█████╗   ██████╗  ███████╗ ███╗   ██╗ ████████╗ ██╗  ██████╗     █████╗  ██╗
██╔══██╗ ██╔════╝  ██╔════╝ ████╗  ██║ ╚══██╔══╝ ██║ ██╔════╝    ██╔══██╗ ██║
███████║ ██║  ███╗ █████╗   ██╔██╗ ██║    ██║    ██║ ██║         ███████║ ██║
██╔══██║ ██║   ██║ ██╔══╝   ██║╚██╗██║    ██║    ██║ ██║         ██╔══██║ ██║
██║  ██║ ╚██████╔╝ ███████╗ ██║ ╚████║    ██║    ██║ ╚██████╗    ██║  ██║ ██║
╚═╝  ╚═╝  ╚═════╝  ╚══════╝ ╚═╝  ╚═══╝    ╚═╝    ╚═╝  ╚═════╝    ╚═╝  ╚═╝ ╚═╝

Learning Hub for Product Builders

The most complete collection of battle-tested AI-assisted development resources — for Product Managers, Designers, and Developers who want to ship real products with AI.

What's inside: 329 agent skills (Cursor, Claude Code & Codex) · 8 slash commands · 21 coding rules · 201 Jupyter notebooks · 51 research papers (PDF, 9 themes) · 16 industry reports · 21 n8n workflow templates · 14 system prompts · 36 OpenClaw agents · 5,380 OpenClaw skills indexed · 73 curated GitHub projects.

Whether you're a PM who wants to prototype faster, a Designer who wants to understand the code your AI is generating, or a Developer looking for the sharpest rules to ship with — this repo is built to be copied, forked, and used the same day.

Quick start

Pick your path and start in under 5 minutes:

For Product Managers

1. Read cursor-claude-codex/product-management/no-vibe-coding.md — Spec-Driven Development
2. Use cursor-claude-codex/product-management/create-prd.md to turn an idea into a PRD with AI
3. Generate tasks with cursor-claude-codex/product-management/generate-tasks.md
4. Ship with cursor-claude-codex/skills/writing-plans/ + cursor-claude-codex/skills/executing-plans/

For Designers

1. Drop cursor-claude-codex/skills/frontend-design/ into your Claude Code project
2. Follow cursor-claude-codex/skills/web-design-guidelines/ (Vercel) for distinctive UI
3. Read cursor-claude-codex/best-practices/accessibility.md before shipping

For Developers

1. Install the core skills: brainstorming, test-driven-development, systematic-debugging
2. Grab the slash commands: cursor-claude-codex/commands/ (code-review, final-review, git-commit, security-audit)
3. Pick your stack rules from cursor-claude-codex/coding/ (Python, TypeScript, FastAPI, Next.js, …)
4. Lock down security with cursor-claude-codex/security/anthropic-security-audit.md

For Learners

1. Start with the notebooks in research/nn-zero-to-hero/ (Karpathy's Zero to Hero)
2. Read learning/README.md to pick a textbook
3. Follow research/understanding-deep-learning/ chapter-by-chapter

Quick links

What's inside

Cursor, Claude Code & Codex (cursor-claude-codex/)

Prompts library (prompt-engineering/)

Battle-tested prompts for Cursor, Claude, Grok, Kimi, n8n, Lovable, v0, and more — see prompt-engineering/README.md and prompt-engineering/prompts/.

Learning (learning/)

Five freely-available textbooks and references that ground the notebooks and skills in this repo: Understanding Deep Learning (Prince), Mathematics for Computer Science (MIT 6.042J), Algorithms for Decision Making (Stanford), the CUDA C++ Programming Guide (NVIDIA), and Optimizing Software in C++ (Agner Fog). See learning/README.md for what each is best for.

Reports (reports/)

16 industry reports from McKinsey, Deloitte, KPMG, OpenAI, Anthropic, Stanford HAI, Air Street Capital, and others — useful for pitch decks, business cases, and agent metrics. See reports/README.md for a themed index.

OpenClaw (openclaw/)

36 agent projects catalogued (OpenClaw + 35 derivatives) and 5,380 community skills indexed in 30 categories (local snapshots from machinae/awesome-claws and VoltAgent/awesome-openclaw-skills). Details: openclaw/README.md, openclaw/skills/README.md.

Projects to watch (nice-projects/)

73 hand-picked open-source repos — tools, AI/ML, agent skills, and the upstream sources behind vendored hub content. See nice-projects/README.md and the full catalog at cursor-claude-codex/references/upstream-repos-catalog.md.

n8n templates (n8n-templates/)

Workflow templates (AI assistants, messaging, sheets, scraping, etc.).

Research & experiments (research/)

Educational notebooks and autonomous research setups. Full catalog and source links: research/README.md.

Other items (e.g. DeepSeek OCR) are documented in research/README.md when present.

Papers (papers/)

51 research papers (PDFs) in 9 thematic subfolders — from classic deep learning (AlexNet, DQN, Word2Vec) through the foundation-model era (Transformers, BERT, GPT-1/2/3, scaling laws, Chinchilla, RLHF, diffusion) to contemporary agent, harness, reliability, and ethics research. Full index: papers/README.md.

Includes 12 foundational PDFs added to the repo (early DL through alignment and diffusion). Code-LLM papers (AlphaCode, StarCoder, DeepSeek-Coder, …) are external links in papers/README.md.

Stats

Counts verified against the repo tree (2026-07-02):

About

This repository is maintained by Adrianno, a Staff Product Manager at Pipefy, diving into the magic behind LLMs.

You can find more about me on GitHub and LinkedIn. Feel free to connect with me, I'm always open to discussing AI, product management and building cool things together!

Who this is for

• Product Managers who want to prototype ideas without waiting for engineering
• Product Designers who want to understand the code their AI generates
• Product Builders who want to go from idea to product faster
• Developers looking for optimized Cursor, Claude Code, and Codex rules
• Anyone curious about how AI-assisted development actually works.

What makes this different

This isn't just another collection of AI tools. We focus on:

• Understanding the fundamentals — You'll learn why things work, not just how to use them
• Real-world applications — Every example is something you'd actually build
• Product thinking — We connect technical concepts to business outcomes
• Reproducible results — Everything is tested and documented

Inspired by

AI & development

• awesome-copilot — Custom agents, instructions, skills, and plugins for GitHub Copilot
• awesome-llm-apps — LLM applications with AI Agents
• awesome-cursorrules — Configuration files that enhance Cursor AI editor experience
• awesome-deepseek-integration — Integrate the DeepSeek API into popular softwares
• awesome-datascience — Data science resources

Programming languages

• awesome-python — Python resources
• awesome-typescript — TypeScript resources

Architecture & design patterns

• awesome-design-patterns — Software and architecture related design patterns
• awesome-system-design-resources — Learn System Design concepts and prepare for interviews
• awesome-scalability — The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

Design & product

• Awesome-Design-Tools — The best design tools and plugins for everything
• awesome-for-beginners — A list of awesome beginners-friendly projects
• awesome-cto — Resources for Chief Technology Officers, with emphasis on startups

Contributing

1. Fork the repo
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (see CONTRIBUTING.md for Conventional Commits)
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

Full guidelines: CONTRIBUTING.md.

License

This project is licensed under the MIT License — see LICENSE.

Ready to level up? Start with cursor-claude-codex/README.md, openclaw/README.md, nice-projects/README.md, or prompt-engineering/README.md. The best way to learn is by doing.