'm starting a AI marketing agency targeting boring local businesses that do two to $10 million a year in revenue.

I feel like they're overlooked.

I want you to use the positioning angles skill to find out how we can optimally position our company.

Now, for those wondering about skills, you can create your own skills.

Like you can say, hey, Cloud Code, I want to create a skill around finding an angle for my company, just like I did.

Now, what I do is do a very deep research process using Perplexity, using Firecrawl, using all these data sources to build my skills.

I include world-class references in there.

I review them by hand to make sure that they are good and they have all my taste built in.

You can follow that same process to do it on your own as well for whatever needs that you have.

So, right now it is loading the skill, and I always invoke this skill within my prompt.

Cloud Code can also pick it up if needed, but I typically call it out.

All right, so create an MD file with this and save it.

Cool, so we've got a bunch of like really good angles right here from our skill.