Jon Syu
4.6K posts

Jon Syu
@jonsyu
Watch me make surprisingly bad takes on #bitcoin, behavioral psychology, startups, marketing, and sometimes criminal justice
Colorado เข้าร่วม Eylül 2013
466 กำลังติดตาม6.5K ผู้ติดตาม

I just gave Claude control of my cold email campaigns. Here's what happened:
Most cold email managers are stuck in the same loop:
☒ Log into Instantly manually every day
☒ Check metrics one sequence at a time
☒ Pause underperformers by hand
☒ Write new copy with no data to guide it
Until we built the opposite.
And I just recorded a full walkthrough breaking down the complete system:
→ How Claude logs into Instantly, reads your dashboard, and flags what's broken
→ How to set rules so Claude pauses sequences under 1% reply rate automatically
→ How Claude scales winning sequences by 20% volume without touching a thing
→ How Claude rewrites losing email steps using only your best-performing copy as reference
→ How Claude pulls weekly reports and saves them to a local folder - zero dashboard diving
This isn't theory or fluff.
I'm showing the exact prompts, the folder structure, the permission setup, and the confirmation flow Claude uses before making any changes.
The wildest part?
We do it all from one Mac with the Claude desktop app.
(No extra tools. No dev work. No agency.)
No bloated tech stack. No extra headcount. No manual ops work eating your week.
This system is built on Computer Use - Claude sees your screen, navigates your tools, and asks for confirmation before anything risky.
You stay in control. Claude does the work.
Want the full breakdown?
Follow me
Reply "COWORK"
I'll send it straight to your DMs.
English

A two-person GTM team at a Series B SaaS company closed $2.4M in pipeline in one quarter.
No SDRs. No demand gen agency. No paid ads.
Signal-based outreach. Intent scoring. AI-sequenced follow-up. Automated reporting.
Two GTM engineers running the whole motion - for one quarter.
I pulled it apart.
Compared it to every system we've built across the GTM teams we've worked with.
Then asked myself one question:
If I had to reverse engineer this from scratch - what would it actually look like?
Turns out the architecture isn't that complicated.
I mapped the whole thing into a step-by-step playbook you can upload directly to any LLM.
It walks you through building your own version from GTM strategy to fully AI-powered execution.
Comment "GTM" and I'll send it over.

English

I built 140 ad creatives in 11 minutes
Here's how, using Claude Code 👇
Normally I open Figma, write copy in a doc, resize 4 times, export, upload, repeat.
That's 2-3 hours for a single batch.
Now I describe the campaign once and Claude Code builds the rest.
Here's what the skills handle:
1/ Ad copy matrix
You give it one product brief.
It writes 50+ variations — short, medium, long-form — matched to each audience segment.
2/ Creative templates
React components that look like real ads.
Before/after, testimonial cards, stat callouts, UGC-style frames.
3/ Bulk image generation
Swaps headlines, CTAs, colors, and backgrounds automatically.
One template → 100 unique PNGs ready to upload.
4/ Hook optimizer
Rewrites your first 3 seconds of video scripts.
Tests curiosity gaps, pain points, bold claims — the stuff that stops the scroll.
5/ Platform formatter
Takes one concept and outputs it for Meta feed, Stories, Reels, Google Display, and LinkedIn — correct sizes, character limits, aspect ratios.
6/ Creative scoring
Grades every variation before you spend a dollar.
Flags weak hooks, unclear CTAs, and off-brand copy.
7/ Performance reporter
Pull your ad data, and it tells you which angles are winning,
which creatives are fatigued, and what to test next.
What used to take me a full afternoon now takes a coffee break.
140 creatives.
Every size.
Every platform.
On brand.
No Figma. No freelancer. No 47 browser tabs.
Just describe what you sell and who you sell it to.
The skills are free. Drop them into Claude Code and start.
Comment "Creatives" and I'll send you the full skill pack + setup guide.
(must be connected)

English

Claude Code + Nano Banana 2 is f*cking cracked 🤯
I built a skill inside Claude Code that writes JSON image prompts for Nano Banana 2, and the outputs look like they came from a professional photo shoot.
One plain-text prompt. Claude rewrites it as structured JSON with lighting, camera, composition, style, and negative prompts.
Then fires it off to Nano Banana 2.
All inside Claude Code.
Perfect for DTC brands and agencies who need high-volume ad creative without booking a shoot.
If you're using Nano Banana 2 for product shots and lifestyle images but every generation feels like pulling a slot machine lever — random lighting, inconsistent style, plastic skin, misspelled labels ...
This skill fixes the entire output:
→ You describe what you want in plain English
→ Claude rewrites it as a structured JSON prompt (lighting, camera angle, lens, depth of field, color grading — all of it)
→ Fires it to Nano Banana 2 via API
→ Saves the prompt + image in organized folders
→ You iterate on the style until it's dialed, then every output matches
No more slot machine prompting.
No more inconsistent brand imagery.
No more burning credits on unusable generations.
What you get:
- Photo-realistic product shots and lifestyle images on demand
- Full control over style, lighting, composition, and camera settings
- Saved JSON prompts you can reuse across every campaign
- A skill that gets smarter the more feedback you give it
Built 100% in Claude Code with a custom skill + Python scripts.
I put together a full playbook showing the exact skill, the JSON schema, and the workflow to set this up yourself.
Want the full playbook?
> Like this post
> Comment "BANANA"
And I'll send it over (must be following so I can DM)
English

Hooks are the 80/20 of ANY ad.
But a TON of brands get it completely wrong.
After generating $100M+ on Meta ads, I built a system for creating and testing hooks that actually stop the scroll.
And now, for the next 48 hours I’m giving it away:
✔ Our 25+ page guide I give away internally to my team
✔ 50+ stealth-style hook examples used in 7–8 fig ad accounts
✔ A swipe file of 500+ viral hooks & headlines that stop the scroll
Want it? Like + Comment: “HOOK” and I’ll sent it over.
(Must be following)

English

I run my google ads with @openclaw for $0/month 😱
here's the system that runs autonomously:
step 1: map what you're actually spending
→ agent pulls every keyword from your @GoogleAds account
→ classifies intent: buyers, researchers, comparison shoppers, freebie hunters
→ tells you if overspending on clicks or if you're buying the wrong ones
step 2: kill waste before it compounds
→ @OpenClaw flags keywords burning budget with NO buying intent
→ specific negatives that won't kill your good traffic by accident
→ one account: 23% of spend on research queries. zero conversions. gone.
step 3: separate winners from losers
→ buyers and researchers in the same ad group = bids optimizing against trash
→ agent shows you exactly which ad groups to break up
→ clean signal in, clean decisions out
step 4: write ads from real buyer language
→ agent reads what your converting searchers actually type
→ generates RSAs from their words,
→ not templates. not Google's auto-AI. patterns from YOUR winners
step 5: apply with instant undo
→ every change is a draft. dry run. confirm. done.
→ negatives, pauses, budget shifts w/ full audit trail
→ nothing hits your account without you saying yes
step 6: morning brief + memory that compounds
→ /google-ads daily = what matters today. 90 seconds. → bleeding campaigns, wasted spend, what's ready to scale
→ week 4 catches what week 1 missed. it doesn't forget
input: your google ads account + your target CPA
output: an AI that kills waste, writes ads, shifts budget, and learns what works
agencies charge $3-5K/month for this. this runs for $0.
I packaged the entire system as the google ads kit.
15 @OpenClaw skills:
- connect (setup + health check)
- daily (what matters today)
- audit (full strategic review)
- search-terms (waste + signal + routing)
- intent-map (compounds across sessions)
- negatives (scoped, with collateral warnings)
- structure (campaign architecture)
- rsas (copy from buyer language)
- budget (scaling grounded in signal)
- apply (controlled writes + instant undo)
giving it away free.
comment PAID + like + follow
(must follow so i can DM)
English

🚨BREAKING : Claude Cowork pour le SEO est maintenant disponible.
(je ne reviendrai jamais en arrière)
Avant, je passais des heures à essayer de deviner la bonne décision à prendre en SEO.
Trop de données, aucune idée de comment les exploiter.
Maintenant ? Cet outil me guide dans la bonne direction à chaque fois.
-> Fini les templates copiés-collés.
-> Fini les "hey ChatGPT trouve-moi des mots-clés"
-> Fini les "je fais quoi maintenant ?"
Voici un aperçu de ce que ça peut faire pour vous :
-> Analyser votre Google Search Console
-> Trouver ce qui plombe votre croissance
-> Les mots-clés que vous ne ciblez pas (et sur lesquels vous perdez de l'argent)
-> De vraies décisions intelligentes pour votre travail SEO
J'ai créé des dizaines d'articles, corrigé des dizaines de problèmes. Les résultats sont déjà là.
La différence ? J'économise plus de 15 heures par semaine.
J'ai compilé tout notre système dans un seul doc :
- Comment utiliser l'outil SEO Claude Code
- 50+ prompts que vous pouvez utiliser dès maintenant
- Quand intervenir pour le contrôle qualité
- Comment configurer le MCP avec Claude Code
Tu veux le système complet ?
1. Follow moi
2. Commente "Cowork SEO"
P.S. Reposte pour un accès prioritaire ♻️

Français

We spent hundreds of hours building Claude Code skills for our $7M ARR GTM agency (and we're giving them away for free)
- ICP research
- signal scoring
- cold email writing
- sales intelligence
- campaign intelligence.
These run inside every system we build for 70+ B2B clients.
Reply "Claude Code" and I'll send you the Github repo with everything.
GIF
English

NEVER use GPT for your ads again.
Gemini 3 replaced an entire performance team inside my workflow.
Founders don’t fail because their product is bad.
They fail because their ads never break into profit.
Wrong targeting.
Weak copy.
Broken bidding logic.
No diagnostic systems.
I built a Gemini 3 prompt pack using real data from 1.2B in ad spend.
Here’s what it produces:
• High converting copy in seconds
• Campaign diagnosis and repair
• Keyword and audience maps
• New angles, hooks, and creatives
• Bid and budget optimization
• Full account audits in under 30 seconds
This came from the exact frameworks I use across 300 brands.
The pack is free.
Inside the pack:
• Copy prompts
• Hook and angle generators
• Keyword discovery
• Persona builders
• Meta and Google optimization flows
• Campaign repair
• A/B test builders
• Creative scripts
• Scaling frameworks
• Bidding logic
• Motion analysis prompts
• Competitor breakdowns
Want it?
1. Connect with me.
2. Comment “GEM”
3. Repost this
I’ll send it to your DMs.

English

NanoBanana 2 just made your static ad agency obsolete.
And I just open sourced the entire tool.
Drop your product page URL.
It pulls your logos, product images, fonts, colors, and brand voice automatically.
Builds a full brand guide for you.
Then generates ad creatives at scale using nearly 4,000 high-performing ad templates across 8 niches.
It dynamically matches the best templates to your brand and brief.
Here's what makes it different:
→ Instant resizing
Get any ad in 1x1, 4x5, 9x16 with one click. No regeneration. No broken text.
→ Highlight-to-edit
See an issue? Highlight the area and tell it what to fix.
→ Multiple brand profiles
Run different brands or segments from one tool.
→ Auto persona building from real customer reviews
→ Multiple QC loops on briefs and final assets
Catches AI-isms before you do.
→ Upload your own templates or use ours
Runs locally.
Just needs your Claude and Google API keys.
This is the lite version of what we use internally.
You get the full finished tool AND the open source code to make it your own.
Creatives still design the system, this handles iteration and scale.
Want a copy to download?
1. Like this post
2. Comment "AI"
Will DM you the tool along with a tutorial shortly after.
English

Claude Cowork is f*cking ridiculous 🤯
One prompt → competitive research, creative briefs, 15 hook variations, and a full performance dashboard.
All saved as real files on your computer.
All inside Claude Desktop.
If you're spending hours every week copy-pasting between tools, pulling competitor ads manually, writing briefs from scratch, and building reports in spreadsheets ...
Claude Cowork eliminates the entire loop:
→ Point it at your project folder with brand voice + context files
→ It asks YOU clarifying questions instead of guessing
→ It builds a multi-step plan and executes while you step away
→ It creates real .docx, .xlsx, .pptx files — not chat responses
→ It connects to Slack, Google Drive, Airtable, and 50+ tools live
No copy-pasting between tools.
No babysitting the AI mid-task.
No downloading and re-uploading files.
What you get:
→ Competitive research synthesized into actionable creative angles
→ Ad briefs, hooks, and scripts generated in your brand voice
→ Interactive HTML dashboards built from your own customer data
→ Weekly performance reports created while you're getting coffee
Built 100% inside Claude Desktop with skills, plugins, and connectors.
I put together a full DTC playbook: 10 workflows with copy-paste prompts, the exact setup process, and the weekly operating rhythm I use.
Want it for free?
> Like this post
> Comment "COWORK"
And I'll send it over (must be following so I can DM)
English

Hey agency owners and GTM Engineers, let me save you 2 years.
After building and scaling 2 SaaS to $1M ARR in < 1 year with LinkedIn, I documented the exact systems we run into one practical SOP database.
It’s everything we still use internally every day to land hundreds of leads/ day.
What’s inside:
- DM setting SOPs
- 300k weekly impressions commenting SOP
- lead magnet distribution SOP
- lead tracking & CRM system
- setter scaling system (for agencies)
If you want free access, comment “SOP” and I’ll send it over.
English

@hecubian_devil I'm pretty sure the future is us just having thin clients that are loss leaders, and everything else is just a subscription.
English

We cracked the code with signal-led GTM list building
11 workflows replacing static lists used daily in outbound.
Every list follows the same system: signal → timing → conversation.
We follow the exact same workflow every time.
I documented the full playbook. Follow, RT &
comment “GTM” and I’ll send it free.

English

@KevinEspiritu I don’t know what happened to this platform but I have enjoyed not being on it nearly as much anymore
English

@KevinEspiritu @Grimezsz You’re gonna have to figure out how to vinyl wrap those Birdies with some wild designs.
English

@Grimezsz if you wanna collab on a garden build I'm down Grimes, I have literally done exactly what you are trying to do many times over
English

Starting a garden to ideally fulfill all veggie / fruit / green requirements? (How hard is this?)
Any suggestions? Feeling like indoor in some capacity makes most sense for potentially growing what we need year round?
Asking ai for help but I have zero history w this and human input from farmers rly helped w chicken farming lol
if u were doing farm in the yard in the city what wud u prioritize? Any soil testing easy and good to do?
English

GTM Engineers & Agency Owners:
I’ve recently started a private Slack community specifically for GTM engineers, agency owners, and operators.
A space designed to:
1. Share proven GTM, acquisition, and scaling strategies
2. Connect with other operators & agency owners for collaborations
3. Broaden your operator network 👊
4. Access the latest AI, automation, and growth tools with exclusive community early access and free trials
Whether you’re just starting your SaaS/agency or already scaling fast, you’re welcome to join.
It’s free and focused on real value.
Comment “JOIN” and I’ll send you the invite.
English

Fuck it.
I’m dropping my full Deep Researcher Mega Prompt for free.
It turns ChatGPT, Claude, and Perplexity into a real research analyst:
→ Structured insights
→ Market breakdowns
→ Competitor analysis
→ Multi-layer reasoning
Comment “Research” and I’ll DM you the file.
(Must be following me to receive it)

English


