Getting the transcript
Reading the captions from YouTube. A video nobody has opened here before takes 10 to 30 seconds; this page fills in on its own.
Getting the transcript
Reading the captions from YouTube. A video nobody has opened here before takes 10 to 30 seconds; this page fills in on its own.

Apify · @Apify
Words
1,740
Runtime
12:08
Speaking pace
143wpm
Reading time
7min
143 words per minute, below the 160 25th percentile of 349 measured videos. That distribution comes from the 349-video hook study.
Opening (first 30 seconds)
Hi, this is Sammy from Apify. So, unless you've been living under a rock, you know about Claude code. It's been the hottest thing in AI right now. But, many people think that Claude code is for developers only. It's actually quite easy and with the Claude code section inside Claude desktop, even business users can use it. And what makes Claude code effective are skills. What are skills? Well, just like
72 words, the words spoken in the first 30 seconds at 143 words per minute.
Free, no signup. See how the first 30 seconds hold attention, with rewrites.
Sentence shape
| Measure | This transcript |
|---|---|
| Sentences | 158 |
| Average words per sentence | 11.0 |
| Longest sentence | 33 words |
| Questions asked | 11 |
| Sentences containing a number | 5 |
Most used terms
Filler phrases
72 in total: actually 22 · um 15 · uh 9 · you know 9 · right? 8 · like 5 · basically 3 · kind of 1.
A literal whole-word count of the same phrase list the Prepublish browser extension uses, so a phrase inside another word is not counted and a phrase used in its ordinary sense still is. It is a count and not a judgement.
What this transcript is
Every word below is the caption track YouTube publishes for this video, pulled from the video itself and reproduced unchanged. It is not Prepublish's writing, not a summary, and not a re-transcription: it is the video's own published captions. English captions, generated automatically by YouTube, in the video’s original language. Source: the video on YouTube. A channel that would rather this page did not exist can ask for its removal through the contact page, and it is removed.
No Script X-ray for this video: YouTube shows a Most replayed graph only once a video has enough views.
Hi, this is Sammy from Apify. So, unless you've been living under a rock, you know about Claude code. It's been the hottest thing in AI right now. But, many people think that Claude code is for developers only. It's actually quite easy and with the Claude code section inside Claude desktop, even business users can use it. And what makes Claude code effective are skills. What are skills? Well, just like skills that you might have like riding a bike or painting, skills allow the AI agent to actually do tasks effectively and they also involve some call two calls.
So, today I want to show you how you can use Claude code inside Claude desktop, which makes it easy for anybody to do and use Apify skills, specifically the ultimate scraper skill. So, in this video, I will show you how you can use those two things to do some cool lead generation. Everybody loves lead generation and now with Claude code and Apify skills, it just became a lot easier to do. So, let's start. All right. So, the easiest way to start with Claude skills is actually to go to this website called skills.sh.
And here you will find thousands, maybe hundreds of thousands of skills. Actually, there is about 90,000 skills right now. The Apify skill is actually here. If you just click on official, you find all the official skills and right here under Entropic, you have all the Apify agent skills. And we have a lot of skills. So, in these two sources, we have 13 skills and agent skills and awesome skills, nine skills. You can see the number of installs.
So, the skill that we're looking for is actually going to be here. It's called the Apify ultimate scraper. So, it's the most popular skill and this is the skill that we're going to use. So, what I'm going to do is basically just take this URL of the skill and by the way, you can read about what actually the actors that it uses. So, here it uses for example, 12 Instagram actors, Facebook actors. It's all bundled together and it has exact instructions on how to use those actors.
So, in in many ways, you know, it gets you from using the actual actor without you having to figure it out or through a for example, API or other methods. So, this is obviously one of the key advantages of skills. It has all that context for you. It's bundled all the actors together. And of course, there is a more simplified way for the actual Claude code to use those different actors. So, an example for lead generation, right?
So, for lead generation, this is the use case that I want to show today. It's going to use the crawler Google places, the Google Maps extractor, the contact info scraper. All really, let's say the top tier enrichment and lead gen actors that we have. All right. So, take that URL and let's go to Claude desktop. And if you've used Claude desktop, you know, it started with chat. I had a video which I will also link below for co-work and now we're at Claude code.
So, this is really the place where a lot of the buzz online you hear about Claude is coming from Claude code. Now, when many people would use this in for example, VS code and obviously you can do that. But, for this video, I want to make it super easy for everyone to use so you can actually use it right here. The first thing that you want to do is actually choose the right folder. So, just choose the right folder that you want to work from.
So, for example, let's just create a new folder here. I'm going to call it let's say for today's lead gen, I want to find some sales and marketing people from you know, IT IT companies for example. Let's say in Berlin, okay? So, I'm going to do IT companies lead gen. All right. So, that allows us you know, whatever files that you do actually with Claude code. So, for example, if for this case, I'll probably end up creating a CSV.
It will be in this and of course, you can keep working on this. All right. So, first thing you want to do is actually install the skill, right? Um, so easiest way to do that, install this skill, right? Go ahead and trust this workspace. And that's the beauty here in Claude code. You're in the environment where you know, you have full control over the CLI. So, it will probably do everything for you here. So, let's go.
Um, so it's actually doing that bash command. Okay. I'm just going to go ahead and auto accept edits. Yeah, as I said, you can actually open this eventually in VS code or cursor if you prefer that, but I'm just going to make this for um, easy. All right. All right. There you go. So, this was already installed um, but you know, the concept is the same. You just give it the actual skill name from sh and it will be able to install it for you.
The one thing that you do need to do is actually create an env file with your Apify token. So, I will I will do that, but first let me invoke the skill that was installed. So, I'll Okay. So, I'm going to invoke it this way. Use this skill to find me the top 100, let's say. Maybe I want to sell to these agencies. So, let's say sales people in IT companies in Berlin. Come All right. I'm going to use Opus and off we goes.
All right. So, um, it gave me exactly what it what it's going to do and it ran a bash command. Now, it wants me to actually approve this. So, I'm going to go ahead and approve this. All right. So, this is the thing. It asks for the actually the Apify token. So, you can just go ahead and say yes, I have one. I'm going to actually use the Google Maps and contact enrichment. So, this is the beauty about skills too. It gives you more of structured way that you can use these tools.
Okay. And which output format do I want it? So, in this case, I think I will just use it for manual follow up. So, I will choose the CSV and off it goes. Okay. So, in this case, I will just take an Apify token. Obviously, you need this to run the skill. So, I'm just going to go here and find my token. All right. So, here we go. I have the tokens here. It's under your settings, right? So, if you go there, I'm just going to go ahead and copy that.
I'm just going to give it the token. My suggestion is that you rotate the token after you give it to it. Please use this token. All right. So, now it's running the Google Maps scraper for IT companies in Berlin and you can actually check the runs. If you go back to Apify, you can check exactly which runs are being triggered right now. So, there it is. The Google Maps scraper is there. And if you click on it, you can see it's already it's already populating some IT companies in Berlin.
You can always cross check with the input itself and here it is, Berlin, Germany. And it actually kind of you know, defined all the schema that I needed. So, I go back and it seems to be still waiting for the actual um, actor to to finish. So, right away when it completes, it checks by itself through that. So, now 99 companies were found. Um, so now it's going to extract these websites and enrich them with the contact info.
All right. This is going beautifully now. All right. You can see that this is much faster and actually doing it this way will also save you money. Um, then you know, going some other ways, right? Because when when the when the actual agent knows exactly how to use these specific actors, it becomes a lot more efficient. So, basically it's now running these URLs through the contact detail scraper and you can just cross check that.
So, if you go to runs again, you can see the contact detail scraper is now being um, triggered. Here we go. We're already finding some interesting emails. Um, let's see. Here we go. Interesting emails for for sales, right? >> This is also social profiles. All right, so let's go back. And let this cook for a while. All right, so I'm back. So now it's merging the Google Maps company data with the enriched contact data.
Uh and it will produce that final CSV for me. So now we're at uh step five and it's now at the final step where it's actually going to summarize all these results. And this is all done with like two or three uh prompts, basically. All right, so it's done. Um All right. Uh actually it as it's asking me for some follow-ups. Um Of course, you can do a deep enrichment, right? You can keep going. Uh let me just check here.
Uh so if you go back now to your finder to where the actual folder was, right? So here it is, ID companies. And here is where we have um the enrichment that was done. Let's open that. We got the companies and the category that's in, the address, the city, uh the website, and some emails uh for them, some contact phone numbers here, uh LinkedIn and etc. And then you can of course put this into your CRM um or into your marketing automation tool and just run campaigns on them.
So, it's as easy as that. With just a few clicks, you can use Cloud Code and Amplify skills like the ultimate scraper skills to create some really good and productive um workflows. And we're super excited to see what you can do with these skills. Thank you. So, thank you for watching. Check out our channel for more helpful tutorials, and make sure you like and subscribe. Until next time.
The words are the caption track's own and nothing is reworded or re-transcribed. Paragraph breaks are placed between sentences so the text reads as prose.
Free tools for your own script. No signup, no login.
Paste your draft and see where viewers are likely to drop off, with a rewrite for each weak line.
Paste the first 30 seconds of your own draft for a hook score and rewrites.
Check your draft against YouTube's advertiser-friendly guidelines before you record it.
Read this channel's public videos and transcripts, and download a writing brief for it.