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
Weizhena/Deep-Research-skills
Deep Research Skills packages a structured, multi-phase research workflow as installable skills for the Claude Code, OpenCode and Codex command line agents. The design is human-in-the-loop: research is split into an outline phase and a deep investigation phase so the user can inspect and extend the plan before any large search run begins. Five commands drive the flow. The research command takes a topic and produces an outline listing the items to investigate together with the fields to collect for each of them; add-items and add-fields extend that outline when the first pass is too narrow; research-deep then works through the outline, dispatching parallel web search agents to gather the requested fields for every item; and research-report turns the accumulated JSON results into a markdown report with a table of contents. Installation copies the skill directory into the agent configuration folder, adds a bundled web search agent definition plus its supporting modules, and installs the pyyaml Python dependency. Each host has its own variant: Claude Code and OpenCode read from the Claude skills directory, while Codex uses separate skill and agent directories with a TOML agent definition and needs multi-agent and user-input features enabled in its configuration, for which an installation script is provided. The README notes that web search in OpenCode requires an environment variable to be set, otherwise only the weaker fetch tool is available, and that recent Claude Code versions can trigger the skills directly by name. English and Chinese versions of every skill are included. Stated use cases are academic surveys and literature analysis, technical comparison of frameworks and tools, market and competitor research, and due diligence such as company or investment analysis. The workflow is inspired by the RhinoInsight paper on control mechanisms for model behaviour and context, and the project is MIT licensed.
https://github.com/Weizhena/Deep-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.