Gringo

[Roque Castro @_RoqueCastro]

Una verdad dura... pero verdad al fin.

[Dudu Barbalho @edujbarbalho]

Sites para aprender fundamentos de design de forma mais descontraída.

[ElBuni @therealbuni]

Hoy el equipo económico de la liberad avanza tenia que bajar la inflacion y subir la calificación crediticia del pais de SD- (default selectivo) a B

Mientras que el equipo politico tenia que evitar putear a sus propios militantes y denunciarlos por Twitter

[sam @samgrows]

BREAKING: Claude can now watch videos for you!

You can plug in a YouTube, Tiktok or Instagram URL and let Claude break it down for you

Live now inside of Algrow

[Marco @maarcoofdezz]

CURSO COMPLETO DE CLAUDE DE 4 HORAS

Esta es la guía más detallada de Claude que he visto en línea.

Guarda esta página antes de que se te olvide.

Construye herramientas.
Automatiza el trabajo.
Aprende cómo las personas construyen bots y sistemas.

[kaize @0x_kaize]

https://t.co/ScYWvkqPa4

[Jesse Pujji @jspujji]

https://t.co/BQiXJVUT17

[CG @cgtwts]

This is INSANE, Anthropic ran its marketing with basically one person.

Austin lau, a non-technical growth lead, was running paid search, paid social, email, and seo solo.

Here’s the workflow:

> export ad CSVs into Claude Code
> AI flags underperforming ads
> agents generate new headlines + descriptions
> Figma auto-swaps copy across 100 ad templates
> MCP server pulls live Meta data

The results:

> ad creation went from 2 hours to 15 minutes.
> total marketing output grew 10×.
> conversion rates landed 41% above industry average.

One person doing what used to take an entire marketing team.

[santi @santtiagom_]

Tenés un e-commerce y bajaron tus ventas.

Entonces le decís a Claude:

“Analizá por qué bajaron las ventas esta semana.”

Eso es el prompt → lo que pedís en ese momento.

Para que pueda mirar datos reales, por ejemplo tu base de datos, necesitás conectarlo a tus sistemas. Podés hacerlo con MCP (Model Context Protocol) o con una tool custom definida por vos.

Eso le permite listar ventas, agrupar por fecha o traer campañas.

Pero no querés que Claude analice como quiera.

Querés que siempre compare contra la semana pasada, separe por channel, detecte qué producto cayó más y marque alerta si la caída supera el 20%. Y que cualquier equipo use exactamente ese mismo criterio.

Por eso lo convertís en una Skill.

Una skill son instrucciones y pasos definidos en archivos que Claude lee como contexto. Esto no es un prompt suelto ni una función que se ejecuta sola. Es tu forma de trabajar formalizada para que siempre analice con el mismo criterio.

Y si el problema fuera más grande, el agente podría delegar partes del trabajo. Por ejemplo, crear un subagent para revisar campañas y otro para analizar cohorts, y después combinar todo en una conclusión final.

Un Subagent es un agente invocado por otro para encargarse de una parte del proceso

Entonces:

Prompt → lo que pedís
MCP o tool custom → acceso a datos
Skill → instrucciones formales que Claude usa como contexto
Subagent → agente que puede encargarse de una parte del proceso

[arc. @arceyul]

Tutorial de 1 hora para dar tus primeros pasos con Claude Code aunque no sepas programar ni hayas tocado la terminal.

Consejos, casos de uso y proyectos reales para que aprendas desde 0.

Te lo dejo aquí ⬇️

[Ole Lehmann @itsolelehmann]

i can't believe nobody caught this.

Anthropic's entire growth marketing team was just ONE PERSON

(for 10 months, confirmed)

a single non-technical person ran paid search, paid social, app stores, email marketing, and SEO for the $380B company behind claude

here's exactly how one human is doing the job of a full marketing team:

it starts with a CSV.

1. he exports all his existing ads from his ad platforms along with their performance metrics (click-through rates, conversions, spend, etc)

2. feeds the whole file into claude code

3. and tells it to find what's underperforming.

claude analyzes the data, flags the weak ads, and generates new copy variations on the spot

this is where he gets clever:

he then splits the work into 2 specialized sub-agents:

1. one that only writes headlines (capped at 30 characters)

2. and one that only writes descriptions (capped at 90 characters).

each agent is tuned to its specific constraint so the quality is way higher than cramming both into a single prompt

so now he's got hundreds of fresh headlines and descriptions.

but that's just the text.

he still needs the actual visual ad creative, the images and banners that go on facebook, google, etc.

so he built a figma plugin that:

1. takes all those new headlines and descriptions
2. finds the ad templates in his figma files
3. and automatically swaps the copy into each one.

up to 100 ready-to-publish ad variations generated at half a second per batch.

what used to take hours of duplicating frames and copy-pasting text by hand

so now the ads are live.

the next question is which ones are actually working.

for that he built an MCP server (basically a custom integration that lets claude talk directly to external tools) connected to the meta ads API.

so he can ask claude things like:

• "which ads had the best conversion rate this week"
• or "where am i wasting spend"

and get real answers from live campaign data without ever opening the meta ads dashboard

and the part that ties it all together and closes the loop:

he set up a memory system that logs every hypothesis and experiment result across ad iterations.

so when he goes back to step one and generates the next batch of variations...

claude automatically pulls in what worked and what didn't from all previous rounds.

the system literally gets smarter every cycle.

that kind of systematic experimentation across hundreds of ads would normally need a dedicated analytics person just to track

the numbers from the doc:

ad creation went from 2 hours to 15 minutes. 10x more creative output.

and he's now testing more variations across more channels than most full marketing teams

a $380 billion company.

and their entire growth marketing operation (not GTM) = just one person and claude code lol

truly unbelievable

[Corey Ganim @coreyganim]

https://t.co/5PXVu4D7bL

[¿Por qué es Tendencia? @porktendencia]

"Scary Movie 6":
Por el lanzamiento de su primer tráiler

[H҉A҉C҉K҉E҉R҉ TV @hackervnzl]

🚨🇦🇷 | INCREÍBLE: Mientras que en Perú, las embarcaciones Chinas depredadoras ingresan como en su casa a extraer todo a su paso, en Argentina, la Guardia Costera les da la bienvenida a punta de bombazos hasta hundir sus barcos piratas. ¿Vieron que no es tan difícil?

[Dhanesh Gianani @dhanesh500]

NO WAYYY

Claude in PowerPoint is absolutely INSANE !

It’s so over…

[Grey @jgreyfriend]

In 2010, Bill Ackman gave a 44-minute masterclass on how money actually works using a lemonade stand.

He talks about:
•⁠ ⁠How businesses create value
• ⁠Why most investors lose money
• ⁠How compounding really builds wealth

12 timeless lessons from Ackman's masterclass:

[mrredpillz jokaqarmy @JOKAQARMY1]

Wisdom of Warfare 🤔

[Declaration of Memes @LibertyCappy]

Time for a coffee shark sea shanty... 😂