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
KhazP/vibe-coding-prompt-template
The vibe-coding prompt template is a documentation repository that packages a structured workflow for building minimum viable products with AI chat tools and AI coding assistants. It contains a series of long prompt files, one per stage, that the user copies into a chat tool such as Claude, ChatGPT, Gemini or Cursor. The workflow moves through five stages: deep research to check demand, competitors and scope realism; a product requirements document that fixes what the MVP must do; a technical design step that selects a stack; generation of agent instruction files such as AGENTS.md that carry the accumulated context into the coding phase; and the build phase itself, done in small passes. Each stage prompt is written so the model interviews the user with clarifying questions and then produces a document that is saved and fed into the next stage, which means the context handed to the coding agent is assembled deliberately rather than improvised. The repository also ships Claude Code skills in a .claude directory, a worked end-to-end example under examples, sections on advanced agent practices, project structure and deployment, and a troubleshooting list of common pitfalls. It is tool-agnostic in the sense that the prompts are plain Markdown and work with any chat model, while badges and instructions call out Claude, Gemini, ChatGPT, Cursor and VS Code as the environments the author uses. The material is aimed at solo builders and small teams who want a repeatable process for turning an idea into shipped code with AI assistance, and the author lists several production sites built with it. There is no code to install; the deliverable is the set of prompts and agent documents themselves.
https://github.com/KhazP/vibe-coding-prompt-template
Also in 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.