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
hamzafer/cursor-commands
Cursor Commands is a curated library of slash-command prompts for the Cursor IDE. Cursor commands are plain Markdown files stored in a .cursor/commands directory; when a developer types a slash in Cursor chat or agent input, the IDE lists every command found in the project directory and in the user-global ~/.cursor/commands directory and inserts the selected prompt ready to run. The repository packages a ready-made set of these files so a team does not have to author them from scratch. Because the commands are ordinary files committed to the repository, they are version-controlled and shipped alongside the code, which keeps prompt behaviour consistent across a team and lets prompt changes go through normal review. The collection groups commands by workflow. Code quality and maintenance covers linting and automatic fixes, running the full linter suite, refactoring while preserving behaviour, performance optimisation, adding error handling, cleaning up verbose AI-generated code, and breaking ambiguous tasks into actionable steps. Review and collaboration covers structured code-review checklists, processing GitHub pull request comments, quick passes over existing diffs, preparing pull requests and drafting pull request descriptions. Testing and reliability covers running the whole suite and triaging failures, generating focused unit tests, step-by-step debugging, resolving compilation errors and tailing Docker container logs. Documentation and onboarding covers writing documentation, generating API documentation with schemas and examples, and checklist-driven onboarding for new developers. Further commands handle security audits and reviews, accessibility audits, database migrations, diagrams, roadmaps, repository overviews, git commit and push flows, and feature scaffolding. Each file is editable, so teams can adapt the wording to their own standards or add new commands. The repository was featured by Cursor and has a companion project, Cursor Hooks, that runs automatically after every file edit.
https://github.com/hamzafer/cursor-commands
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.