21 Lessons, Get Started Building with Generative AI

Extracted system prompts from ChatGPT (GPT-5.4, GPT-5.3, Codex), Claude (Opus 4.6, Sonnet 4.6, Claude Code), Gemini (3.1 Pro, 3 Flash, CLI), Grok (4.2, 4), Perplexity, and more. Updated regularly.

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

220+ Claude Code skills & agent plugins for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory.

AI Observability & Evaluation

The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

Stop prompting. Start specifying.

Vibe-Skills is an all-in-one AI skills package. It seamlessly integrates expert-level capabilities and context management into a general-purpose skills package， enabling any AI agent to instantly upgr

Curated GPT-Image-2 prompts for the OpenAI API — portraits, posters, UI mockups, game screenshots, character sheets, and more. Ready-to-use prompts for gpt-image-2.

Humans and AI agents, building knowledge bases together. Self-hosted document annotation, version control, semantic search, and MCP.

🍰 PromptLayer - Maintain a log of your prompts and OpenAI API requests. Track, debug, and replay old completions.

Prompt Driven Development Command Line Interface

A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.

Local coding agent with neat UI

YAO = Yielding AI Outcomes. A lightweight but rigorous system for creating, evaluating, packaging, and governing reusable agent skills.

89 skills and 38 specialized agents that enforce proven engineering practices for AI-assisted development. TDD, systematic debugging, parallel code review, and 10-gate development cycles — as a Claude

CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework

🧠 Curated collection of 214+ best OpenClaw personas — weekly updated by Deskclaw.net from GitHub & community. AI, productivity, dev, marketing, finance & more.

Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.

A practical LLM learning path from clear prompting to tool use, IDE collaboration, MCP, Skills, and harness-driven agent workflows.

The Ultimate Claude Code Toolkit — 127 skills, 86 agents, 109 marketplace repos (11,700+ community skills), 30 commands, 8 hooks, GSD framework. Drop-in ~/.claude config that auto-activates the right

See how you really use AI — X-ray your AI coding sessions locally

Agentic prompts are the most important code you're not engineering. PromptKit fixes that — composable, version-controlled prompt components (personas, protocols, formats, templates) that snap together

These guides are designed to help teams and individuals leverage AI tools like GitHub Copilot, OpenAI, and Claude to build software projects efficiently and effectively

Handle LLM output variance for ruby_llm — retry on malformed JSON or rule violations, escalate to a smarter model, measure variance on datasets, gate CI on regressions.

The building blocks of an enterprise adoption framework for agentic coding — technical training, adoption playbooks, governance policies, industry analysis, proposal templates, and practical workflo

🛠️ Build reliable AI agents and prompts using our open-source tools and models for effective AI engineering. Join the discussion on Discord for insights.

A tool that compiles messy natural language prompts into a structured intermediate representation (IR) and optionally sends them to LLMs like ChatGPT for cleaner, more reliable responses.

A comprehensive suite of protocols, meta-prompts, and orchestration tools designed to streamline software development workflows, project management, and team collaboration. Includes the VibeCode Proto

PromptOS is a centralized prompt intelligence system that understands, evolves, and adapts across domains. Acting as a Prompt Operating System, it continuously improves using user feedback and reinfor

Multi-agent orchestration system for GitHub Copilot with 29 specialized agents, reusable skills/prompts, and validation tooling.

Persistent, deterministic, and user-managed project memory for vibe coding.

🧭 PromptDrifter – one‑command CI guardrail that catches prompt drift and fails the build when your LLM answers change.

Declarative framework for orchestrating multi-model LLM pipelines with context engineering and quality gates.

🍌 Explore curated Nano Banana Pro prompts for creating stunning PPT slides and infographics with multilingual support and instant previews.

SIGNAL — Agent Skills: terse structured output (tiers, templates, checkpoints), git workflow skills (commit, push, PR, review, ckpt), Karpathy-inspired coding norms. Claude Code, Cursor, Gemini CLI, C

Explore curated Seedance 2.0 prompts with proven results, clear sources, and ready-to-use templates for faster content generation.

🎥 Generate precise video prompts for Jimeng Seedance 2.0 using structured patterns, templates, and AI agent compatibility.

Improve AI text to sound natural, clear, and human-like by reducing stiffness and enhancing specificity for multiple AI writing tools.

🧠 Qualify leads with an AI-driven system that understands intent, asks key questions, and structures quality leads without hardcoding processes.

🎬 Provide unofficial API access and documentation for Seedance 2.0 to enable video generation with ByteDance’s model.

🤖 Enhance AI coding assistants with battle-tested rules for reliability, predictability, and effectiveness in your projects.

A dotfiles repo that treats AI agent behavior as infrastructure

Convert website capabilities into reusable, API-first AI skills with automated authentication and seamless integration for workflow automation.

🍌 Generate JSON prompts for ultra-photorealistic images of nano bananas and related subjects, ensuring reproducible and high-quality visual outputs.

Enhance ChatGPT on the web with session management, prompt reuse, formula and Mermaid support, plus export and backup features.

🌑 Manage agentic memory and context persistence with Shadow Genesis, a self-replicating system built for scalable, intelligent data handling.

Provide structured markdown guides to teach AI assistants how to complete complex React Native engineering tasks efficiently.

🎨 Create stunning logos effortlessly with ai-logo-maker, your offline tool for designing unique identities while keeping your data secure and local.

Power advanced AI to create films using text, images, audio, and video inputs with a flexible quad-modal filmmaking engine.

🚀 Remove watermarks from SORA 2 video generations to enhance clarity and accessibility. Experience seamless AI-generated content without distractions.

Enhance prompts by injecting real project context to create clear, professional, and actionable instructions with quality and risk insights.

Provide a structured code refactoring process for OpenAI Codex with guardrails, decision gates, and parallelism awareness to simplify and improve code quality.

llm-skills breaks down complex AI tasks into small, reusable building blocks that work like LEGO pieces for browser based LLMs. Instead of writing one giant instruction, you snap these simple parts to