kedric
894 posts

kedric
@kedric
Founder: Boss Financial / Cofounder: DeFi MasterClass / Partner: Fewshot (formerly Sekoia) Worried AI will take your job? I have a plan...Click link below:
Here's my token portfolio → Katılım Mayıs 2008
4.9K Takip Edilen1.3K Takipçiler

Self-improving Claude Code skills are f*cking ridiculous 🤯
One loop → 10 test runs, scored against an eval, prompt rewritten, retested, winner kept.
A hook writer skill went from 32/50 to 47/50 overnight.
All inside Claude Code.
Perfect for DTC brands and agencies who have a Claude skill that's *almost* there — but the outputs still need a human pass before they're usable.
Here's the problem:
You build a skill that writes hooks. Or briefs. Or product descriptions.
The first version is decent. Maybe 70% there.
You spend the next two weeks tweaking the prompt by hand. Add a rule. Test it. Add another rule. Test it. The skill gets slightly better and you have no idea if you actually improved it or just got a lucky run.
This loop solves it:
→ Define what "good" looks like — a 10-point eval rubric the skill is graded against
→ The skill runs 10 times against real inputs
→ Claude scores every output against the rubric
→ Claude rewrites the skill's prompt based on where it lost points
→ Repeats until the score plateaus
→ Saves the winning version
No more guessing if your tweaks helped.
No more two-week tuning marathons.
No more skills that work 60% of the time.
What you get:
- A repeatable optimization loop you can run on any skill in your library
- Clear before/after scores so you know exactly what improved
- Skills that get sharper every time you run the loop
- The exact eval rubrics for hook writing, brief generation, and ad copy
Built 100% in Claude Code.
Want the full setup?
> Like this post
> Comment "EVAL"
And I'll send it over (must be following so I can DM)
English

I'm going to delete this post in 48 hrs...
Because I just dropped the complete system to scale from ZERO to $1,000,000 with Facebook ads.
This is the exact 3-pillar framework we use to take ecom brands from broke to million-dollar months - the same system that helped my Inner Circle student Luca hit $1.1M in 6 months.
We charge $10,000/mo to do this for clients…
But today, I'm giving it away 100% FREE.
Like + Comment "MILLION" and I'll send it to you.
English

how to build banger funnels on Google
1. Claude generates 5 headlines
2. you pick the best one
3. Claude design creates the full advertorial
4. send design to Manus
5. Manus builds it into your Shopify theme
I'm using this to speed up testing & build funnels for Google clients in hours
game changer
comment 'DESIGN' if you want the full Loom
English

I’m sure you’ve all heard of MEDVi by now
They grew from 0 to $1.8B in 2 years with 2 employees
Me and my team did a write up on them including:
- Their business model
- Their affiliate funnel
- Their numbers
So you can learn from them
Comment ‘send’ and I’ll DM it to you for FREE
(must be following)

English

🚨EXPOSED: 109s of Premium AI Agents.
If you missed it before, I'll give it again.
Worth $3K+ per build — now FREE for the first 3500.
Inside the file: 👇
→ Booking & outreach automations
→ Scrapers, support agents & more
→ Cold email engines
→ Social listening dashboards
→ Lead gen bots
→ Content pipelines
→ Auto-scheduling assistants
→ AI copywriters
→ Form-to-CRM connectors
→ Data enrichment bots
→ Chatbot funnels
→ Review aggregators
→ Auto-reporting scripts
→ AI-powered survey analysers
$14K+ Agency Clients, closed faster than ever.
Fill it up & GET:
- Comment "File"
- Like & Retweet
- Follow me
@ZayvenKnox
to get DM Fast.
- BOOKMARK [Must]
English

Gemini 3 is actually wild.
I turned it into a full UGC production studio.
I fed it one product link...
and it generated high-performing UGC ads in minutes.
No creators.
No editing.
No $300–$800 per video.
Then I paired it with my AI Ad Agent workflow —
and suddenly our UGC looked like top 1% DTC brands on autopilot.
Honestly, it feels like something that
shouldn’t be public yet.
Thinking about dropping the exact workflow + prompts.
Comment “3” and I’ll send everything over.
(must be following)
English

Anthropic ran their entire marketing operation with one person.
$380 billion company.
Paid search. Paid social. SEO. Email. App stores.
One non-technical hire doing all of it — for 10 months.
I pulled it apart.
Compared it to every system we've built across the clients 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 47-page PDF you can upload directly to any LLM.
It coaches you through building your own version step by step.
Comment "marketing" and I'll send it over.

English

RIP landing page designers 🤯
I just built a system in Claude Code that clones high-converting advertorial pages & rebuilds it for your brand in minutes.
Find a presell page that's been running on Meta for months →
Feed it to Claude Code →
Get back a production-ready page with your product, your copy, your angles.
Built 100% in Claude Code.
Perfect for DTC brands and agencies testing multiple advertorial angles on Meta.
The best brands on Meta are running 5-10 different advertorial pages at any given time.
Each one targets a different audience, a different pain point, a different hook.
Building those pages manually means freelancers, back-and-forth, and weeks of waiting.
This system solves it:
→ Find an advertorial that's scaling on Meta
→ Feed the page to Claude Code
→ Claude extracts the exact DR framework
→ Swap in your brand details, product, audience, and mechanism
→ Claude one-shots a complete HTML page following the same proven structure
→ Paste into Shopify. Done.
No designer.
No copywriter turnaround.
No starting from scratch.
What you get:
→ The exact advertorial structure that's already converting on Meta, rebuilt for your brand
→ Full HTML page ready to import into Shopify in 60 seconds
→ Copy that follows every DR beat — authority, pain escalation, root cause reframe, social proof, offer
→ A repeatable system you can use to spin out new angles whenever you need them
The pages that are scaling hardest on Meta all follow the same formula. This just lets you use it.
I put together a full guide showing the exact process — how to find winning pages, extract the structure, and build your own in Claude Code.
Want the full guide for free?
> Like this post
> Comment "CLONE"
And I'll send it over (must be following so I can DM)
English

With Quiz Funnels getting more popular...
It is my duty to make sure we revisit the best quiz funnel of 2025
Mad Muscles Tai Chi Quiz
Recently I listened to an iced coffee hour pod where the guest said, "I just do Tai Chi...you've never seen those ads"
Like, RT & Comment "TAICHI" will dm you the figma
Let's break it down👇

English

Claude Cowork Sub-Agents are f*cking cracked 🤯
One prompt → 50 competitor ads analyzed, hooks extracted, and a full creative brief generated.
10 AI agents running in parallel, under 5 minutes.
All inside Claude Cowork.
Perfect for DTC brands and agencies who are still doing creative research and ad production one task at a time inside Claude.
If you're analyzing competitor ads one by one, copying hooks into a spreadsheet manually, writing brief after brief from scratch, and watching Claude's output quality fall off a cliff after the 15th variation because the context window is completely bloated...
Sub-agents eliminate the entire bottleneck:
→ Drop in a spreadsheet of 50 competitor ads and spin up 10 parallel sub-agents
→ Each sub-agent analyzes 5 ads simultaneously — hooks, angles, CTAs, emotional tone, creative format
→ They report structured summaries back to the main agent without bloating the context
→ The main agent synthesizes patterns across all 50 ads into a competitive intel brief
→ Then spin up another round of sub-agents to generate 30 ad copy variations across 10 personas
→ Each sub-agent writes for 1-2 personas in a fresh context — so variation 30 is as sharp as variation 1
No analyzing ads one at a time.
No context window blowing up halfway through.
No copy quality degrading after the first dozen variations.
What this gives you:
→ 50 competitor ads broken down in minutes — hooks, angles, CTAs, formats, all structured
→ Pattern analysis across the full dataset that you'd miss reviewing ads individually
→ 30+ ad copy variations with persona-specific messaging that actually stays sharp
→ A workflow you can save as reusable skills and trigger with one command next time
→ The same output quality on the last task as the first
Built 100% inside Claude Cowork with sub-agents.
I put together a full DTC playbook:
5 bulk workflows with copy-paste prompts, the exact sub-agent prompting pattern, batching guidelines, and an honest breakdown of when this setup is worth it vs. when a simpler approach is the better move.
Want it for free?
> Like this post
> Comment "AGENTS"
And I'll send it over (must be following so I can DM)
English

RIP landing page designers 🤯
I just built a system in Claude Code that clones high-converting advertorial pages & rebuilds it for your brand in minutes.
Find a presell page that's been running on Meta for months →
Feed it to Claude Code →
Get back a production-ready page with your product, your copy, your angles.
Built 100% in Claude Code.
Perfect for DTC brands and agencies testing multiple advertorial angles on Meta.
The best brands on Meta are running 5-10 different advertorial pages at any given time.
Each one targets a different audience, a different pain point, a different hook.
Building those pages manually means freelancers, back-and-forth, and weeks of waiting.
This system solves it:
→ Find an advertorial that's scaling on Meta
→ Feed the page to Claude Code
→ Claude extracts the exact DR framework
→ Swap in your brand details, product, audience, and mechanism
→ Claude one-shots a complete HTML page following the same proven structure
→ Paste into Shopify. Done.
No designer.
No copywriter turnaround.
No starting from scratch.
What you get:
→ The exact advertorial structure that's already converting on Meta, rebuilt for your brand
→ Full HTML page ready to import into Shopify in 60 seconds
→ Copy that follows every DR beat — authority, pain escalation, root cause reframe, social proof, offer
→ A repeatable system you can use to spin out new angles whenever you need them
The pages that are scaling hardest on Meta all follow the same formula. This just lets you use it.
I put together a full guide showing the exact process — how to find winning pages, extract the structure, and build your own in Claude Code.
Want the full guide for free?
> Like this post
> Comment "CLONE"
And I'll send it over (must be following so I can DM)
English

Which blockchain handle this??
Nic@nicrypto
Stripe CEO says AI agents will we need a blockchain with 1 Billion TPS?! I beg your pardon.
English

I analyzed 847 paid ads last month to find what was actually working.
One format kept winning. Over and over.
I call it the 3-second reaction clip.
73% completion rate vs 21% industry average. Cost per view dropped from $0.89 to $0.14.
Here's how the system works:
→ Generate dozens of AI reaction clips with Calico AI + VEO 3.1 or Kling Motion Control
→ Each one costs a few bucks — I made a full batch for $30
→ Cut from the reaction to your actual product
→ Test all variations in Meta and scale the winners
The psychology is dead simple — people don't trust ads, but they trust reactions. When someone's eyes go wide, your brain mirrors it and curiosity takes over before you can skip.
One $47 ad outperformed $8K/month agency creatives by 340%.
Comment "REACTION" and I'll send you all the prompts + full system (must be following so I can dm you).
English








