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
brycewang-stanford/Auto-Empirical-Research-Skills
Auto-Empirical Research Skills is a curated catalog of agent skills aimed at empirical research across social science disciplines, maintained in association with a Stanford empirical research methodology group and the CoPaper.AI product. The repository organizes its skills into collections listed in a large summary table, with extended per-collection descriptions, usage groupings, exact counts and validation methods kept in separate documentation files; a browser-based skill search page lets users filter skills by method, research stage, language and license, and a terminal quickstart prints the same overview. The stated scope is a full workflow from data cleaning through analysis to submission at a target journal, structured as a nine-stage pipeline. Installation is designed around coding agents: users can hand the repository URL to Claude Code or Codex and state the desired scope, and the agent installs into the directory-level, project-level or global skills folder. Manual installation is also supported, either through the Claude Code plugin marketplace, which offers separate plugins for the journal submission workflow and for Python, Stata, and R with Quarto econometric pipelines, or by cloning the repository and copying individual skill folders that carry their own SKILL.md file. Once installed, skills are selected automatically by the agent based on their description when the user states a task in natural language. The project documents a trust surface intended to make quality checkable: numeric benchmark tasks whose gold values are recomputed from real data on each run, and behavioral evaluation scenarios with rubric items, alongside rigor coverage and security scan reports and continuous integration that validates the catalog. Documentation is published in several languages, with Chinese as the default entry point and English, traditional Chinese, Japanese and Korean versions available.
https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills
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.