Cris retweeted
$11.90 CPA from a weird animated cartoon ad most brands would never approve
a toxic green villain
lab background
fully animated character
no UGC
no actors
no filming
yet this creative quietly pulled:
4.92 ROAS
3.76% CTR
~47% video play rate
same campaign
five different cartoon hooks
some lost money
one carried the entire ad set
that’s the advantage of animated AI creatives
you can test ridiculous ideas fast
new characters
new stories
new villains
the weird ones often win
rt + comment “cartoon” and i’ll send the breakdown
(follow for dm)
Clawdbot + Kling = an AI “doctor page” content machine
no real doctors
no clinics
no filming days
no creators to manage
just viral health videos running nonstop
look at this page
one AI doctor character
same scrubs
same style of explanation
but every video tests a different hook
4.3M views
1.3M views
958k views
700k+ views
all from the same character
here’s how the system works:
→ clawdbot generates the doctor persona and script
→ kling produces the video scenes and health visuals
→ capcut auto-edits captions, hooks, and pacing
→ dozens of variations are posted across the page
each video tests a new idea
gut health
“don’t eat this” hooks
home remedies
visual body explanations
most brands film one expert video
wait two weeks
spend $1k+
this system tests 50+ ideas in the same time
the ones that hit get scaled
AI isn’t just making content cheaper
it’s making testing infinite
rt + comment “system” and i’ll send the full workflow
(follow for dm)
Cris retweeted
$88k+/month ad accounts are quietly moving into animated metaphor formats
not mascots
not goofy cartoons
but health problems and products turned into characters
a stiff spine with a frustrated face
an angry onion sitting on irritated skin
a supplement bottle flexing as it “clears” the system
you understand the benefit without reading a single claim
it feels like content
not a hard sell
that’s why it works
people ignore polished influencer pitches
they don’t ignore a visual problem being solved in real time
ai builds the characters
ai stages the internal scenes
ai generates dozens of variations from one concept
one core metaphor
multiple pain points
endless executions
no shoots
no creators
no delays
when one visual hits, you replicate the structure across other offers
simple
slightly strange
highly scalable
rt + comment “metaphor” and i’ll dm the setup
(follow for dm)
Cris retweeted
I run my meta ads with @openclaw for $0/month 😱
here's the system that runs autonomously:
step 1: daily health check
→ social-cli (major shoutout to @vishalojha_me) wraps @Meta's marketing API (token refresh, pagination, rate limits all handled)
→ am I on track? what's running? who's winning? who's bleeding? any fatigue?
→ the same 5 questions I asked Ads Manager every morning for 20 years
step 2: catch dying ads before CPA spikes
→ @OpenClaw pulls daily frequency by ad
→ frequency > 3.5 = audience is cooked, CTR is about to drop
→ this one signal saves more money than any dashboard
step 3: auto-pause bleeders + shift budget to winners
→ CPA > 2.5x target for 48hrs? auto-pause. no hesitation.
→ ranks every campaign by efficiency. recommends shifting spend.
→ last fri it paused an $87 CPA campaign at 3am and scaled my best performer 30%
step 4: write new ad copy from your winners
→ agent analyzes what's working (hooks, angles, CTAs)
→ generates variations based on the patterns in YOUR top performers
→ copy modeled on what already converts in your account.
step 5: upload ads directly to your account
→ new creative + copy
→ live in @Meta Ads Manager
→ no more downloading, formatting, clicking through the upload flow
→ agent handles the entire publish cycle
step 6: content concepts + morning brief
→ spots patterns across winners and suggests what to test next
→ delivers everything to Telegram, Slack, wherever you want it
→ 90 seconds to read. reply "approved." done.
input: your ad account + your target CPA
output: an AI that monitors, kills, scales, writes, AND uploads your ads
dozens of hours in ad manager → 1 text message
I packaged the entire system as the Meta Ads Kit.
5 @OpenClaw skills:
- meta-ads (daily checks + auto-pause)
- ad-creative-monitor (fatigue detection)
- budget-optimizer (efficiency scoring + shift recs)
- ad-copy-generator (writes variations from your winners)
- ad-upload (publishes creative directly to your account)
giving it away free.
comment ADS + like + follow
(must follow so i can DM)
HOLY SH*T… This AI Agent does everything 🤯
Built in n8n :
🔁 Clones viral TikToks
✍️ Rewrites w/ GPT-4o
🎥 Auto creates avatar videos
🎬 Adds captions & edits
📤 Posts to 9 platforms (TikTok, IG, YT, X…)
🔁 Like+RT
✅ Reply “Steal”
🤝 Follow me & I’ll DM you workflow FREE.
Cris retweeted
R.I.P Executive Assistants.
We replaced a $85K/year EA with one AI agent that never clocks out.
(this agent lives inside your texts, email, and calendar 24/7)
→ No more forgotten follow-ups killing deals after calls
→ No more 3 hours daily burned on scheduling and admin
→ No more opening 6 apps just to stay organized
→ No more dropped promises that make you look unreliable
Just one AI agent → autonomous executive infrastructure that never clocks out.
Here's how it works:
→ Pre-Meeting Briefs (texts you context on who they are + what you promised)
→ Action Item Extraction (pulls every commitment from calls automatically)
→ Ghost-Written Follow-Ups (drafts in your voice — without being asked)
→ Schedule Management (handles conflicts, reminders, rescheduling on autopilot)
→ Learning Loop (gets sharper every week based on how you operate)
Built with enterprise-grade context engineering.
Runs 24/7 without supervision.
$0 payroll. Zero dropped balls.
Results after 6 weeks:
• 0% missed follow-ups (down from 40% dropped)
• 3 hours/day reclaimed from admin
• Every promise tracked, drafted, and sent
Want the complete system?
Like + comment "AGENT" + repost, and I'll DM it to you.
(must be following)
Cris retweeted
I buy debt for 2 cents on the dollar and forgive it for $500
Not charity.
Not kindness.
Pure profit.
Buy $10K debt for $200.
Charge debtor $500 to forgive it.
They save $9,500.
I make $300 profit.
Here's the $40K/month empathy arbitrage:
The Debt Market Reality:
Old debt sells in bulk portfolios.
$1M in face value = $20K purchase price.
Collectors harass people for years.
Maybe collect 5%.
I collect 50%.
By being the good guy.
The Purchase Process:
Find debt portfolios on DebtBuyers.com
Medical debt is cheapest (1-2 cents per dollar)
Credit cards (3-5 cents)
Personal loans (5-8 cents)
Buy $500K portfolio for $10K.
1,000 people each owing ~$500.
The Forgiveness Offer:
Email/text each debtor:
"I bought your $500 debt.
Pay $50 and it's gone forever.
Or pay nothing and I'll keep calling."
90% pay the $50.
They're saving $450.
Think I'm a hero.
The Math:
$500K debt portfolio
Cost: $10K
Collect: $50 x 900 people = $45K
Profit: $35K
Time invested: 20 hours
Better ROI than anything legal.
The Psychological Genius:
Debt collectors threaten and scream.
Get paid nothing.
I offer salvation.
Get paid immediately.
Same debt.
Different approach.
Different outcome.
Recent portfolio:
Bought $2M in medical debt.
Cost: $40K
Offered everyone 90% forgiveness.
Collected: $180K
Profit: $140K
Took 6 weeks.
The Reputation Management:
People post about me online:
"This company saved my life!"
"Only had to pay $100 on $3K debt!"
"They're angels!"
Five-star reviews everywhere.
While making 300% returns.
The Subscription Model:
Monthly forgiveness plan: $50/month
Forgives $500 in debt monthly.
People pay forever.
Thinking they're winning.
2,000 subscribers.
$100K/month recurring.
The Exit Strategy:
Building reputation as "ethical debt buyer"
Will sell company for 10x revenue.
Current run rate: $500K/year.
Exit value: $5M.
For buying garbage debt.
And being slightly less evil.
The Market Size:
$140 billion in unpaid debt.
Selling for $2.8 billion.
Even taking 10% is $280M opportunity.
Competition is zero.
Nobody else thought of being nice.
While still profiting.
This is capitalism perfected:
Everyone wins.
Everyone pays.
I get rich.
The system created desperate people.
I created hope.
For a price.
That's just good business
Cris retweeted
El tema de los proveedores Chinos y las marcas de lujo no es tan sencillo como se ven en lo tiktok. Si bien el costo producción a venta final es súper diferente no es nuevo y existe en todos los productos. “A los ricos le están viendo la cara”.
Solo a los ricos?
👓
Cris retweeted
Replying to @arvidkahl
Ehhhh not really? I have a Laravel package that can help you deploy Lambda functions and then call them from Laravel, if that helps? But you'll still have to figure out the streaming + concatting stuff on your own github.com/aarondfrancis/sid…
Cris retweeted
new computer:
bash is for installing zsh
npm is for installing pnpm
safari is for installing chrome
xcode cli tools is for installing brew
terminal.app is for installing ghostty
Cris retweeted
omg… the first text-to-film AI agent is here
this new SkyReels AI now can generate film script, storyboard, consistent character, video, voice, lip sync, and music automatically and..
it's new AI video editor can edit the film on its own
step by step tutorial:
Cris retweeted
Open Manus AI: EASY Install Guide and Is it REALLY Good?
Subscribe on YouTube for more: youtube.com/watch?v=FGfIoyO7…
github.com/mannaandpoem/Open…
Cris retweeted
`npm install -g @anthropic-ai/claude-code`
there's no more waitlist. have fun!
Cris retweeted
Here is a powerful Claude 3 prompt for engineers.
Use it to automatically refactor, comment, and improve your code:
---
<prompt_explanation>
You are a skilled software engineer with deep expertise in code refactoring and optimization across multiple programming languages. Your task is to analyze a given piece of code and provide suggestions to improve its readability, efficiency, modularity, and adherence to best practices and design patterns.
First, carefully review the code and identify areas that could be improved. Consider factors such as:
Readability: Is the code easy to understand? Are variables and functions named descriptively? Is the formatting consistent?
Efficiency: Can the code be optimized for better performance? Are there any redundant or unnecessary operations?
Modularity: Is the code properly organized into functions or classes? Is there good separation of concerns?
Extensibility: Is the code designed in a way that makes it easy to add new features or modify existing ones?
Best practices: Does the code follow established best practices and design patterns for the given language?
Next, provide an overview of your analysis, highlighting the main areas you believe need refactoring.
Then, go through the code, providing specific refactoring suggestions. Use the following format for each suggestion:
<suggestion>
<original_code>The original code snippet</original_code>
<refactored_code>Your refactored version of the code</refactored_code>
<explanation>An explanation of the changes you made, why you made them, and how they improve the code</explanation>
</suggestion>
After providing individual refactoring suggestions, give an overall summary of the changes you recommend and how they enhance the readability, efficiency, modularity, and adherence to best practices of the codebase.
Finally, present the fully refactored version of the code, incorporating all your suggested improvements.
</prompt_explanation>
<response_format>
<code_overview_section>
<header>Code Overview:</header>
<overview>$code_overview</overview>
</code_overview_section>
<refactoring_suggestions_section>
<header>Refactoring Suggestions:</header>
$refactoring_suggestions
</refactoring_suggestions_section>
<refactoring_summary_section>
<header>Summary of Refactoring:</header>
<summary>$refactoring_summary</summary>
</refactoring_summary_section>
<refactored_code_section>
<header>Refactored Code:</header>
<refactored_code>
$refactored_code
</refactored_code>
</refactored_code_section>
</response_format>
<code_block>
<language></language>
Paste the code you want refactored here.
</code_block>
---
Cris retweeted
How to Convert Figma to Code Using Cursor + MCP
Manually converting Figma designs into code is slow and painful.
Here’s how to automate the entire process:
Cris retweeted
Replying to @cursor_ai
@cursor_ai employees came to share their Cursor workflow while building Cursor. When builders == users, product UX is elite.
I love @shaoruu's config. Super silly to see on the big auditorium screen 💀 trust it works
Paste in Settings > Rules for AI👇
`DO NOT GIVE ME HIGH LEVEL SHIT, IF I ASK FOR FIX OR EXPLANATION, I WANT ACTUAL CODE OR EXPLANATION!!! I DON'T WANT "Here's how you can blablabla"
- Be casual unless otherwise specified
- Be terse
- Suggest solutions that I didn't think about—anticipate my needs
- Treat me as an expert
- Be accurate and thorough
- Give the answer immediately. Provide detailed explanations and restate my query in your own words if necessary after giving the answer
- Value good arguments over authorities, the source is irrelevant
- Consider new technologies and contrarian ideas, not just the conventional wisdom
- You may use high levels of speculation or prediction, just flag it for me
- No moral lectures
- Discuss safety only when it's crucial and non-obvious
- If your content policy is an issue, provide the closest acceptable response and explain the content policy issue afterward
- Cite sources whenever possible at the end, not inline
- No need to mention your knowledge cutoff
- No need to disclose you're an AI
- Please respect my prettier preferences when you provide code.
- Split into multiple responses if one response isn't enough to answer the question.
If I ask for adjustments to code I have provided you, do not repeat all of my code unnecessarily. Instead try to keep the answer brief by giving just a couple lines before/after any changes you make. Multiple code blocks are ok.`
Cris retweeted
Replying to @PrajwalTomar_
Great share! Something I’ve found incredible powerful is to mantain a cursor-log.md
Essentially after all changes i have it grab the date and time and log changes it made.
Cris retweeted
4/ Setting Up the Context Wall
I placed the Implementation Plan inside an /instructions folder and updated Cursor’s context.
Prompted Cursor with:
"Before you code anything, go through all files in @instructions and summarize your understanding of my project from a developer's perspective."
Cursor picked up the context perfectly. No hallucinations. No random code.
























