Rafa

Software Engineer 💻

[dimi @dimitrisanders_]

Cbum traz uma reflexão importante sobre como o ambiente e as pessoas ao nosso redor moldam a forma como pensamos.

E como, aos poucos, isso pode acabar nos afastando do caminho que a gente realmente queria.

[Quincy Larson @ossia]

This weekend learn AI-assisted development best practices. FREE 2 hour course on Claude Code, Open Claw, and tons of other dev tools.

[Dhairya @dkare1009]

Claude Code Project Structure (Quick Guide)

Most projects start with just CLAUDE.md.
That’s why they stay basic.

Here’s the structure that turns Claude into an engineering partner 👇

📌 Core Files
• CLAUDE.md → project rules & context
• CLAUDE.local.md → personal overrides
• mcp.json → connects tools (GitHub, Slack, DBs)
• claude/settings.json → permissions + models

📂 claude/ (real power)
• rules/ → coding + testing standards
• commands/ → reusable workflows (/review, /fix)
• skills/ → auto-loaded expertise (on-demand)
• agents/ → specialized sub-agents
• hooks/ → automation + guardrails

💡 Better structure = better output

Set it once → every session improves.

What does your setup look like?

Save 💾 • Follow for AI workflows 🚀

[Rafa @lrnsans]

Morning 🥇

[Suryansh Tiwari @Suryanshti777]

Holy shit.

Someone just leaked the Claude Code project template teams are quietly using.

This isn't prompting anymore.
This is AI engineering infrastructure. ⚡

The entire setup revolves around one file: CLAUDE.md

Every time Claude makes a mistake → you add a rule
Every time you repeat yourself → you add a workflow
Every time something breaks → you add a guardrail

Claude literally trains itself on your project.

And the structure is wild:

• CLAUDE.md → project memory & instructions
• skills/ → reusable AI workflows
• hooks/ → automated checks & guardrails
• docs/ → architecture decisions
• src/ → actual code modules
• tools/ → scripts + prompts

You're not chatting with AI anymore.
You're building an AI that knows your repo.

The craziest part?

You only configure this once.

After that Claude: – reviews code automatically
– refactors on command
– enforces architecture rules
– writes release notes
– runs workflows from skills
– remembers past mistakes

And it keeps getting smarter.

Most people:
open ChatGPT → write prompt → copy paste → repeat

This setup:
open terminal → run skill → code shipped

You're basically running AI teammates inside your repo.

This template is the difference between: • using Claude occasionally
• running Claude like infrastructure

Drop it in any project.
Your AI stops guessing — and starts operating.

[𝕯𝖊𝖋𝖆𝖑𝖙 🕵🏻‍♂️⚡ @0xdefalt]

🧵👇Quer aumentar suas chances de conseguir um emprego melhor, subir de cargo ou deixar seu currículo muito mais forte em 2026? Você vai entender como ter certificados internacionais em solo brasileiro de uma das maiores empresas de técnologia/IA da atualidade para se preparar para as oportunidades que estão surgindo no Brasil nessa área.

A Anthropic a poucos dias liberou 13 cursos e certificados oficiais de inteligência artificial completamente grátis e eu não sei como tem tão pouca gente sabendo disso!

Isso não é só “mais um curso”. São certificados que você pode colocar no LinkedIn e no currículo, que mostram que você já está preparado para trabalhar com IA — a habilidade mais valorizada do mercado hoje.

Estudantes, profissionais, professores e empreendedores estão usando isso para abrir portas que antes pareciam impossíveis.

Vou listar todos com detalhes para você não perder tempo.
Salva essa thread!

1 - Claude 101
Curso inicial perfeito para todo mundo. Aprenda a usar o Claude no dia a dia: primeiras conversas, comandos avançados, aplicativo para computador, Projetos, Artefatos, Habilidades, Modo de Pesquisa e casos de uso por profissão. Super prático e rápido.
→ https://t.co/M0fPqZbXeL

[Alok Kumar @Alokkumarzz]

Claude FULL COURSE 1 HOUR (Build & Automate Anything)

[Rony @Ronycoder]

Claude FULL COURSE 1 HOUR (Build & Automate Anything)

[Alif Hossain @alifcoder]

🚨 Anthropic just shared the exact file their Claude Code team uses internally.

It’s called CLAUDE.md.

Drop it into your project and Claude will:

→ Plan before coding
→ Learn from corrections
→ Verify before shipping
→ Fix bugs end-to-end

This changes how you build with AI.

[Claudio @kazzkiq]

Vai no seu Claude Code e cola esse prompt, e no final escreve "ultrathink about this":

You'll act as a professional code reviewer and tech lead for this whole codebase. Review all my project code structure, each file, each page (if any), each endpoint (if any), each logic, and write me a QUESTIONS.md with all the architectural, refactoring and technical questions you found odd or need more info about.

The idea here is for you to grasp and understand what this project its about, what its doing, what its lacking in terms of performance, architecture and security. Any flaws, any issues, any bugs or any improvements must be reported in the QUESTIONS.md as independent questions so I can answer them in this file explaining what should be done and how, and what is a bug or what is intended behavior.

This file can be quite big (lots of questions) so don't be shy nor lazy, write all the questions or attention points you find!

Once you write the file, I'll then answer the QUESTIONS.md and prompt you again so you can then start with the improvements in the codebase based on your own questions answered by me in QUESTIONS.md.

[Rafa @lrnsans]

@ManfroiRenato Based

[Polymarket @Polymarket]

BREAKING: New startup "RentAHuman" allows AI agents to rent humans to perform tasks they cannot physically perform themselves.

[Lincoli Xavier • talkbud.app @lincolixavier]

Roadmap que vou usar pra estudar LLM's

Álgebra Linear
- Álgebra básica
- Sistemas lineares
- Vetores e Embeddings
- Matrizes e Tensores
- Multiplicação de Matrizes:
- Transformações Lineares

Funções de Ativação e Cálculo
- Softmax
- ReLU/GELU
- Gradiente Descendente

Probabilidade e Estatística
- Normalização
- Dropout

Trigonometria
- Positional Encoding

Bora?

[freeCodeCamp.org @freeCodeCamp]

Running LLMs locally has a lot of advantages.

It gives you access to AI capabilities offline and ensures data privacy, all without cloud costs.

In this in-depth tutorial, @KraneOliver shows you how to set up, use, and customize popular models locally with Ollama.

https://t.co/mxTsvzbf7M

[freeCodeCamp.org @freeCodeCamp]

If you want to run an LLM, you don't have to rely on cloud-based APIs anymore - you can do it right on your local machine.

And in this tutorial, @chairahalkar helps you build your own local AI agent.

You'll use the Qwen 3 family of LLMs along with Ollama which simplifies running LLMs locally.

https://t.co/JgLjzAbTo0

[Peter Agboola @baba_Omoloro]

Anthropic has launched free courses to master AI with certificates for $0.00

https://t.co/hwJvuJHIdo

[CV.YH @0xCVYH]

A Anthropic acabou de liberar um CURSO GRATUITO de Prompt Engineering interativo.

9 capitulos + exercicios praticos + playground pra testar na hora:

1. Estrutura basica de prompts
2. Ser claro e direto
3. Atribuir roles
4. Separar dados de instrucoes
5. Formatar outputs
6. Pensamento passo a passo
7. Usar exemplos
8. Evitar alucinacoes
9. Construir prompts complexos (casos reais)

Se voce usa IA e ainda nao domina prompt engineering, ta deixando 90% do potencial na mesa.

Prompt bom = resultado bom. Prompt ruim = frustracão.

GRATUITO no GitHub:
https://t.co/1022fVBZ2i

Salva esse tweet. Voce vai precisar.