Hey, welcome to the definitive resource

all about skills. I currently run a

business that does over $4 million a

year in profit and I manage it primarily

through AI agents and skills and I teach

over 2,000 people how to do the same

thing. I think a lot of demos and

walkthroughs of skills right now are

like really flashy and they're typically

centered around the personal assistant

angle, but a lot of people are leaving

tons of money on the table because

they're not applying them to specific

business use cases that actually tend to

produce large returns on investment. And

so what I wanted to do in this resource

is I just wanted to walk you guys

through what that actually looks like.

I'm going to start by showing you guys

examples of a bunch of skills that I

currently use in my $4 million a year

business, as skills that other people

are currently using across a variety of

different industries like e-com, service

businesses, consulting, and so on. And

then I'm going to show you guys how to

build them. And we're not just going to

build cookie-cutter skills that are

glorified personal assistants, but

skills that you guys could actually

implement in your business to do the

work of dozens of people in just a few

minutes. Okay? So everything you need is

in the link in the description. It'll

give you guys these skills so you guys

could use them across your own business.

It'll also give you guys the framework

that you could use to to build new ones

regardless of whatever use cases. No

fluff. Let's get right into it. So if

you don't know what I'm looking at right

now, this is anti-gravity running five

different Claude Code plugins.

If you guys are new or unfamiliar with

this sort of interface, just check the

link that I'm pasting right over here.

It'll walk you through everything from

like what the icons here mean to, you

know, how to communicate with Claude

Code and Gemini and and other, you know,

agent and coding platforms. I'm

literally from the ground up. So you'll

know everything after that. But assuming

you guys are somewhat comfortable, I

want to show you guys five different

skills today and then I'll throw in a

couple of additional bonuses. The first

one over here is going to follow up with

all of my leads. So if you guys are

running a business at really any level

of revenue over a few thousand dollars a

month, you probably have something akin

to like a list of leads or a list of

contacts. This type of thing is

typically referred to as a customer

relationship manager and in general what

you do is you store leads at different

areas along the pipeline from when you

first met them all the way to close

deals and money is in your pocket. And

so, I have an example one here with a

bunch of leads at different stages.

Meeting booked, Jimmy Clin. Proposal

sent, Sarah Chen, Jessica Park, Aisha

Mohammad, and so on and so on and so

forth. And basically, right now, in

order for me to move this pipeline

forward, every day I just have to

manually check in with all the leads.

Well, I built a skill that effectively

automates the entire process. In order

to trigger this, all I need to go and do

is go {backslash} follow up nurture.

Now, what this skill does is it'll goes

through my pipeline. It identifies and

captures all of the conversations I've

ever had with any of these prospects.

So, it actually goes through all of my

email chains and so on and so forth. And

then it uses a couple of templates to

personalize check-ins uh depending on

where they are. So, you know, if a

meeting has been booked, but we haven't

actually attended it, it might check in

with Jimmy and say, "Hey Jimmy, how's it

going? Just wanted to check in on our

meeting in a couple days. Really excited

to have it." You know, if it's to Sarah,

and maybe we send a $2,500 quote for a

specific type of product, I'd be like,

"Hey Sarah, you know, hope you had a

lovely week so far. Just wanted to

circle back on X, Y, and Z proposal. Let

me know if you have any questions." The

whole key here is we do this really

informally and then really casually, so

they think it's us. I think a big

problem that a lot of these automated

follow-up services typically run into is

they just use really like non-human

language. It's very clear, and you know,

I think prospects can tell when an L L M

does the following up for them. But, I

also like the fact that this just does

it all in one shot. And so, the workflow

is literally like you just wake up in

the morning or your salesperson wakes up

in the morning. Um they go {slash}

follow up nurture. They immediately

clear out their full pipeline of

follow-ups, and then they can just focus

on acquiring new business. What's also

cool is it does all this in the tone of

voice and in the same chain of

conversation as the initial email. And

so, in this case, this is an email that

I sent to Mr. James that said, "Hey

James, circling back on the proposal.

Let me know if I can answer any Qs." Uh

this is another one that I sent to Priya

that said, "Hi Priya, hope you had a

great week. Checking in on that test

brief. Let me know where we're at." You

know, this just continuously customizes

based off where the person is. And then

it also gets to pull in, you know,

context and

uh more or less everything that you

currently talked about. So, you're not

just repeating the same thing. This also

goes through and then it lists all of

the follow-ups that I've made to every

single person. So, you can see here

we're signing off slightly differently

between them. We're using uh reply

chains and stuff like that to stay

within the same thread. Um and I'm going

to give you guys that for free. I use it

basically every day. This second flow is

basically a one-shot thumbnail

generator. Um I have this funny image of

Jon Hamm or Don Draper in Mad Men, if

you guys are familiar. And this image

went viral a little while ago. It's all

about vibes and whatnot. And so, I

figured, you know, as somebody making

videos on vibe coding and agentic

platforms, I would try and reproduce the

thumbnail. Um but instead of doing it

manually, I'm actually just going to

say, "Reproduce the Jon Hamm thumbnail.

Use similar lighting, etc."

And then what it's going to do is it's

going to take this thumbnail or this

image, which has already been created,

then it's going to go get my face, and

then it's just going to superimpose my

face onto that image in a really

realistic-looking way. It's also,

instead of just generating one variant,

going to generate multiples so that we

can pick and choose which one looks the

best. And also because not all AI

outputs are perfect. This is an example

of the finished product, and we did that

just in a few seconds. Um I also ran it

again so you guys could see even more,

but I mean, just like going back and

forth between this, pretty freaking

close, right? However, there are some

important differences. The people in the

background are different. The lighting

is just a tiny bit different, uh and so

on and so forth. And I mean, we've we've

generated more. Uh I have this running

again in the background. This one's with

like a darker lighting and different

tone. Uh I don't know. This one here is

sort of like Matrix-style blue and

sepia. And so, all these are just a

little bit different. One's that it's

not just like a one-to-one rip of the

source image, um but also because, you

know, I get to pick and choose variants

that I like the most. And so, in my

case, I really like this one. I think

this like did the most justice to my

face, and this is probably the one I'm

going to use for my video. By the way,

despite the fact that I hate when people

do this to me, I'm going to do it to

you. If you like this sort of thing,

please subscribe. Uh something like 69%

of you guys aren't subscribed for some

reason. So, that's two out of every

three people that I'm talking to right

now. And it just significantly impacts

my channel's ability to grow. So, if

I've given you anything, any value at

any point in time over the course of

this video or any others, just click

that button for me. You'd be doing me a

big solid. Okay, back to the video. This

next one here is all about scraping

leads, and so I can actually just say,

"Scrape me 50 management consultants

in I don't know, let's just say

Arizona." And what this will do is it'll

go on LinkedIn Sales Navigator, which is

currently the highest quality place that

you can get information about real human

beings. It then creates a bunch of

LinkedIn search URLs. And in case you

guys didn't know, LinkedIn Sales

Navigator allows you to filter people

really granularly based off things like

what their job title is, um where they

live, you know, their various seniority

levels, and other industry. And then

basically I just get a list, and not

within Sales Navigator, but in a Google

Sheet with these people and then all of

their email addresses. And like

pre-existing solutions exist to do this

for Apollo and AmpiFire, but I don't

think there's like currently a big one

for LinkedIn Sales Navigator. The reason

why that's valuable is cuz there is no

better source right now for B2B lead

data than LinkedIn Sales Navigator. It's

the most current. Um most other services

just scrape from there anyway. And as a

result, I got to go straight to the

source and then just ask a system for

what I want in natural language. Uh so,

within, you know, three or four minutes

I end up with a nicely optimized list of

high-quality leads with probably like

the highest deliverability out of more

or less any source that you could get

today. And then you end up with a really

high-quality list of people, literal

their full names, first names, last

names, email addresses, and so on and so

forth that we've sourced basically

directly from LinkedIn Sales Navigator.

Um this is done pretty effectively via

cost as well. And then the fact that

it's just going to occur in the

background while I do other tasks, it

can retest its leads, it can figure out

like the best filters to use, and so on

and so forth, um eliminates a fair

amount of my own day-to-day work as

somebody that runs like a growth

management agency. This next one here

writes my cold email campaigns. So, for

those of you guys that don't know, a

cold email is something that goes to

somebody who you haven't actually talked

to before, hence why it's cold, and then

it tries to sell them on some service.

And so, I run cold emails just as my

day-to-day for a couple of clients.

Essentially, what I commonly have to do

is I have to iterate and change cold

email campaigns based off of a new

client's information. And so, what I

want to show you guys is basically how

you can automate this process. I now I'm

going to use the backslash convention.

I'll go cold-email-campaigns.

Sorry, I think that's actually a forward

slash. And this will basically ask you,

"Hey, what are the details of the

client?" And now I'm just going to voice

transcribe and say, "The client is 1

Second Copy.

Their offer is they want to write free

500-word sample articles with no strings

attached. Find the similar campaigns and

then use those as inspiration."

I'm then going to feed that in, and then

my skill is going to go through and then

essentially duplicate high-performing

pre-existing campaigns within my cold

email platform, and then rewrite them so

that they're as similar and high quality

as humanly possible for that given

niche. Then sets it all up in my cold

email platform. So, again, a step that

previously might have taken me 30 to 60

minutes just logistically is now taken

care of. And then obviously all the

offer management stuff like that is also

handled entirely autonomously. So, yeah,

I mean, this takes something that might

be 3 or 4 hours into something that

takes minutes. And then afterwards, we

end up with a bunch of different

campaigns. This is an example of one of

them that says for, I don't know, Nick,

just wrote you a blog post. "Hey Nick,

big fan of your work. Was on 1 Second

Copy site earlier. Thought I'd write you

a free 500-word sample article with a

twist. I'm not giving value up front is

how you form connections, so I thought

I'd start with that. If you have any

interest, just reply and I'll send it

right over. If you want more, just say

the word. Got a few other interesting

pieces of content for you." It also

gives you different variants that you

could use to split test, and then also

even like a little follow-up. So, in

that way, you know, me just templating

out like 80 90% of my work significantly

streamlines the actual offer building

process. And nowadays, because the

models are themselves are getting really

good, like I was doing this with Opus

4.5. Now I'm doing it with Opus 4.6.

Because the models are getting really

good, like half the time I don't

actually make a change. I just say,

"Okay, sure. Let's give this a test and

we'll see how this performs relative to

some of the other ones." The last skill

I want to show you is a simple website

builder. Basically, to make a long story

short, you know, we do a fair amount of

outreach. My goal here is I wanted a way

to quickly and easily whip up

high-quality, reasonably templated, but

also pretty unique websites for clients

or prospects. And then just send them

over, whether or not I have their

business. I was thinking about ways to

offer more value while reaching out to

people cold. And um me literally

building like end-to-end high-quality

websites and then giving them a link

that they could use to access them in

one shot. It's probably like the biggest

value add that you can get so far. So,

this is like very, very low-hanging

fruit. And I would also say that there's

quite uh room right now to do knowledge

arbitrage, where basically because you

have access to tools like this and then

most prospects don't, you could offer

either completely free websites or you

could offer a like a really simple or

templated website or something like that

in order to really blow their socks off.

When it's done, it actually pushes this

to Netlify, which is a hosting service

that lets me get a website like this.

Then I can actually just click this link

and then I have the website right over

here. And I don't think you guys could

see it so super clearly, but um it's

pretty high-quality, you know, it uses

its own customized prompt in order to

build slightly different navigation bars

and menus and then uh different content

types and stuff like that. And then you

end up with I think what most people

consider to be pretty high-quality.

Guess you guys are interested, I

showcased a really similar builder on my

Claude Code course a little while ago

and then my Gemini course as well. Um

you know, this is pretty high-quality,

right? I think if an average person were

to get a website like this for free,

they'd probably be like, "No way,

really? There has to be a catch." But

nowadays, you can generate these

deliverables for basically cents on the

dollar and then get like high-quality

animations and stuff like that um with

literally you just putting one prompt.

So, obviously, I wanted to build a bunch

of economically valuable skills and I

have dozens more, probably close to 30

or 40 right now that manage most aspects

of my bu- business. But um I also wanted

to show you guys, sorry, that's my alarm

here. I want to show you guys how easy

it was also just to build skills that

handle like really nuanced one-off

things. And so, um, in addition, I also

built a couple of cool ones that I want

to show you. One called WeWork booking,

another called Amazon shopping. And I

mean like these aren't even really as

businessy as they are me just like

dealing with a problem that I had. So,

for the WeWork one, um, WeWork is a

shared co-working space which basically

allows you to book and then show up

sometime in the next few hours. Uh, you

have access to things like kombucha on

tap sometimes. Uh, I don't know, free

coffee. Well, it's not free, I guess

we're paying for it. Looks like their

marketing's worked on me. But to make a

long story short, um, in order for me to

access WeWork, I need to like book ahead

every day. And uh, one day I tried

booking the same day and then I showed

up and my card reader didn't work and I

was like, "Why?" And they're like,

"Well, it's usually good to book ahead

because sometimes the card reader takes

time to sync." And I was like, "Well,

this sucks. I don't want to freaking do

this." And then I realized like, "Wait a

second, I have Claude now. So, why don't

I just write a skill that just

automatically books me every single day

for like the next 30 days." And so,

that's what I did. Uh, I basically just

took like 30 seconds of my day. Then I

said, "Hey, write me a skill that books

me in for WeWork." So, when I want to

access it, I just go, "Book me into

WeWork." Then this goes and books me

automatically for like the next 30 days

ahead using some credentials that I've

already set up and then it also like

actually literally opens up a tab. So,

you could see this is doing it right

here at the one that I currently

frequent, um, Steven Avenue Place. So,

I'm just going to say, "Hey, hit me.

Give this a a book." And then it'll go

through and actually make like HTTP

requests behind the scenes in order to

to push. If necessary, it'll actually

also open up WeWork so you could see it

actually like do the freaking desk

bookings, which is wild. Um, and you

know, watching this thing go is pretty

neat. And then after I built this and

then, you know, did all of the WeWork

bookings, I also naturally got more

interested in like, "Hmm, what could I

automate with my browser?" And I ended

up creating another skill. So, that was

a pretty interesting one-off build.

Takes just like 30 seconds as you see

there. You just have to log into

whatever service and then say, "Hey, I

want you to automate this with Chrome

DevTools MCP." I'll show you guys how to

do that as well. But, I was also kind of

interested in um what else I could

automate that was just kind of like a

silly personal task that I used to have

to do. And one thing that I do nowadays

quite a bit is like I just buy stuff off

Amazon, and then I have it shipped

directly to my door. And I do that

because I think, you know, I'm making a

fair amount of money, and I don't really

want to drive all the way over to Home

Depot or whatever because it'll just

consume a lot of time and energy and

ultimately be unnecessary. Why not pay

for the premium of having somebody else

do it? The only issue is, as I'm sure

you guys know, anybody here that shops

on Amazon, there's like a bajillion

listings nowadays with like um

crappy SEO, and they try and use every

term to rank for everything. So, what I

did is I just built a really simple

Chrome DevTools MCP called Amazon

Shopping. And what I do is I simply say,

"Hey, find me the best floss on Amazon."

It then loads up the Amazon skill right

over here, and then it opens up Amazon,

in my case CA. And I'm just going to

make that a little bit smaller here so

you guys can't see my postal code. And

then it automates the process of like

going through Amazon and then looking

for whatever the heck I want. So, in my

case, I'm looking for dental floss,

right? Well, it's just going to open up

one little thing here, and then it's

going to go through, and it's going to

compare all of the dental floss with

each other to find basically the best

combination of cost and then

effectiveness that does whatever I want.

And at the end of it here, you can see

we have all of the products that it's

recommending um literally in just like a

little sheet, so I can give this a quick

click. We also have the cost, uh

popularity, the why buy, and so on and

so forth. Uh and then, you know, he

basically uses all these things in order

to recommend them. So, I basically built

like a personal shopper app. Um I've

done the same thing with like grocery

delivery, which is pretty cool. So, I

just one-shot my grocery delivery. I go

on, you know, Instacart or another

related service, click a few buttons,

and then boom, you know, I'm basically

done for the rest of the year. Uh and

you know, you could build these sorts of

one-off systems at this point now with

Opus 4.6, you know, GPT 5.2, 5.3, or uh

Gemini 3.1, whatever model you want to

use, whether or not you're using Claude

Code or some other platform, okay?

Now that you guys have seen at least a

little bit about what I think like

actual helpful useful skills that

realistically move the needle, not just

glorified um you know, personal

assistant demos look like. Let me show

you guys how to actually go ahead and

then build them. Okay, so first, if it's

not already abundantly clear, skills are

basically the evolution of standard

operating procedures just for agents.

Whereas SOPs and checklists are for

human beings for the most part, skills

are for these new AI agent

intelligences. And just as such, you

wouldn't really just give a checklist

over to an agent and say do it. You'd

have to translate its language just a

little bit into sort of like the native

format that the agent understands. So, a

brief example here, if I have maybe a

checklist and it's make a PB

and J sandwich. And you know, I work at

a company where all we do all day is

make PB&J sandwiches. Boy, would I love

to live there.

You can imagine how new hires go their

very first day and then they're given a

checklist of tasks. And it's basically

take bread

out of basket.

Put jam on one side.

Put peanut butter on the other side. And

then maybe one final one that just says

stick them together. So, this might be

for a human. And essentially, as a human

goes through it, what do we do? We

obviously check all of these tasks off.

That's just how standard operating

procedures are in business. They just

for the most part standardize things,

hence the name. Because this is

organized differently for agents than

you know, for human beings, we organize

them into what are called markdown or

.md files. And these markdown files are

basically just text files with a little

bit of a twist. For instance, I have a

markdown or .md file open over here. If

I try and create a new file here and

then I call it skill spec.txt and then I

paste everything in, you notice how

everything is the same color. Whereas,

if I go back to that markdown variant,

we all of a sudden have blue, we have

orange, we even have some green.

Well, the way that markdown files work

is they take base data, and then they

also take a little bit of formatting,

and then they apply the formatting to

the base data, just so that it's a

little bit easier to see, a little bit

more interpretable.

And so, if you guys could tell, the data

that we're marking up here, okay,

funnily cuz it's called markdown, but

the data that we're changing the the

color of and stuff like that, is usually

prepended with a couple of symbols. The

first symbol here is this little

hashtag.

This always refers to like a header. And

so, you can kind of think of it like a

chapter heading in a book. Another one

are these sort of backticks here, which

typically refer to files. There are a

couple of other little tiny formatting

things here, like links and so on and so

forth, that you don't really get with

TXT files, but hopefully you guys

understand that it's not really that big

of a deal to memorize everything in a

markdown file. You just have to know

that they're slightly different

formatting compared to text files. The

reason why is because you're never

really going to have to make them

yourself. All you're going to have to do

is just give your agent some bullet

points, usually a brief description,

which I'll show you how to do, and then

it'll combine all of that into the

optimal markdown skill format for you.

Now, unlike just a few months ago, today

every major provider on Earth,

basically, so our OpenAI's, our

Google's, our I wrote Claude here, but I

really meant Anthropic. They're all

moving towards harnessing and then

making skills generally available, just

as part of like their their their LLMs.

And so, here you could see Anthropic has

a page on their Claude code box that say

extend Claude with skills. These are the

guys that sort of made skills up first,

but because of popularity, a bunch of

people um that were OpenAI developers

and stuff like that started talking

about it and asking for it. And so,

they've created their own skills format.

It's very, very close to the Claude code

skills format. And then also, over here

the Gemini CLI, you could see you can

add agent skills.

Basically, no matter what framework or

LLM or platform you're using, you can do

the exact same thing. So, my rule of

thumb is if you guys have a standard

operating procedure, if you have an SOP,

you have a skill. Okay, all you really

have to do is just copy that SOP from

your business and feed it into Claude or

Gemini or Codex and ask it to make a

skill. As of the time of this recording,

the skills spec or definition is it's

not like baked directly into the models.

So, the one thing that you have to do in

addition to that is you basically have

to give it the skill spec and then ask

it to turn your task list into a skill.

But, assuming you can, you know, drag a

file into your freaking working

directory and assuming you have any SOPs

at all, even poorly written ones, you

now basically have an agent capable of

doing a big chunk of your knowledge

work. Once you're done with this, you

just ask the agent to run it at least

once cuz you have to test and amend.

On the first run, if the agent needs

something else, it'll ask you for it.

Otherwise, it'll build the asset

yourself itself. So, maybe like an Excel

file or something like that, it'll

actually put that together for you.

Although obviously if you have assets

like some contacts or PDFs or whatever,

you can provide them, no problem. And

then assuming that you prompted it right

with the spec that I'm going to provide

to you, every time the skill runs after

that, if the agent finds a mistake while

doing it or maybe a service is out or it

doesn't have the knowledge it needs,

it'll automatically figure out how to

solve it and then it'll patch the skill

for you. And so, in that way, here's the

real power of skills, they're

self-healing over time. They heal

themselves. They get better, they

improve constantly. Much like an

ambitious intelligent staff member who

sees a checklist, notices that there's a

gap and then chooses to fill it. Skills

are the same thing, just with agents,

which is what makes them so incredible.

So, why don't we get started and produce

ourselves some skills and then as we

produce and then shortly after, I'll

also run through the special directory

of dot Claude skills, which with Claude

is how you organize these things. I'll

also touch on just a couple of other

ones in case you're using a different

LLM. But for the most part, they're

going to be exactly the same.

So, the very first thing you need to do

is you need to grab the skillspec.md.

And you can grab that down below from

the Google Drive link. Um it's free, as

mentioned, you don't need to sign up or

give me your email. I don't need it. I

have enough of those.

And what you're going to see in here is

basically the condensed spec or

definition of skills, as well as the

file structure, all the locations, all

the different formatting options, and

stuff like that. Um and what we're going

to do is we're going to give this to our

agent alongside our request, so that it

can just figure out how to put together

the highest quality skills for us.

What I did in order to put this

together, by the way, is I just went

over to Anthropic's Claude code docs

with skills page. I copied the entire

thing, fed it back into the LLM, and

then just said, "Hey, I want you to

really, really shorten this, compress

this, significantly increase the

information density, because I don't

want this to be 500 lines. I want this

to be, you know, 150 to 200."

Okay, so once we have this, basically

what we do is we just make this our

Claude.md.

You know, just so we're on the same page

here, Claude.md is just the prompt

that's injected at the top of every new

conversation. And so, what I'm going to

do is I'm just going to rename this and

just call this old Claude.md. And this

one here is going to be the new

Claude.md or just Claude.md. Any

[snorts] file in your root directory

that contains the capital c a c l a u d

e dot lowercase m d will automatically

be prepended and and added to the

prompt. And so, what we do is basically

by by doing this,

every workspace where it is just

automatically going to know what skills

are. If you have other stuff in your

Claude.md, you can also just copy this

and then paste this um as well.

Although, you know, at least for the

purposes of creating skills, I recommend

just being as short and and

straightforward, and basically having

this in as few lines as humanly

possible. Next up, to build your skill,

just open up a new agent window. So,

I've just done that here with Claude

code, and then just tell it what you

want it to do. I'm going to use a voice

transcription tool, Whisper flow, just

to put in my own SOP.

What I want to do, at least for this

demo, is just build a simple inbox

cleanup tool that just goes through my

inbox, and then

opens up all of the unread messages, and

then just immediately reads all the ones

that are pointless and sort of, I don't

know, invoice reminders or follow-ups

about whatever or simple templates.

And then I want it to highlight, like

realistically, the high priority emails

in my inbox, so that I just have a short

list of everything. So, it's pretty

simple and straightforward. I'm just

going to hold this little key down, and

then say, "I'd like to build a Claude

code skill that goes through my inbox,

identifies all unread messages, reads

all of the unread messages, and then

marks as read all of the ones that

aren't

important to me or high priority."

My definition for important is basically

anything that isn't automatically

generated. If the email is automatically

generated by, like, a service or it's a

simple notification email or whatever,

it's not important. If the email is

written by, like, some cold email

copywriting fellow who's trying to reach

out and get my business, it's not

important. The only stuff that is

important are emails that are

personalized, customized, and that give

off the vibe that they were written

basically just for me. Once we're done,

we're going to feed that right in. Then

we're going to go ahead and build it.

The very first thing it's going to do is

look at all of the existing skills in

any Gmail code inside of my workspace

to see if there's anything that it could

use. And it's doing this because, you

know, as human beings go, we don't

really want to rebuild the wheel if we

don't have to, right? So, this is it

just reading everything right now. You

can see that it's also changed to plan

mode. That's why that little thing in

the bottom left-hand corner has changed

alongside that red bypass permissions

color to blue. This happens more or less

anytime you try and build something that

it would consider to be even slightly

complicated. It wants to go into plan

mode so that it can plan out the build

of the skill. Now it correctly went

through and found that I had a couple of

configuration files that allowed it to

use different emails here. And for the

purposes of this demo, I'm just going to

use this one. Obviously, if you didn't

have this, it would just ask you what

email do you want to set up. Now what

it's going to do is actually create the

skill the old on MD. It's also going to

create a script for me, which looks like

it's going to call inbox_cleaner.

Then afterwards, it's going to test it

end to end. Why? Because that's just

what's in our spec sheet. We basically

tell it how to do all of this stuff

natively.

Now what it's going to do is create the

script. You could see that because I

have a pre-existing skill, that

follow-up one that I was showing you

guys, it gets to borrow based off of

that. And you can see that it's actually

gone ahead and wrote the script.

If I go to inbox_cleaner

here and actually look at the skill.md,

you can see it right over here. If we

just make this a little bit bigger,

let's move this here so we can focus on

this.

Basically, what we have is a

step-by-step guide for a future agent on

how to do the task that I just asked it

to. You now see that it's now been

organized in a very particular way.

For instance, there are these three

dashes up at the top, three dashes

underneath the section. There's a name

key that says inbox cleaner, a

description key that says clean up key

mail inbox by reading all unread emails

using add identifier which ones are

generally important and mark them the

rest as read. User cleaning inbox,

triaging email, or clearing unread

notifications. Then it also allows it to

use some tools. Now you may be

wondering, you know, I think these two

are pretty self-explanatory, but why is

it allowing certain tools? Well, Claude

and all other LLMs basically have access

to some little pieces of software under

the hood. Like they can read files, they

can grep, glob, or bash. And these are

just various like command line utilities

that allow it to look through files,

look for specific sections, and so on

and so forth. And so, what we've done

with this skill, okay, it's almost like

a sub agent. We've basically given it

the ability to do these sorts of things

when we invoke or instantiate this.

Aside from that, we have the title, we

have the goal, what counts as important,

what gets marked as red. Notice how it

basically took everything that I have

provided it in just a few lines of voice

transcription, and then turn this into a

pretty coherent and then consistent SOP.

Now, going back to the actual building

thread here, it's actually gone ahead,

wrote the script, and now it's doing the

classification. We give this button a

quick little click, you could see that

it's now doing it in batches of 10,

which I didn't even ask it to, okay?

It's identified which ones it considers

important, which ones are not important,

and now it's saying, "Hey, do you want

me to mark these 97 emails as red now?"

I don't actually want it to mark the 97

as red. What I want it to do is I want

it to show me what they are so that I

could tell it which ones are right. So,

I'll say, "No, I'd actually like you to

show me all of the 97 that you marked as

red so that I could take a look and tell

you if there are any exceptions." Now,

what it's going to do is give me a big

list of all of the emails, and as you

can see here, it has correctly

identified that 79 of the emails I got

were from a broken make scenario. So,

that's pretty interesting. Um obviously,

these are more or less exactly the sorts

of emails I don't really want to One is

some normal commission notification from

referral stack, another is a

subscription renewal for that voice

transcription flow. Another's from

Bright Data, another's from whatever

company. I got a bunch of cold outreach

over here, okay? I have sponsorship

pitches, one word yes reply to lead

magnet. I guess what I'm trying to say

is this did a really good job. There

isn't a single email here that I

actually really care about. So, I'm just

going to say, "Nope, mark all as red."

That's pretty sweet, right? Now, at any

point in time, I could open up a new

Claude instance, and we have to go new

just because of how skills work, okay?

Then we can go {slash} inbox cleaner,

and then we can run it. And because we

are running based off of this SOP, it's

always going to run in the exact same

way. It's going to be repeatable,

consistent, and dependable. Also, if it

runs into any issue, let's say the

script doesn't work, let's say there's

an API rate limit or something like

that,

it will identify the problem and then

automatically go through fix it and then

rewrite its own skill. In my case, I've

got a lot of unread emails. So, I think

what I'll do is I'll say, "Hey, I've got

a ton of unreads. Could you actually go

through and fetch a thousand instead of

a hundred?" And now I have the ability

also to modify the way that the skill

works just a little bit, so that instead

of the base 100, maybe I can do a

thousand. Maybe I could pass in a flag

like {dash} A, and that stands for

amount, and then I can do You can see

it's actually what's going on under the

hood. It's passing the the a number

1,000 to said script. Now that you guys

see how these skills actually work in

practice and how to easy it is to build

one as long as you have the right spec

sheet, I just want to really quickly

deconstruct the various parts of this

file, make sure that you guys understand

how all of this stuff works and the what

each of these parts are for.

Okay, so you guys have probably already

noticed these three little dots here are

really different from all the formatting

elsewhere.

What this basically is, in at least

markdown speak, is something called

front matter.

Front matter is a highly optimized way

of basically putting a tiny summary at

the beginning of any markdown file.

Remember how there's different fields

and colors like keys,

headings, there's sort of more headings.

I mean, there's a lot of different

things here. But, you can just think of

front matter as being the same idea.

It's just a different like variable or

type. And the way that you start it is

with these three uh dashes, and then you

end it with these three dashes. And so,

this little summary is is doing you a

massive service

by significantly reducing the number of

tokens that you need to load into your

context window at any point in time. If

you think about it, what we could be

doing every time we load this skill in,

if I just copy this whole thing and go

to a free word counting service, is we

could be adding 373 words, which is

approximately 500 tokens into context,

okay?

But with front matter, what we do is

instead of storing the entire script

into context and making it accessible to

the model, we do is we store a much

smaller summary, which is closer to like

60 or 70 tokens, and then we say, "Hey,

if the user calls inbox cleaner

specifically, then and only then do I

want you to load the other you know, 350

words or so, okay?" And so, what this

means is in practice, if I were to show

you guys all of the different skills

that are currently loaded into context,

they basically all look like this.

And so, my prompt at the very beginning,

just assuming I have these three skills,

is always basically going to be my

claw.md up here.

Underneath, we're going to have our

skills, so there's going to be one, two,

three.

And then underneath it'll be your

prompt, which is basically whatever the

heck you want to say. "Hey, I want to do

XYZ."

And so, this is more or less the

structure that every conversation with

Claude, in my case, but obviously any

LLM in yours, whether it's gemini.md,

agents.md, so on and so forth, is going

to realistically look like. You'll have

your prompt down here, but before then

you'll have a bunch of hidden stuff. And

then what's cool is, you know, if you

say, "Hey, I want to do

um follow-ups," what it's going to do is

it's going to say, "Follow-ups, wait a

second. I know that we have some

follow-ups mentioned earlier on under

the skills section. Okay, great. That

means this must be a standardized

skill." And then it'll go and actually

load the whole follow-up nurture

directly into its context, which will be

the rest of this, and then it'll

basically stick the rest right here, and

then resubmit the prompt, and now it

knows everything that it needs to do in

order to obviously get that right. So,

the agent would go, "Okay, great. I have

the skill spec right here. Let me follow

each step." And then it'll go and, you

know, start with number one, which is

load pending leads. Number two, for each

pending lead, and so on and so on and so

forth. Now, this actually has a term.

This is called skill matching. Anytime a

user types a request like, "Hey, get me

50 dental leads." It'll automatically

scan those descriptions or that front

matter for whatever the most relevant

is. It says find business leads. Here,

it says find business leads. Here, it'll

say, "Oh, this must be the one that they

want." Then it'll load the full skill.md

in the context before finally calling

some scripts, okay? And then giving you

guys an output. And where you put those

scripts don't really matter. The basic

skill definition, I think, just bundles

it all into one folder. You could put

the script somewhere else if you want to

keep them organized. And if you have

other assets like PDFs or whatever, you

can build whatever scheme you want to

keep those files handy. The reason we do

this, of course, is both for efficiency

because the less context in a model's

context window at any point in time, the

higher the quality of the output, but

also for costs. Providers like Anthropic

and so on and so forth actually don't

want you to spend an arm and a leg,

believe it or not. Um they want you to

continue using their software, and in

order to do so, they need to make it

like reasonably cost-efficient for you

and deliver a high ROI to you um at the

same time. And so, this concept of

progressive disclosure is now not only

really being applied to skills, but a

lot of other things as well. And all

this is again the pursuit of reduced

cost, reduced overhead. Okay, let's

build three more skills with what we

know now. And just for simplicity and to

make this as fast as humanly possible,

both for myself and for you guys, what

I'm going to do is I'm going to open up

three separate Claude code little

plugin, which it's here.

And in the first, I'm going to switch

all these to bypass permissions.

I'll make this a little bit smaller so

you guys could see.

And then in the first, I'm going to

paste in skill number one.

In the second, I'll paste in the skill

number two.

In the third, I'll paste in the skill

number three.

What I'm going to say is create skill

one, create skill two, and create skill

three. And we're just going to trigger

all three of these and see how they

operate.

So, what skill one is is it's a simple

way to turn meeting notes to action

items. We basically just paste in a

meeting transcript and get a structured

action item with owners and deadlines

and so on and so forth. The idea here is

to show you guys that a skill can be

really nothing more like an SOP which

doesn't even include Python scripts or

anything like that.

The second one is an invoice data

extractor, which is basically going to

be skilled on MD plus some Python

script. So, we're going to take a PDF

invoice then return structured JSON in

the form of a vendor, amount, date, line

items, and tax. And this is to help you

guys see how skills can delegate

deterministic work to code. AKA, we can

use Python scripts and whatnot like you

guys have already seen.

And then the third skill is going to be

a content repurposer, which is going to

let us take a transcript and then output

a tweet thread, a LinkedIn post, and

then a newsletter draft all in parallel.

And the idea here is we're going to have

templates. I'll show you guys some brief

examples. And I'll also show you guys

how this works with some instructions.

And so, before I was even finished

reading this freaking thing, we're

almost already done two out of the

three. Isn't that wild?

Anyway, the first skill pretty

straightforward just called meeting

notes. It just processes meeting notes.

So, what we can do here if we want is we

could say, "Hey, I want you to output

specific elements of the meeting." In

this case, it has some decisions, open

questions, and so on and so forth. But I

also want you to find and identify any

contact information. So, I'll say, "Hey,

this is great. I want you to update the

skill also to extract any contact

information that's mentioned. I'm

looking for things like email addresses,

websites. I'm looking for phone numbers

and so on and so forth. Anything that

somebody offhand mentions during the

call." Sometimes we also specifically

ask for this information for follow-up

reasons. So, it would be nice to have it

in structured sort of way. Over here,

it's now created both files of the

invoice data extractor. So, we could see

there's a skill.md here, which basically

takes the PDF invoice, returns

structured JSON with vendor. So, in

order for me to really appreciate how

this works, I'm actually going to go and

grab myself a brief little invoice, uh

just feed in it in an example, and then

we'll see how it works. I see a couple

of services here that have sample

invoices. This one looks pretty good.

Why don't I download this?

I'll say example_invoice.

What I want to do is I just want to feed

this in right over here. And I'll say,

"Great. Use this on

example_invoice.pdf."

Then over here, it looks like this is

now done. And what I'm going to do is

I'm going to go find some of my own

content and just feed that in just as an

example. So, we'll go on my YouTube

channel and I'll find something that is

probably not 4 hours because that would

take a lot of tokens for no purpose.

This 10-minute one looks pretty good. I

said,

"Let's get my fat ugly head to shut the

heck up."

I'll scroll down here to where it says

show transcript. And then right now,

just cuz it's an example, I'm just going

to copy all the stuff in manually, but

obviously you guys could do whatever you

want with this.

Going back here, I'll then paste this

in.

And what I want to do is I basically

just want to see whether or not it can

do all of those three things. I'm also

going to take a quick peek here at the

script. And um this is what I wanted to

happen actually, which is nice. It ran

into an issue with one of the summary

rows and the subtotal. So, what it's

doing now is it's actually going to fix

the script's filtering logic so that it

doesn't catch the subtotal or the credit

terms or something like that. Okay,

cool. On the right-hand side, it's

extracted this transcript. Looks pretty

good. And now what it's going to do is

spawn all three formats in parallel,

which is its way of saying it's going to

rewrite my uh main transcript and turn

this into like blog posts and Twitter

threads, whatever the heck it's going to

do. While all of this is happening, this

is me pictured. I'm just manifesting all

of the skills. I actually have to do too

much. I just kind of close my eyes and

wait, and then they appear. Taking a

look at this tweet thread over here.

Let's just make this look a little bit

prettier.

We now have a bunch of tweets that are

divided, and this is automatic, which is

pretty cool. A 16-year-old posted a

prompt on Twitter. Former professional

web designer copy-pasted in a Gemini.

The AI produced a better site than he

could in 5 hours in minutes. Design is

commoditized. Should you guys have seen

these sorts of threads all over the

internet? Let me tell you why. It's

because people have built very simple

repurposing pipelines like this. And

although that one just took me 5

seconds, the content's reasonable. Not

going to say it's going to win any

awards. It's pretty LLM-y, but hopefully

you guys could see with at least a few

neurons between your two ears, you guys

could repurpose, change the tone of

voice, and so on and so forth, and make

it something actually pretty cool.

Likewise, we also have LinkedIn posts,

and then we even have a newsletter draft

for me. So, that's pretty sweet. You can

see that its design decision was to do

this via Sonnet sub-agents. You guys can

modify this SOP at any point with

literally just a line. Finally, in the

middle here, skill two is all good to

go. Great job. It's gone through and

it's actually updated the main skill as

well, which is quite neat. If you guys

were paying attention, you would have

noted that every time that we add a new

skill, or change skills, or whatever,

there's a top left folder over here

that's {dot} Claude {slash} skills that

changes. And this is essentially the

format and file directory structure of a

skill. So, it's worth us pointing it

out. Now, in case you guys have never

seen this convention in the top

left-most corner, you see how there's a

little dot in front of a Claude folder?

Well, that's basically just the kind of

universal file explorer convention for

hidden. Now, if I open up this exact

folder, the skills example folder, in my

macOS native file explorer,

you notice that it looks pretty

different from what we're seeing over

here.

Notice how on the left-hand side we have

{dot} Claude {dot} tmp, then we have one

second copy config data. And notice over

here that the list actually starts at

one second copy, then goes Claude.md,

then it goes config, and then it goes

data. So, I mean, aside from the fact

that this is organized a little bit

differently, generally speaking, we

always have folders organized first in

the file explorer here. So, if we kind

of match that up one for one, you'll

notice that the only things that are

missing are basically the files and the

folders with little periods in front of

them.

So, the first thing to note is like most

people just have no idea where this

thing is because when they go to the

file explorer, like it's always hidden.

Well, in macOS it's pretty easy to

reveal. You just go shift command uh

dot period basically and then you can

show all hidden folders. They'll be

present. It's just they'll be a little

bit um more translucent. And then we can

actually open it up and then go through

all the skills.

Okay, so that's the very first thing to

know. On a Windows, which you guys may

be using, it's it'll be a different

hotkey. Just Google it. There's uh

plenty of information on there about

hidden files. I think you can also just

right click and go like show hidden

files or something cuz I used to have a

PC and that was pretty straightforward.

But uh yeah, essentially inside of every

main workspace in any sort of IDE, if

you do have skills, they're probably

going to be hidden from you, which is

kind of difficult and and intimidating

to to kind of understand.

Okay, so then after that, the way that

it's organized, which is not super

plainly clear here, so to make it a

little bit clearer for you guys, is you

have the dot Claude folder, right?

And then underneath the dot Claude

folder, you have the skills folder.

Then underneath the skills folder, you

actually have the specific skill folder

that you want. So, let's just go, you

know, inbox cleaner.

That's another folder and then inside of

that folder, you actually have the skill

file itself. So, then you have the

skill.md. So, notice how nested this is.

I mean, it's a massive pain in the butt.

I don't know why they do it like this,

but um they make it pretty difficult for

most beginners to understand. Um and

they do so in this sort of like

hierarchy that begins again with dot

Claude, then go skills, then go you

know, the specific name of the skill and

then the skill.md itself. And then over

here, okay, and this is sort of

optional, but this is how Anthropic

typically does it. Here, you can put

your other stuff.

What is your other stuff? Well, your

other stuff is going to be things like

your scripts. So, hypothetically, if you

had like scripts that helped you do the

invoice cleaner inbox cleaner or

whatever, maybe an inbox uh dash

cleaner.py,

you know, you'd probably put it

somewhere in here. I personally like

doing it in a different folder called

execution. Sue me. I just think it makes

more sense, a little bit cleaner. Uh

likewise, if you have, I don't know,

like your Gmail off tokens or something,

you know, you might include them over

here. If you have, I don't know, some

other file like example.txt,

um you'd include it over here. And so

this is just like the base way that all

skills are organized. And yeah, I think

it's just unfortunate that it's usually

a hidden folder, which is kind of

intimidating. I should note that the

skills live right alongside a bunch of

other hidden folders like agents and

stuff like that. Um I can't really talk

about this now, but if you want more

contacts on that, just check out my

full-length Cloud Code course. I got a

ton of juice for you in there. Okay,

last thing I really want to do is just

talk a little bit about what skills are

actually worth making.

You know, I do a lot of business

consulting now. Uh somebody that started

in door-to-door sales, I saw the

importance of focusing on the levers

that actually increased revenue first

and foremost above all else. And so for

me, it was always door-to-door. But then

transitioning into marketing and then

broader through things like uh content

creation, articles, and now videos. I

think a lot of people are very

misaligned on what like a high revenue

SOP even looks like to begin with. And

the reality is with agents nowadays, you

can do anything. But that doesn't mean

that you should do everything.

These things are so damn good. They can,

of course, design whatever crazy

back-end fulfillment pipeline you want.

But I find most of the demos on the

internet that talk about stuff like that

are really miss the mark because we've

been able to design these pipelines

forever. And most people that do these

sorts of things still don't make any

money.

The difference between people that use

new, upcoming, and trend-breaking

technology to make money and actually

have big, you know, success outcomes

versus people that

play shiny object syndrome all day and

just collect a bunch of Pokémon cards

are the former group focuses primarily

on the front end of their business. So

they They on the acquisition of

opportunities. They focus on the

generation of leads. They focus on

mechanisms that improve the quality of

the sales experience for their leads.

They focus on selling closing mechanisms

and so on and so forth.

And then the latter people just over

complexify the hell out of everything

and then make every excuse under the sun

not to focus on sales and marketing. So,

this is all just like a pretty

meandering and long way of saying, if

you're going to design skills, I highly

recommend you focus the design of those

skills primarily on front-end tasks.

Like most of the people that are going

to be watching this video, you know,

they're probably going to have some sort

of side hustle going on or they're going

to be looking to get into that realm.

The simplest and easiest way that you

can move the needle in your own business

is if you're going to design skills and

stuff like that, spend your time

designing them on things that help get

you sales, on things that help, you

know, you do your marketing faster and

better. And then don't just have them

sit around in your folder. Actually use

them. You know, when I was growing my

business, I was doing somewhere between

50 to 100 cold calls every single day.

When I was going door-to-door, it was

something like 80 knocks on physical

doors per day. I wish I had a hundredth

of the technology we have today. I'm not

even that old

to go back and then automate that

process for me. I don't. But it blows my

mind how many people do and then they

choose not to use it on things that

actually make money like those laborious

door-to-door sessions or or cold calls

or whatever. Okay, so ultimately things

that I have seen work really, really

well.

Content repurposing pipelines. These

genuinely can significantly improve your

reach assuming you're growing a brand.

That's for inbound. Lead generation

systems. Things that do stuff like

scrape leads for you. Those are really

big. Skills that use Chrome DevTools MCP

to post on forums automatically for you.

To, you know, do product research

quickly and then tell you which threads

are saying bad things about your

product. These things are valuable.

Skills that, you know, quickly go

through a bunch of books and identify

which things are business expenses and

can be written off versus things that

aren't. These sorts of skills are

valuable. The skills that are not super

valuable are like skills that help you

build other skills or skills that

invent some new design framework that

assists you in the building of AGI,

right? These things are not ultimately

the stuff that I want you to take away

from this video. I want you to focus on

real practical use cases that actually

move the needle for your own business or

the businesses that you're working with.

Cuz at the end of the day, that's the

stuff that's going to make the economy

more efficient. That's the stuff that's

going to make you more money as you know

AI swallows up more and more knowledge

work. All right? So hopefully I didn't

bore anybody to death. Guys, I'd like to

make a big ask. If you guys like my

content, please subscribe. I realized

the other day that 69 point something

percent of all of the people that

regularly watch my content are not

subscribed. That means about two out of

the three people that I'm talking to

right now for whatever reason haven't.

If you like the sort of content that I

make,

you know, the algorithm really does like

it if you subscribe and then it pushes

my YouTube channel to a bunch of new

audiences. But if I don't get enough

subscribers, then none of that stuff

happens and then most of my videos bomb.

So I really appreciate anybody that has

taken the time and energy to subscribe

and I'm not going to do a big cry

session here. Although as a newbie

YouTuber, I always wondered why

everybody was pitching me on subscribe

this, subscribe that. And now I think I

get it. Most people just never do.

But yeah, I would really appreciate it.

Aside from that, if you guys like this

sort of thing, just leave a comment down

below with any sort of question or

recommendation as to future content and

I will happily take that into

consideration. I have skills that now

scan my YouTube comments and then use

that to help me ideate new videos to

make and so on and so forth. So yeah, a

lot of cool stuff in the works for you

guys, but I definitely love to know what

direction to take it. Thank you very

much for watching. Have a lovely rest of

the day.