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
alirezarezvani/claude-code-tresor
Claude Code Tresor is a curated repository of reusable Claude Code assets: subagent definitions, slash commands, autonomous skills and prompt templates. Version 2.7 catalogues 141 agents, split into 8 core agents and 133 subagents organised in a subagents directory across ten colour-coded team categories covering domains such as architecture, security, performance, quality, operations and design. Nineteen slash commands are grouped by purpose. Development commands scaffold project structures and components, run automated code review with security and performance checks, generate test suites to a target coverage, and produce documentation including OpenAPI output. A Tresor workflow set adds meta-prompting, todo management and context handoff between sessions, aimed at keeping long multi-session work coherent. A newer orchestration set of ten commands covers security auditing, vulnerability scanning and compliance checking, profiling and benchmarking, deploy validation, health checks and incident response, and code-health and technical-debt analysis. These orchestration commands select agents automatically based on the detected technology stack, run in three or four phases mixing parallel and sequential execution, and verify dependencies before dispatching agents in parallel so concurrent runs stay safe. Installation is a scripted one-command setup with automated updates, and the collection is also published on the Smithery skills registry. The repository ships extensive documentation, agent catalogues and cross-team collaboration guides, and a major earlier release renamed several core agents, replacing architect, code-reviewer and debugger with systems-architect, config-safety-reviewer and root-cause-analyzer. The author positions it alongside two companion repositories, a skill factory for building custom skills and a library of pre-built professional domain skill packages. The material is written in Markdown and shell, intended for solo developers and teams who want ready-made agent and command definitions rather than authoring their own. Licensed MIT.
https://github.com/alirezarezvani/claude-code-tresor
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.