Minwoo

Adventurer

[Boris Cherny @bcherny]

I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is different. You should experiment to see what works for you!

[TechieSA @TechieBySA]

3D Landmark Renders by Nano Banana 2 on @TapNow_AI - the workflow is the key!🗽🍌

Prompt⤵️

#tapnow #TapTV #createinpublic #ad

[Linus ✦ Ekenstam @LinusEkenstam]

Would you play this?

[Gadgetify @Gdgtify]

I asked Nano Banana 2 to draw me the evolution of writing.

Prompt: Do this for writing: <instruction>
Input A is a historical concept, technology, or animal evolution (e.g., "The Horse," "Writing," "Flight").
Analyze: Break down the subject into 5 distinct evolutionary stages (from primitive origins to modern day).
Goal: A horizontal unfurling ancient parchment scroll lying on a wooden table.
Rules:
- Path: The scroll acts as a "road." The left end is rough/aged (the past), the right end is smooth/vibrant (the present).
- Scene: Miniature 3D figures/objects are physically walking or evolving along the paper path.
- Transition: The ink drawings of the early stages on the paper slowly lift off and become 3D models as they move right.
- Props: A quill, ink bottle, and a magnifying glass placed near the most detailed modern stage.
- Lighting: Warm, library-style spotlight hitting the center.
Output: ONE image, 16:9 wide aspect ratio, storytelling focus.
</instruction>

[Umesh @umesh_ai]

Use this generic prompt to convert any [VISUAL] into playful, kid-style artwork.

Prompt : A child's crayon drawing on white lined notebook paper. [DESCRIBE YOUR VISUAL HERE], drawn with chunky wax-crayon strokes, wobbly uneven outlines, and simple flat shapes. Bright bold colors with messy coloring that overflows the outlines. Visible heavy pressure marks, small waxy smudges, and uneven scribble shading. Important things are drawn disproportionately big, everything else is tiny. Round friendly faces with dot eyes and big curved smiles, mitten-shaped hands, and blobby rounded animals. A large yellow sun in one corner with radiating lines, puffy cloud shapes, and scattered hearts or stars. A few tiny margin doodles. Flat composition with no realistic perspective or shading. Childlike, joyful, naive art style.

Individual prompts in ALT.

Generate using Nano Banana Pro on @LeonardoAi

[Rimsha Bhardwaj @heyrimsha]

Prompt engineering is dead.

Anthropic recently released the real playbook for building AI agents that actually work.

It’s a 30+ page deep dive called The Complete Guide to Building Skills for Claude and it quietly shifts the conversation from “prompt engineering” to real execution design.

Here’s the big idea:

A Skill isn’t just a prompt.
It’s a structured system.

You package instructions inside a SKILL .md file, optionally add scripts, references, and assets, and teach Claude a repeatable workflow once instead of re-explaining it every chat.

But the real unlock is something they call progressive disclosure.

Instead of dumping everything into context:

• A lightweight YAML frontmatter tells Claude when to use the skill
• Full instructions load only when relevant
• Extra files are accessed only if needed

Less context bloat. More precision.

They also introduce a powerful analogy:

MCP gives Claude the kitchen.
Skills give it the recipe.

Without skills: users connect tools and don’t know what to do next.
With skills: workflows trigger automatically, best practices are embedded, API calls become consistent.

They outline 3 major patterns:

1) Document & asset creation
2) Workflow automation
3) MCP enhancement

And they emphasize something most builders ignore: testing.

Trigger accuracy.
Tool call efficiency.
Failure rate.
Token usage.

This isn’t about clever wording.

It’s about designing an execution layer on top of LLMs.

Skills work across Claude, Claude Code, and the API. Build once, deploy everywhere.

The era of “just write a better prompt” is ending.

Anthropic just handed everyone a blueprint for turning chat into infrastructure.

Download the guide here: https://t.co/Bf3j0GFRGu

[Mark Gadala-Maria @markgadala]

It’s only been 24 hours since Nano Banana 2 launched.

And people are already pushing it to the limit.

10 wild examples:

1) Creating new Pokemon games that never existed

https://t.co/3mrBdoLWhO

[Noor 🌸 @Noor_ul_ain43]

1. Open @grok

2. Upload your photo

3. Prompt⤵️
A high-quality 3D cartoon sticker pack of a cute young girl with short messy brown bob hair and big expressive brown eyes, wearing a burgundy leather jacket over a white shirt. Multiple different emotional reactions arranged in a grid layout. Expressions include: shocked (hand over mouth, “OMG!” text bubble), angry (red anger mark, steam from head), surprised (holding phone, open mouth), crying loudly with tears, screaming “AAA!”, thumbs up saying “Cool!”, furious with fire background, winking with hearts, sad with rain cloud above head, shy saying “Sorry”, confused with spiral eyes and question marks, and loudly crying “WAAH!”.
Soft warm beige background, white sticker-style outlines, glossy finish, soft shadows, Pixar-style 3D rendering, highly detailed, vibrant colors, cute emoji-style speech bubbles, clean studio lighting, centered composition, high resolution.

[lucas @lucas_flatwhite]

Google Labs + DeepMind 작정하고 만든 마케팅 도구
= 포멜리 (Pomelli)

이번에 새로운 기능을 달고 업데이트되었네요!

소규모 비즈니스나 1인 마케터들에게는 정말 좋은 소식이예요. 브랜드 아이덴티티를 유지하면서 고퀄리티 마케팅 자산을 순식간에 만들어준다고 하니까요.

특히 이번에 추가된 'Photoshoot' 기능이 인상적이예요. 제품 사진 한 장만 있으면 스튜디오 촬영급 연출컷을 뽑아낼 수 있어요.

↓

포멜리의 핵심은 'Business DNA'라는 개념이에요.

내 웹사이트 URL만 입력하면 AI가 텍스트, 이미지, 로고, 폰트, 컬러 팔레트까지 싹 분석해서 우리 브랜드만의 '디지털 유전자'를 추출합니다ㄷㄷ

덕분에 매번 디자인 가이드를 뒤적거리지 않아도, AI가 알아서 우리만의 브랜드스러운 결과물을 만들어주는 거죠.

- 3단계로 끝나는 마케팅 워크플로우:

1. Business DNA 구축: URL 입력 한 번으로 브랜드 성격과 시각적 가이드라인 자동 생성

2. 캠페인 아이디어 제안: 계절 이벤트나 신제품 출시에 맞는 아이디어를 AI가 먼저 제안

3. 자산 제작 및 편집: 인스타, 페이스북, 링크드인 등 플랫폼 규격에 딱 맞는 이미지와 카피를 생성하고 즉시 다운로드 가능

↓

새로 추가된 'Photoshoot' 기능을 다시 얘기하자면..

기존에는 제품 누끼 따고 배경 합성하느라 고생했는데, 이제는 제품 사진 한 장만 업로드하면 됩니다.

AI가 제품을 인식하고 브랜드 톤에 맞는 다양한 배경과 연출을 합성해서, 마치 전문 스튜디오에서 촬영한 듯한 커스텀 제품 샷을 만들어줘요.

마케팅 예산이 부족한 팀에게는 구세주 같은 기능이 될 것 같아요.

↓

현재는 미국, 캐나다, 호주, 뉴질랜드에서 무료로 사용할 수 있습니다. (아쉽게도 아직은 영어권 우선이네요)

구글 랩스의 실험적 프로젝트라 베타 딱지를 달고 있지만, 딥마인드의 기술력이 들어간 만큼 퀄리티는 상당할 것으로 보여요.

단순한 디자인 툴이 아니라 'AI 브랜드 비서'를 지향한다는 점에서... 무섭군요?

디자인 감각이 부족하거나 대행사 쓸 예산이 없는 초기 창업자들에게는 포멜리가 든든한 파트너가 되어줄 것 같습니다!

[Google Labs @GoogleLabs]

Today, we’re introducing Pomelli’s latest feature update, ‘Photoshoot’

With Photoshoot, you can start from a single image of your product and easily create high quality, customized product shots to elevate your marketing.

Available free of charge in the US, Canada, Australia & New Zealand! Get started with Pomelli today at https://t.co/SbeT00ToNx

[Minwoo @mwk_rex]

I'm claiming my AI agent "Gejang" on @moltbook 🦞

Verification: shore-JPMA

[Min Choi @minchoi]

Genie 3 is pretty wild.

People just dropped some new insane 3D world videos

100% AI

1. "You are a fish, you must escape the kitchen"

[아이반 IVAN @0ooooo0]

저는 바이브코딩으로 6명의 AI와 함께 일하고 있슴다

저는 @yuyustudioteam 날씨앱을
혼자 개발하고 있지 않슴다!

1. 프론트엔드 개발자
2. 인터렉션 디자이너
3. QA 엔지니어
4. 보안 개발자
5. UI 디자이너
6. UX 디자이너

무려 6명의 AI와 함께 일하고 잇쥬
이렇게 적절한 에이전트를 만들어두면
작업할 때 적절하게 의견을 줌다 ㄷㄷ

UI 디자이너 입장에서는
아이콘이 불일치하니 통일하자고 의견을 줬고

프론트엔드 개발자 입장에서는
누락되거나 사용하지 않는 위젯에 대해 확인해주고

UX 디자이너 입장에서는
부족한 타이포를 적절하게 수정까지 해줌다 ㄷㄷㄷ

이렇게 에이전트를 잘 구성하면
진짜 좋은 퀄리티의 바이브코딩이 가능해지는 것임다
지짜 미쳣죠

[Anima @Anima_Labs]

Today, I tried to create a more traditional character the kind you might imagine in an animated film

I can picture her as a slightly clumsy and absent-minded florist, often getting scolded because of it, but with a very big heart and she could also be quite a foodie

AI tools : 👇
Midjourney (2D) + @LeonardoAi : Nano Banana 2 (3D) + Kling 2.5 (Animation) + Topaz (Upscale) + Suno (Music)

[Dilum Sanjaya @DilumSanjaya]

Vibe coded a ship selection UI for a space exploration game

3D assets
Nano Banana + Midjourney → Hunyuan3D
UI
Nano Banana → Gemini Pro

More details ↓

[MeshyAI @MeshyAI]

Image to 3D, now in ANY pose! 🤸‍♂️

Simply upload your image + a pose reference photo. Meshy generates the model to match it perfectly.

No complex rigging needed. Create 3D characters your way.

[Lian Lim | Dashboard & AI Automation Expert @dashboardlim]

i built 47 n8n workflows in 3 months

everyone asks: "how do you build so fast?"

ONE prompt

i created a mega prompt that tells any LLM how to architect n8n workflows

the process:
→ copy prompt
→ describe what you want
→ get production-ready spec

no more:
- spending weeks figuring out structure
- googling "where does error handling go"
- wondering if you need code or built-in functions
- rebuilding because you missed something

the AI generates:
→ complete workflow architecture
→ node-by-node specs
→ error handling built in
→ API integration details
→ testing cases
→ deployment checklist

works for ANY automation:

like order processing, CRM sync, email sequences, document workflows, approval chains, calculations

same prompt structure every time

reality check:

most people will save this and never use it

but if you actually use it?
50+ hours saved this year = $5K-$25K in time back

the prompt is free.

inside:
→ complete mega prompt (copy-paste)
→ 3 example workflows
→ works with ChatGPT/Claude/any LLM
→ common mistakes to skip
→ advanced customization
→ 10-step checklist
→ ready-to-use templates

WANT the prompt playbook on how to build any n8n workflow with AI?

Like + Comment “FREE” and i’ll dm it to you.

some people are building agencies around this.

[Stella @AI_With_Stella]

$345K in 35 days.

No add agency, no freelancer. No creative team.

Just 1 tool that spits out 348+ videos/day while we sleep.

400+ TikToks auto-posted daily
30 burner accounts
100% organic traffic

Comment “ Ai Mass”

&amp; I’ll send the tool.
(Must be following)

[Zephyr @Zephyr_hg]

I never run out of content to post anymore.

Built an automation that monitors 50+ news sources, scores articles for relevance, and writes social posts automatically.

It finds trending topics in my niche before they explode everywhere else.

Saves me 15-20 hours monthly and keeps me ahead of every trend.

Comment "NEWS" and I'll DM it to you (must be following)

[MJ Kayum @mjkayum]

Nano Banana + MakeUGC + Veo3 = AI content Factory

This agent pumps out hundreds of ads daily — fully automated.

- No $300 creators
- No $10K/month agency fees
- No products

Comment “Nano” and I'll send it for FREE!
(must be following)