Suryakant Chaurasiya

Most people think using Claude Code is about writing better prompts. It’s not. The real unlock is structuring your repository so Claude can think like an engineer. If your repo is messy, Claude behaves like a chatbot. If your repo is structured, Claude behaves like a developer living inside your codebase. Your project only needs 4 things: • the why → what the system does • the map → where things live • the rules → what’s allowed / forbidden • the workflows → how work gets done I call this: The Anatomy of a Claude Code Project 👇 ━━━━━━━━━━━━━━━ 1️⃣ CLAUDE.md = Repo Memory (Keep it Short) This file is the north star for Claude. Not a massive document. Just three things: • Purpose → why the system exists • Repo map → how the project is structured • Rules + commands → how Claude should operate If CLAUDE.md becomes too long, the model starts missing critical signals. Clarity beats size. ━━━━━━━━━━━━━━━ 2️⃣ .claude/skills/ = Reusable Expert Modes Stop repeating instructions in prompts. Turn common workflows into reusable skills. Examples: • code review checklist • refactoring playbook • debugging workflow • release procedures Now Claude can switch into specialized modes instantly. Result: More consistent outputs across sessions and teammates. ━━━━━━━━━━━━━━━ 3️⃣ .claude/hooks/ = Guardrails Models forget. Hooks don’t. Use hooks for things that must always happen automatically. Examples: • run formatters after edits • trigger tests after core changes • block sensitive directories (auth, billing, migrations) Hooks turn AI workflows into reliable engineering systems. ━━━━━━━━━━━━━━━ 4️⃣ docs/ = Progressive Context Don’t overload prompts with information. Instead, let Claude navigate your documentation. Examples: • architecture overview • ADRs (engineering decisions) • operational runbooks Claude doesn’t need everything in memory. It just needs to know where truth lives. ━━━━━━━━━━━━━━━ 5️⃣ Local CLAUDE.md for Critical Modules Some areas of your system have hidden complexity. Add local context files there. Example: src/auth/CLAUDE.md src/persistence/CLAUDE.md infra/CLAUDE.md Now Claude understands the danger zones exactly when it works in them. This dramatically reduces mistakes. ━━━━━━━━━━━━━━━ Here’s the shift most people miss: Prompting is temporary. Structure is permanent. Once your repository is designed for AI: Claude stops acting like a chatbot... …and starts behaving like a project-native engineer. 🚀

@rah_x99990 Thanks

@coder_surya Amazing

Most people think using Claude Code is about writing better prompts. It’s not. The real unlock is structuring your repository so Claude can think like an engineer. If your repo is messy, Claude behaves like a chatbot. If your repo is structured, Claude behaves like a developer living inside your codebase. Your project only needs 4 things: • the why → what the system does • the map → where things live • the rules → what’s allowed / forbidden • the workflows → how work gets done I call this: The Anatomy of a Claude Code Project 👇 ━━━━━━━━━━━━━━━ 1️⃣ CLAUDE.md = Repo Memory (Keep it Short) This file is the north star for Claude. Not a massive document. Just three things: • Purpose → why the system exists • Repo map → how the project is structured • Rules + commands → how Claude should operate If CLAUDE.md becomes too long, the model starts missing critical signals. Clarity beats size. ━━━━━━━━━━━━━━━ 2️⃣ .claude/skills/ = Reusable Expert Modes Stop repeating instructions in prompts. Turn common workflows into reusable skills. Examples: • code review checklist • refactoring playbook • debugging workflow • release procedures Now Claude can switch into specialized modes instantly. Result: More consistent outputs across sessions and teammates. ━━━━━━━━━━━━━━━ 3️⃣ .claude/hooks/ = Guardrails Models forget. Hooks don’t. Use hooks for things that must always happen automatically. Examples: • run formatters after edits • trigger tests after core changes • block sensitive directories (auth, billing, migrations) Hooks turn AI workflows into reliable engineering systems. ━━━━━━━━━━━━━━━ 4️⃣ docs/ = Progressive Context Don’t overload prompts with information. Instead, let Claude navigate your documentation. Examples: • architecture overview • ADRs (engineering decisions) • operational runbooks Claude doesn’t need everything in memory. It just needs to know where truth lives. ━━━━━━━━━━━━━━━ 5️⃣ Local CLAUDE.md for Critical Modules Some areas of your system have hidden complexity. Add local context files there. Example: src/auth/CLAUDE.md src/persistence/CLAUDE.md infra/CLAUDE.md Now Claude understands the danger zones exactly when it works in them. This dramatically reduces mistakes. ━━━━━━━━━━━━━━━ Here’s the shift most people miss: Prompting is temporary. Structure is permanent. Once your repository is designed for AI: Claude stops acting like a chatbot... …and starts behaving like a project-native engineer. 🚀

@Code_SantrexAI Thanks

@coder_surya Amazing share

@ZohaibAi__sf Thanks

@coder_surya Excellent post

LTX-2.3 is now live on OpenArt. 🎬 The most capable open video model just got a major upgrade and you can use it right now. What's new in 2.3: → Sharper fine detail: Hair, textures, text, edges. All of it. → Tighter prompt adherence: Complex multi-subject prompts? Handle it. → Stronger image-to-video: less freezing, less Ken Burns drift, more actual motion. → Cleaner audio: fewer artifacts, tighter sync across text-to-video and audio workflows. → Native portrait: up to 1080×1920, trained on vertical data.

@ya71r Thanks

MIT published free AI courses anyone can take. No tuition - just free world-class knowledge. Get the PDF with clickable links: Subscribe free at WildCapital.co Here are 10 free MIT AI courses: 1. Artificial Intelligence Learn core AI principles including reasoning, search, knowledge representation, and machine learning foundations. 🔗 ocw.mit.edu/courses/6-034-… 2. Introduction to Machine Learning A beginner-friendly overview of the main ML techniques and algorithms used in real systems. 🔗openlearninglibrary.mit.edu/courses/course… 3. AI 101 A simple starting point that explains the essential ideas behind artificial intelligence. 🔗 ocw.mit.edu/courses/res-6-… 4. How to AI (Almost) Anything Explore how AI is applied in creative fields like music, art, and perception. 🔗 ocw.mit.edu/courses/mas-s6… 5. Introduction to Deep Learning Hands-on introduction to neural networks and modern deep learning methods. 🔗 introtodeeplearning.com 6. Understanding the World Through Data Learn how to use data analysis and machine learning to interpret real-world problems. 🔗 edx.org/learn/data-sci… 7. Introduction to Algorithms Master the algorithmic thinking required to build efficient AI systems. 🔗 ocw.mit.edu/courses/6-006-… 8. Foundation Models and Generative AI Understand large models and generative AI systems behind tools like ChatGPT. 🔗 ocw.mit.edu/courses/6-s087… 9. Artificial Intelligence in K-12 Education Learn the fundamentals of AI and how it can transform education. 🔗 ocw.mit.edu/courses/6-s062… 10. Minds and Machines Explore the deeper questions about intelligence, cognition, and the nature of AI. 🔗 mitxonline.mit.edu/courses/course… You don’t need expensive courses to learn AI. You need great teachers and consistent practice. Start with one course. Study a little every day. Build real projects as you learn. P.S. Which AI topic are you learning right now? ♻️ Repost this to help someone discover these free MIT resources.

@primemans Thanks

@coder_surya Great share

@TipsAdobe6390 Thanks

@coder_surya Amazing

This is what 99% of people are missing about AI Learn AI in hours, not months Absolutely Free. 1. Claude Skills: substack.com/p/claude-skills 2. AI Slides (PPT in 2026): substack.com/p/powerpoint 3. Claude 101: substack.com/p/claude 4. Claude Cowork + Project: substack.com/p/claude-cowor… 5. Best AI for Search: substack.com/p/grok-420 6. Claude in Excel: substack.com/p/ai-couldnt-d… 7. You're an AI workaholic: substack.com/p/ai-holic 8. Claude Code: substack.com/p/claude-code 9. Setup AI before prompting: substack.com/p/how-to-bette… 10. Nano Banana 2: substack.com/p/banana-2-3bd 11. Claude to sound like you: substack.com/p/i-am-just-a-… 12. 1M followers with AI: substack.com/p/1000000 13. Claude as your computer: substack.com/p/claude-compu… 14. No prompt saves you: substack.com/p/magic 15. Claude for your team: substack.com/p/claude-for-t… 16. Claude interactive charts: substack.com/p/claude-charts 17. Set up Claude Cowork: substack.com/p/claude-cowork 👇Comment "AI" if you find this helpful. Repost so others can take help. Follow me for more. Must bookmark for future reference. Follow @coder_surya for more AI update

@rah_x99990 Thanks

@coder_surya Amazing

@RaviSahu349 Thanks

@coder_surya Amazing share

@rah_x99990 Thanks

@coder_surya Great

@ZohaibAi__sf Thanks

@coder_surya Amazing post

@rakib_md007 Thanks

@coder_surya Great share

@AIToolStrive Thanks

@coder_surya Very informative

@pushkersoni72 Thanks

@coder_surya Free courses make AI accessible!

@primemans Thanks

@coder_surya AWESOME

List of 15 websites where you can download unlimited books for free: 1. planetebook .com 2. oceanofpdf .com 3. freecomputerbooks .com 4. zlibrary .to 5. bookboon .com 6. gutenberg .org 7. manybooks .net 8. pdfdrive .com 9. digilibraries .com 10. openlibrary .org 11. standardebooks .org 12. librivox .org 13. standardebooks .org 14. getfreeebooks .com 15. authorama .com add more👇

@fazla_md85102 Thanks

@coder_surya Great share