Crypto Joker

[Charlie Hills @charliejhills]

GitHub is blowing up with free skills that turn Claude Code into a video studio.

Here are 8 worth bookmarking if you're tired of paying for motion graphics:

1/ pixelfx

244 hand-coded pixel effects: fire, explosions, magic, weather.

The skill makes Claude act like a fussy pixel artist. It draws, renders, checks and tweaks until the effect looks right.

https://t.co/MAr9nrztaC

2/ huashu-motion
Ask for "a 30-second launch video for my product". It writes the script and picks the music.

Don't like a moment? Click that spot in the frame and it fixes only that bit.

https://t.co/rnEBvZTxq5

3/ mg-styles-15

15 motion graphics styles, each with a 10-second demo.

Every one was built by Opus 5.5. Prompts and source code included.

https://t.co/ndOfbksKQo

4/ motion-prompt

A dictionary of 192 motion, camera and web effects.

Each one has a live example and the exact words to prompt it. Perfect when you know the look but not the name.

https://t.co/5JseyprmCJ

5/ animate

Explainer shorts and mini stories, made in pure code.

7 styles built in: paper cut-out, pen hatching, stencil print, pixel art and more. Give it a reference image and it learns a new one.

https://t.co/JLuAsgCxKF

6/ vibe-knowledge-film

Viral Douyin-style knowledge shorts on autopilot.

Drop in a topic or script. It handles subtitles, storyboard and sound effects. You approve a 30-second sample before it builds the full cut.

https://t.co/iVOnc838pU

7/ story-studio

Narrated history and character stories, start to finish.

Topic, script, voiceover and visuals, delivered as a CapCut draft you can open and edit.

https://t.co/xNg0Cm7YfL

8/ video-editor-skills

Rough cuts for vlogs and voiceovers inside DaVinci Resolve.

It removes retakes and pauses, then adds B-roll, music and subtitles. Needs paid DaVinci. Non-commercial use only.

https://t.co/Oy241KDXJb

That's the list.

Bookmark this so you have it when your next video is due.

Repost to help someone else stop paying for motion graphics ♻️

[0xMarioNawfal @RoundtableSpace]

Animated story shorts are all over TikTok and Reels. This free Claude skill makes them on your own PC.

You give it a topic. It writes the script, plans the shots and renders a 55-70 second vertical short: 2D characters in a colorful 3D world, painted town, gliding camera, music and sound effects.

It doesn't use an AI video generator. Everything is rendered in code with three.js and Remotion, so every shot is consistent and editable.

Install: copy the repo into ~/.claude/skills/ and tell Claude Code "Use the cartoon short skill and make a short about..."

https://t.co/pb0Qv2X003

[mojesko @mojeskoqq]

this is f*cking insane. andrej karpathy: "the biggest regret of every engineer in my field right now is every AI conversation they never saved, and in 10 years the ones who started saving in 2024 will be running circles around the rest of us"

andrej karpathy, co-founder of openai, pulled 16M views on one idea: stop using AI to write code, use it to build a second brain that remembers every article, pdf, transcript and conversation you ever fed it

you point claude code at a folder, drop anything into it, and claude reads it, cross-links it with everything already there, and writes it into a living wiki. your knowledge finally compounds instead of leaking out of your head every friday

the stack:

→ brew install obsidian, mkdir ~/vault, cd ~/vault
→ run claude in that folder and type "init a knowledge vault with CLAUDE.md as the rules, /raw for sources, /wiki for your pages"
→ drop any file into /raw (youtube transcript, meeting notes, 400-page pdf, screenshot of a tweet) and type "ingest"
→ claude writes a wiki page, links it to 5 existing ones automatically, updates CLAUDE.md with any new pattern it noticed about how you think
→ never open a blank claude chat again. every question goes through the vault, every answer cites your own sources with dates and links

5 minutes to set up. compounding knowledge from that evening forward

the ugly part most will scroll past: in 10 years the engineers who started this in 2024 will remember every book, every podcast, every meeting with receipts. you will remember none of them. karpathy already picked which side he is on and you are still not on his

full step-by-step is in the article below

bookmark this before you waste another monday

[Chetaslua @chetaslua]

Fable 5.5 its over for video and image models 🤯

THIS IS PURE CODE

one shotted this video holy shit , how this is more beautiful than ai video models

Two ways to check this yourself:

Ask: “Where did @karpathy go in 2026?” with web search and memory turned off. Only the new Fable knows the answer. Then give it the prompt.
Run the same prompt I used for the test (it’s in the screenshot) and see for yourself.

Don’t rely on Grok for basic reasoning like this. Grok doesn’t have up-to-date knowledge of niche stuff. Either join the community or run the test yourself.

Also, a knowledge cutoff doesn’t mean a model knows everything before that date. Sometimes a model doesn’t know about an event even if it happened before its cutoff. This test shows that too.

Run the same prompt on regular Opus 5.5 and the quality drops. On Fable 5.1 it’s worse.

[Hurricane @hurricodes]

THIS IS F**KING GOLD

475 VIDEO DEMOS BUILT WITH CLAUDE OPUS 5.5 IN ONE GITHUB REPO

Motion graphics, explainers, 3D scenes, and even games, all made with HTML, Canvas, SVG, and Three.js.

The crazy part? Every demo comes with its original prompt and source post, so you can pick any one and try recreating it yourself.

475 examples to learn from and experiment with.

Repo in the comments 👇🏻

[Dhruv kumar @Dhruvkumar16797]

Anthropic engineer said something that completely changes how you think about AI agents:

"Don't prompt Claude. Build a system that prompts itself."

In just 26 minutes, he walks through exactly how that works from the core idea to building the entire system step by step.

Most people are still manually prompting AI for every task.

The next generation of builders is designing systems that can plan, execute, evaluate, and improve on their own.

Watch the talk first, then save the guide below you'll look at AI agents very differently afterward.

[Quan Nguyen @stablequan]

Ummm guys, I took @googlegemma Embedding 2 model and train it on 3,000hrs of Vietnamese audio. IT REACHED SOTA. All it took is 2 hours on 8xH100

[Hurricane @hurricodes]

THIS IS F**KING INSANE

This guy just revealed how he's using Claude Code + YouTube to make $98k/month

Just 12 minutes worth watching.

Bookmark and follow for more

[Vincent文森特 @VincentWei93]

最近尝试了非常多 opus5.5 制作视频的不同风格，有些效果实在是惊艳

这个视频盘点了我尝试的风格中，达到商业制作水准的 15 种风格，整个视频、音乐、音效全程由 opus5.5 写代码制作而成

后续会分享每一种风格的提示词

这下视频制作的门槛是真的被打下来了

[Crypto Joker @crypto_jokr]

@threejs Which AI you used for the song? It's an absolute banger!!

[Crypto Joker @crypto_jokr]

@_mexicat @pleometric What AI did you use to create the song? It sounds amazing!!

[Noah Morris @noahmorris]

The wait is over...

Today, We're releasing VidRush to the public:

A swarm of AI video production agents that, over the last 6 months, has been responsible for over 100 million views. 🧵

Use code to skip waitlist → VIDRUSH

[Ryan @ryanspfc7]

Lionel Messi ganhou no jogo de corpo do Kane e Gordon a ia passar do Anderson e Spence ainda kkkkkkkk

39 anos e o cara faz isso ainda, só param na falta.

Fisico bizarro.

[Portal Messi @PortalMessi]

39 anos.

[Winna F.C. @WinnaFC]

🚨| BREAKING: Almost every major World Cup record now belongs to Lionel Messi.🐐

[Ebus 📊 @iamebukaa__]

@TouchlineX Greatest of all time

Destroying kids

Harry Kane on both images 😂😂

[MessiXtra @MessiXtraHQ]

This is undoubtedly the best picture of the World Cup so far. 📸🐐

[ESPN FC @ESPNFC]

Messi and his bodyguards.

[NobleAdolf💎♥️💙FCB @Noblewolf1010]

@ESPNFC England is lucky de Paul ain't on the pitch

[Abduljalal Musa Aliyu @AbduljalaalMusa]

@TouchlineX It’s simply Messi vs. England tomorrow.

This midget is unreal at 39. He’s already surpassed his performances from the last World Cup by the quarterfinals of this one.

Utter madness, man.