Frontal AI

We built 52 Claude Code skills that run a full sales and marketing team. They've produced $7.83M in qualified pipeline for one client, with zero new SDR hires. It runs as six specialists, the same roles you'd staff a revenue team with: 1. Strategy: reads your site, works out who you can sell to, scores every account out of 100 2. Signals: tracks the right accounts and waits for the trigger. a raise, an SDR hire, a new CRO, a competitor swap 3. Data: pulls real phone numbers and emails for the accounts worth chasing 4. Copy: writes each message off the specific signal it caught, never a template 5. Execution: ships the emails, the LinkedIn touches, and the follow-ups 6. System: wires the other five together so one prompt runs the whole thing Each skill is a plain text file. Anyone on your team can open it and change how it works, no code. This is the exact system we run at @Frontal_AI right now. The full build and a live run are in the video. Comment SKILLS and we'll DM you the repo. Must be following.

The fastest way to make outbound look like it is working is to measure meetings booked. An AI-booked calendar fills up easily. The more transparent number to track is whether a booked meeting turned into a real opportunity within 45 days. That is one CRM stage. Add it and the rest of the system corrects itself, because targeting, messaging and routing all start getting judged on revenue instead of volume. Most teams never add the stage. So they spend a quarter scaling whichever part was already broken.

@JoshEdmondson_ @itsalexvacca @Kenny_GTM 🤣🤣

@itsalexvacca @Kenny_GTM Kenny just found out he was the lead magnet

pov: @Kenny_GTM finding out i just gave away 600 hours of his work for free

@GeniusPothead @itsalexvacca @Kenny_GTM 💯

@itsalexvacca @Kenny_GTM Massive respect for people pushing knowledge instead of keeping everything locked away

@itsalexvacca you and Claude after you read this:

you are paying thousands for data someone scraped off linkedin and sold back to you. plug apify into claude code and scrape it yourself: 1/ create an apify account. free tier comes with $5 in credits 2/ connect the apify mcp to claude code. one-time setup 3/ paste your website url into claude 4/ claude reads your offer and works out the icp on its own 5/ ask for the list. claude picks the scraper, runs it, hands back the rows 6/ swap the personal emails for work emails with an email api (we use leadmagic) 7/ qualify in clay, send our run: 100 leads, 70 on company domains, 10 cents of compute. same play works on your post engagers too. one of my posts had 479 last week, claude pulled every one of them and ranked them against the icp. full walkthrough in the video below (bookmark for later):

STOP BUYING LEAD LISTS plug apify into claude code and scrape unlimited leads for literally cents

founders paying hundreds of dollars for lead lists watching this

cool so we're just handing out the whole system now..

@potrichh sent!

@Frontal_AI SKILLS

We built 52 Claude Code skills that run a full sales and marketing team. They've produced $7.83M in qualified pipeline for one client, with zero new SDR hires. It runs as six specialists, the same roles you'd staff a revenue team with: 1. Strategy: reads your site, works out who you can sell to, scores every account out of 100 2. Signals: tracks the right accounts and waits for the trigger. a raise, an SDR hire, a new CRO, a competitor swap 3. Data: pulls real phone numbers and emails for the accounts worth chasing 4. Copy: writes each message off the specific signal it caught, never a template 5. Execution: ships the emails, the LinkedIn touches, and the follow-ups 6. System: wires the other five together so one prompt runs the whole thing Each skill is a plain text file. Anyone on your team can open it and change how it works, no code. This is the exact system we run at @Frontal_AI right now. The full build and a live run are in the video. Comment SKILLS and we'll DM you the repo. Must be following.

@renanumpierre Sent!

@Frontal_AI SKILLS

@joeysterlingg sent

@Frontal_AI SKILLS

Publish a LinkedIn post, glance at it once, close the app, and you just threw away 70% of its reach. Almost everyone does exactly that. LinkedIn tries every post out on a small crowd first. Get some traction in the opening 60 to 90 minutes and it opens the doors wider, get nothing and it lets the post slip away. That single window decides about 70% of the reach a post will ever see. The actions inside it carry different weight, too. A comment is worth 15x a like, a share 5x, a save 3x. Which means the moment you publish, the work has barely started. Reply to every comment in that first hour and you earn 50% more engagement across the whole life of the post.

@itsalexvacca you and Claude Code after you read this.

I've seen a lot of worse products beat better ones, and the reason is almost always the same. We've run outbound for 275+ B2B companies so far, across just about every kind of product you can think of, the polished ones and the ones barely holding together. Across all of them, it comes down to the same thing: distribution. Distribution is getting the right offer in front of the right people, with a message relevant enough that replying is the obvious move. It takes patience, and there's no clever way around it. None of that is new, but AI has pushed it to an extreme. Now that anyone can rebuild your product over a weekend, how hard it was to build stopped counting for much, and what you're left competing on is distribution. That happens to be the part most people are worst at. It also adds up over time. Someone can clone your software and still be starting from nothing, because they don't have the list you spent months cleaning up, the offers you already tested, the reply data, or the pipeline that's warm to you and nobody else. That takes a long time to build, and none of it comes across when they copy you. That's what we build and run for you at @Frontal_AI. You start with it already booking meetings, instead of spending your first year building it.

Cold outreach works. It just works harder than it has to. The buyer decides in about a second whether you're worth reading, and a name they've already seen clears that bar faster than the sharpest opener you can write. So we run a thin layer of ads at the exact accounts we're about to contact, timed to land first. By the time the email or DM arrives, the name already looks familiar, and the second touch feels like a second meeting instead of a first introduction. Here's the whole system, start to finish: → Same list you already sequence. Target accounts ranked hot / warm / cool. No new data needed. → Upload it as a LinkedIn Matched Audience + Google Customer Match. Ads run against those companies only, never the open market. → Ads lead by 2 weeks. Outreach starts in week 3, on a name that already looks familiar. Both overlap through week 5, then the budget rolls to the next batch. → Keep the audience narrow and the spend small. You're reaching a handful of companies, not the whole internet, so a tiny daily budget stretches a long way when you cap it weekly. → Hold a slice of your accounts out of the ads, give them identical outreach, and compare the two groups. That gap is the whole argument. → Anyone who clicks or visits gets bumped up the list. Every cycle hands you a sharper list than the one before. Most teams run ads and outbound as two separate machines that never look at each other. Point them at the same accounts, in the right order, and the whole thing compounds. It's all yours to copy with whatever tools you already run.

@itsalexvacca Pure sauce 🔥

We spend $100k+/month running LinkedIn Ads for clients. I'm giving away the 12 Claude Code skills that run it all. Free. LinkedIn Ads is one of the most tedious platforms out there. Bid adjustments, audience changes, campaign analysis, catching creative fatigue, all of it across dozens of campaigns and ad sets. That work used to fill entire days. So Ivan Falco from our team, who leads ABM at @Frontal_AI, built the fix. He turned everything he knows about LinkedIn Ads into skills inside Claude Code. His own AI media buyer, essentially. It runs as 3 agents: 1. Reporting: performance analysis, account audits, creative fatigue 2. Campaign management: campaign builds, audience targeting, bids and budgets, optimization 3. Creative: audience research, concept ideation, ad copy, designs You write one prompt. It builds the campaign, uploads the creatives, and reports back. You still make the calls. Same move we made on outbound: hand the AI your playbook, let it run the repetitive work. It's probably the only skills database in the space that runs LinkedIn Ads from Claude Code at a real professional level. Years of scaling B2B SaaS and agency accounts, plus the onboarding to set it all up. 12 skills, 3 agents, the full setup. 300+ hours of what we use inside our $7M ARR GTM agency, yours free. Comment "ADS" and I'll send the whole thing over.

Our head of ABM, Ivan, runs client LinkedIn Ads from the terminal on live buying signals, over $2M managed through Claude Code. We're giving away the exact 12 Claude Code skills he uses for free 👇