heatdrop.ai

A free, from-scratch curriculum that makes you build backprop before you touch PyTorch, then ships every lesson as a reusable prompt or agent.

Datawhale's open-source curriculum wants to turn LLM users into agent builders, not just prompt engineers.

Most users run a few prompts and stall; this guide turns Claude Code into a production workflow engine with templates, quizzes, and a weekend-length curriculum.

An HKUST professor bottled a decade of top-conference publishing and reviewing experience into structured AI prompts for grad students.

Clone a travel agent, earnings-call analyst, or multi-agent team in three commands instead of rebuilding from scratch.

A crowdsourced library of copy-paste academic writing prompts, gathered from researchers at MSRA, ByteDance Seed, and top Chinese universities.

A Chinese-language learning roadmap that treats agent engineering as infrastructure, not prompt theater.

A community-curated knowledge base that maps every Claude Code feature to working examples and best practices.

Twenty-five bite-sized projects showing how to wire up LLMs, RAG, and agents into things that actually do work.

Teaches absolute beginners to ship real apps by describing what they want to an AI, then gradually explains how the code actually works.

This repo catalogs 1,000+ "skills" — reusable instruction packages that teach Claude (and rivals) how to do real work, from legal triage to browser automation.

A curated directory of official agent skills from Anthropic, Google, Stripe, and dozens more teams that actually wrote them.

DataTalksClub's open course teaches RAG, agents, and vector search by making you ship a working AI assistant in 10 weeks.

A massive, crowdsourced archive of leaked system prompts from Cursor, Devin, Windsurf, and two dozen other AI assistants.

A trilingual learning roadmap that splits learners into "CLI power users" and "agent builders," then walks both from token math to multi-agent orchestration.

A project-based course on the scaffolding, state management, and verification systems that keep coding agents from declaring victory on broken code.

A crowdsourced archive of extracted and leaked system instructions from major AI models and agents.

Curated prompts and API patterns for OpenAI's GPT-Image-2, organized by real use case rather than vibe or aesthetic.

This repo catalogs 500+ AI agent projects so you don't have to hunt them down yourself.

A curated hub of notebooks, apps, and guides that treat Oracle AI Database as the single backbone for vectors, graphs, memory, and SQL.