asgeirtj/system_prompts_leaks
This repository provides a collection of extracted system prompts from various large language models (LLMs) including Anthropic's Claude, OpenAI's ChatGPT, Google's Gemini, and xAI's Grok, updated ...
Awesome AI Agents › Prompt Libraries
Prompt Libraries
HKUDS/RAG-Anything
RAG-Anything is a next-generation all-in-one multimodal Retrieval-Augmented Generation system that processes and queries diverse document content including text, images, tables, and equations within a unified framework.
dzhng/deep-research
Open Deep Research is an AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models to generate comprehensive markdown reports.
dottxt-ai/outlines
Outlines is an open-source tool that enables structured text generation with large language models, ensuring predictable and schema-compliant outputs for various applications.
microsoft/RD-Agent
RD-Agent is an open-source R&D automation tool by Microsoft designed to automate and enhance industrial research and development processes focused on data and models using AI.
arcee-ai/mergekit
mergekit is a toolkit for efficiently merging pre-trained large language models using various algorithms, supporting CPU and GPU execution, and enabling creation of versatile merged models with maintained inference costs.
icip-cas/PPTAgent
PPTAgent is an innovative system that automatically generates and evaluates high-quality presentations from documents using a two-phase approach and a comprehensive multi-dimensional evaluation framework.
serenakeyitan/awesome-notebookLM-prompts
A curated collection of NotebookLM and Kael.im slide prompts designed to generate presentation-ready decks from various content types.
snap-stanford/Biomni
Biomni is a general-purpose biomedical AI agent that autonomously executes diverse research tasks across multiple biomedical subfields by integrating advanced LLM reasoning, retrieval-augmented planning, and code-based execution.
brycewang-stanford/Auto-Empirical-Research-Skills
Curated catalog of agent skills for empirical social science research, installable into Claude Code or Codex as plugins or skill folders and covering a nine-stage pipeline from data cleaning to journal submission.
johnbean393/Sidekick
Sidekick is a native macOS app that enables offline interaction with a local large language model to retrieve and analyze information from files, folders, and websites on the user's Mac, offering advanced features like function calling, memory, and image generation.
KhazP/vibe-coding-prompt-template
A documented five-step prompt workflow that takes a product idea through research, PRD, technical design and generated AGENTS.md files to an MVP built with AI coding assistants.
muellerberndt/mini-agi
MiniAGI is a simple autonomous agent leveraging OpenAI's GPT models to perform complex tasks autonomously using chain-of-thought reasoning, short-term memory, and self-criticism.
guy-hartstein/company-research-agent
Agentic Company Researcher is a multi-agent AI-powered tool that generates comprehensive, real-time company research reports by synthesizing data from multiple sources using Gemini 2.0 Flash and GPT-4.1 models.
Weizhena/Deep-Research-skills
Structured deep research workflow packaged as skills for Claude Code, OpenCode and Codex, splitting work into an editable outline phase and a parallel web investigation phase that ends in a markdown report.
YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill
Agent skill that searches a curated library of over 10,000 Nano Banana Pro image prompts and returns matching prompts with sample images, or remixes one to fit user-supplied content.
parthsarthi03/raptor
RAPTOR is a retrieval-augmented language model framework that uses recursive tree-structured processing to enable efficient and context-aware information retrieval from large documents.
NeoLabHQ/context-engineering-kit
Marketplace of advanced context-engineering plugins, skills, and commands for coding agents like Claude Code, Cursor, and OpenCode, focused on low token footprint and result quality.
abilzerian/LLM-Prompt-Library
The LLM Prompt Library is a comprehensive collection of experimental prompt templates and tools designed for multiple major large language models, supporting advanced prompt engineering and optimization across various domains.
memfreeme/memfree
MemFree is a hybrid AI search engine and AI page generator that provides accurate answers from personal knowledge bases and the internet, while enabling rapid creation of production-ready web pages using advanced AI models and popular front-end frameworks.
agentcoinorg/evo.ninja
Evo.ninja is a dynamic AI generalist agent that adapts to tasks by selecting specialized agent personas to efficiently achieve user goals through a continuous execution loop.
mshumer/ai-researcher
AI Researcher is an AI-powered tool that automates comprehensive topic research by breaking down subjects into subtopics, generating detailed reports, and combining them into a final document using Claude 3 and SERPAPI.
alirezarezvani/claude-code-skill-factory
Toolkit of templates, prompt systems and guide agents for mass-producing Claude Code skills, subagents, hooks and slash commands, with validation, packaging and install commands.
qx-labs/agents-deep-research
An advanced deep research assistant using a multi-agent iterative approach with the OpenAI Agents SDK to generate detailed research reports compatible with various LLMs and tools.
pgalko/BambooAI
BambooAI is an open-source Python library that leverages Large Language Models to enable conversational data discovery, analysis, and visualization through natural language queries and AI-generated code execution.
alirezarezvani/claude-code-tresor
Claude Code Tresor is a collection of Claude Code utilities bundling 141 specialised subagents, 19 slash commands, autonomous skills and prompt templates across the development lifecycle.
DataScienceUIBK/Rankify
Rankify is a comprehensive Python toolkit for unified retrieval, re-ranking, and retrieval-augmented generation, integrating numerous benchmark datasets and state-of-the-art models for advanced research and development in information retrieval.
hamzafer/cursor-commands
A curated, version-controlled collection of Cursor slash-command prompts in Markdown that give teams reusable AI workflows for reviews, testing, refactoring and documentation inside the Cursor IDE.
mhattingpete/claude-skills-marketplace
A marketplace of Claude Code plugins bundling model-invoked skills and agents for engineering workflows, visual documentation, productivity auditing, code operations and a Python execution runtime.
Ar9av/PaperOrchestra
Skill pack that reimplements the PaperOrchestra multi-agent paper-writing pipeline as instruction documents any coding agent can execute, with no API keys or LLM SDK calls of its own.
Code-and-Sorts/awesome-copilot-agents
Curated list of GitHub Copilot customization files - instruction files, prompts, agent skills, MCP server entries and custom agent definitions - organised by programming language, framework and tool.
dzhng/deep-seek
DeepSeek is an LLM-powered internet-scale retrieval engine designed to comprehensively extract and enrich entities from vast sources, providing detailed structured data rather than single answers.
project-codeguard/rules
Model-agnostic security ruleset that pushes secure-by-default practices into AI coding agents, shipping core rules, translators for popular agent rule formats and validators that test rule compliance.
MODSetter/gpt-instagram
GPT-Instagram is an autonomous multi-agent AI application that analyzes a user's Instagram history to generate personalized and potentially viral Instagram post recommendations reflecting their personality.