Adolf

🧑🏼‍💻 Senior Software Engineer
🎸 Musician

[Adolf @admodev]

Loco, no se cansan de hablar tanto de AI? Muéranse todos 👿

[Adolf @admodev]

@KikeVacantes @Richardalv_1 @alebogado_dev @nicobustelo__ Creo que nadie de los que respondieron acá entendió el punto, mucho vibe codeo muchachos, les está quemando las neuronas

[Adolf @admodev]

@EmmaRincon Negro, feo y perdedor

[Adolf @admodev]

Si el hombre se vuelve malo, al hombre lo llaman perro. Que ofensa para mí perro, compararlo a gente mala!

[Adolf @admodev]

Se puso bien nacionalista y patriota la cosa, me agrada, pero deberían de ser así todos los días, no solo ahora por jugar contra Inglaterra manga de chotos

[Adolf @admodev]

Tanto van a joder porque un hombre de bien mató a un chorro? Yo hubiera hecho lo mismo una vez en el piso, lo remataba, lo meaba y le zapateaba arriba. Hay que matarlos a todos esos negros de mierda y los peronistas son un cancer tambien…

[Adolf @admodev]

@leonpalafox Si fueras serio de verdad, no usarías IA directamente… o a lo sumo la usarías solo para conversar respecto a la arquitectura de tu producto o para temas de marketing, etc y harías toda la parte dura a manopla sin delegarlo a una IA

[Adolf @admodev]

Todas las CLI que te generan un proyecto base para trabajar en cross plataforma desktop development deberían de inicializar React con typescript por defecto a estas alturas si elegis React…

Viva Angular

[Adolf @admodev]

@maxifirtman @nicoharone This. Sumando también el hecho de que más allá de que usemos todos estos métodos, siempre está el factor de la ambigüedad del mensaje escrito si la persona no sabe expresar con claridad lo que precisa

[Adolf @admodev]

Basta de hablar de IA por un día aunque sea hdps

[Miguel Ángel Durán @midudev]

7 conceptos de Ingeniería de Software que te harán mejor programador:

⓵ Bus Factor 🚌
¿Cuántas personas pueden irse del proyecto antes de que todo se pare?
Si la respuesta es 1, hay un problema. Comparte conocimiento y evita dependencias críticas.

⓶ Yak Shaving 🪒
Ibas a cambiar un botón y acabaste migrando medio proyecto.
Son subtareas infinitas que te alejan del objetivo real. Mantén el foco.

⓷ Rubber Duck Debugging 🦆
Explica tu código en voz alta, a un pato o a alguien del equipo.
Al verbalizar la lógica, muchas veces encuentras el error tú solo.

⓸ Deuda Técnica 💸
La solución rápida de hoy puede ser el problema caro de mañana.
Cuanto más tardes en arreglarla, más intereses pagas.

⓹ Optimización Prematura 🧠
Hacer el código más eficiente antes de saber si hay un problema real.
Suele acabar en código más complejo y difícil de mantener.

⓺ Cargo Cult Programming ✈️
Copiar patrones, arquitecturas o código porque “lo hacen los pros”, sin entender por qué. No imites: entiende tus herramientas.

⓻ Scope Creep 📈
El clásico “ya que estamos…”. Pequeñas funcionalidades que se acumulan hasta convertir un proyecto simple en un monstruo. Aprende a poner límites.

[Adolf @admodev]

+1000

[Fazt @FaztTech]

Qué privilegio haber programado tantos años sin agentes ni IAs. No tengo nada en contra de ellas, de hecho me gusta usarlas, pero había una satisfacción real en escribir las cosas por uno mismo. Hoy quizá ya no sea necesario, pero dominar el código es una experiencia que nadie debería perderse, sobre todo si quiere dominar herramientas a profundidad, y aún así estando en estos tiempos de la IA.

[Shraddha Bharuka @BharukaShraddha]

Most people talking about AI agents in 2026… still mix up the basics.

Here are 6 terms you actually need to understand:

1. MCP (Model Context Protocol)
The “USB-C for AI” → One standard to connect AI with tools + data

2. Skills (most confused)
→ Not tools. Not APIs.
→ The logic layer that turns tools into outcomes

3. Single-Agent
→ One brain does everything (plan → execute → respond)

4. Multi-Agent
→ Team of specialized agents working together

5. Agentic RAG
→ Decide → verify → adapt → then answer

6. Memory
→ Short-term (context) + Long-term (vector DBs)

Understand this → you’re ahead of 90% of devs.

Bookmark this.

[Ruben Hassid @rubenhassid]

Stop writing 500-word prompts that don't work.

Here's the exact 3-part structure that works better:

Part 1: Context (.md) files.
Part 2: Clear instructions.
Part 3: "Don't start yet - ask me questions first."

That's it. But most people skip all three. Here's what each one fixes:

Part 1 - Context files.
Step 1. Create a file called "ABOUT ME."
Step 2. Put in your role, audience, goals, and tone.
Step 3. Create a second file: "WRITING STYLE."
Step 4. Add 3–5 examples of your best past writing.
Step 5. Save both as .md files.
Step 6. Upload them before you type a prompt.
Step 7. It knows who you are before it writes a word.

Part 2 - Clear instruction.
Step 1. State the task in one sentence.
Step 2. Name the format. (Post, email, thread, ad.)
Step 3. Name the audience. (Founders, marketers.)
Step 4. That's your prompt. Not 500 words. 3 lines.

Part 3 - "Ask me questions first."
Step 1. Add this line at the end of every prompt:
"DO NOT start writing yet. Ask me clarifying questions first."
Step 2. Claude will ask 3–6 questions.
Step 3. Answer them by clicking buttons.
Step 4. Now Claude writes something that actually sounds like you said it.

Or skip all of that. To download my exact files:

Step 1. Go to https://t.co/psB7XxB2Y4.
Step 2. Subscribe for free. Don't pay anything.
Step 3. Open my welcome email.
Step 4. Hit the automatic reply button inside.
Step 5. Download my .md files. Upload to Claude.

✦ Here's why your current prompts fail (red flags):

"Write me a LinkedIn post about AI tools."
"Make it engaging and professional."
"Keep it under 200 words."

One sentence. No context. No style. No voice.
You gave Claude nothing to work with.

That's like handing someone a blank page & saying, "write something amazing." No reference, examples & direction.

The fix isn't a longer prompt. It's a smarter setup.

Bad prompt: one vague sentence → generic AI slop.
Better prompt: clear task + "ask me questions first"
Best prompt: .md files + clear task + "ask me questions first" → sounds like you wrote it.

To get my exact files, subscribe to https://t.co/psB7XxB2Y4.

♻️ Repost to help one person, prompt better.

[Nainsi Dwivedi @NainsiDwiv50980]

This is the Claude Code Resource Bible.

54 tools.
Agents. MCP servers. Skills. Automation.
Most people still haven’t discovered this stack.

That’s your edge. ⚡

Here’s the curated version (3 best links per section) 👇

🟦 OFFICIAL

• https://t.co/4o8VOOgrcU — Claude Code docs
• https://t.co/laPvgyjYdX — official MCP servers
• https://t.co/N6xZRiTSvX — free certification

🟧 DIRECTORIES

• https://t.co/TGr4PjSdWj — everything Claude Code
• https://t.co/GcZ9KMVeDX — MCP list
• https://t.co/q0U424jqkr — 50+ MCPs

🟨 MCP SERVERS

• https://t.co/q6xQX7gPMJ — browser automation
• https://t.co/ml2Sd1Ss4h — database + auth
• https://t.co/relFond2jA — deploy apps

🟩 SKILLS

• https://t.co/3u23g80ooL — browser control
• https://t.co/ZHAmHlxo27 — full dev workflow
• https://t.co/4lDVEtn49f — recurring tasks

🟪 MULTIPLEXERS

• https://t.co/NTv0UMMdcD — agent terminal
• https://t.co/SXr00XcEcY — orchestrate agents
• https://t.co/NDTR0quWsC — parallel dev

🟥 AGENT FRAMEWORKS

• https://t.co/x0hXlDljbe — multi-agent coordination
• https://t.co/g2VluwZUsD — agent collaboration
• https://t.co/oDcSBof6zR — NousResearch agents

⚙️ AUTOMATION

• https://t.co/DqNqV1E3jX — workflows in code
• https://t.co/QAT0L6GTXL — monitor agents
• https://t.co/vtOYfhlrL0 — self-hosted infra

📚 ARTICLES

• https://t.co/tYcXf1H1Jl — best CLI tools
• https://t.co/zVGTx4UCJC — top MCP servers
• https://t.co/qBhy12KftB — parallel agents

This is basically the Claude Code ecosystem map.

Learn it now → you're early
Ignore it → you're late

Bookmark this. You'll need it

[Ruben Hassid @rubenhassid]

How to set up Claude Cowork completely in 1 hour:

(duplicate my exact folder, files, and prompts)

1. Download the Claude desktop app.
2. Click the Cowork tab at the top.
3. You need a Pro plan ($20/mo). Worth it.

-----

→ 0-10 min: Build your 'Claude Cowork' folder.
Create "CLAUDE COWORK" on your computer.
Inside: About me, Projects, Templates, Output files.
To download mine, go here: https://t.co/psB7XxAv8w.
Don't pay anything. It's free in the welcome email

(The most important step, don't skip it)

→ 10-25 min: Write your .md files.
about-me .md = who you are, how you work.
anti-ai-style .md = every word you'd never use.
To download my files, go to https://t.co/psB7XxAv8w.

(These two files replace 500-word prompts forever)

→ 25-35 min: Set Global Instructions.
Go to Settings → Cowork → Edit Global Instructions.
Folder rules. Naming conventions.
What Claude must read before every task.

(You write this once. It runs every time)

→ 35-45 min: Create your first Cowork Project.
Cowork tab → Projects → +.
Pick a task you do every week.
Scoped memory = it remember what it did last week

(You stop re-explaining yourself)

→ 45-55 min: Run your first real task.
Prompt: "I want to [task]. Ask me questions first."
Claude generates clickable forms to prompt you.
It creates a real .docx in your folder.

(Stop prompting. Start directing)

→ 55-60 min: Schedule a task.
"Every Monday at 7am, create my weekly briefing."
You wake up to a finished doc. That's the endgame.

Pro tip: Always add "Use AskUserQuestion" to every prompt. Claude prompts you instead.

To download all of my other Claude infographics:

Step 1. Go to https://t.co/psB7XxAv8w.
Step 2. Subscribe for free. Don't pay anything.
Step 3. Open my welcome email (most skip this).
Step 4. Hit the automatic reply button inside.
Step 5. Download my infographics from my Notion.
Bonus. Enjoy my best copy-paste prompts, too.

[Adolf @admodev]

https://t.co/Lgm0jrHHwR

[Adolf @admodev]

Built a small Rust CLI for .env file management — three commands I keep wishing existed:

envx diff .env .env.production — semantic diff, not line diff. Shows what actually changed between environments. Secrets are always redacted (passwords, tokens, keys).

[Adolf @admodev]

https://t.co/2Lt5keOA1W

[Adolf @admodev]

envx audit --schema .env.schema .env.staging — validates an env file against a list of required keys. Tells you what's missing, what's empty, and what's undeclared.

envx encrypt .env / envx decrypt .env.age — passphrase encryption via age. No config, no keyfiles.