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
Ar9av/PaperOrchestra
PaperOrchestra packages the five-agent research paper writing pipeline described in the arXiv paper of the same name as a set of skills that a host coding agent reads and follows. It contains no LLM SDK code and requires no API keys: each skill is a dense SKILL.md instruction document plus reference material and deterministic local helper scripts, and all model reasoning, web search and literature lookups are delegated by instruction to the host agent, which can be Claude Code, Cursor, Antigravity, Cline, Aider or OpenCode. The pack ships seven skills. An orchestrator skill drives the run; an outline agent turns an idea, an experimental log and a template into a structured outline in JSON covering the plotting plan, the literature review plan and the section plan; a plotting agent renders figures and conceptual diagrams with an optional vision-model critique loop; a literature review agent searches for candidate references, verifies them against Semantic Scholar using fuzzy title matching and deduplication, and drafts the introduction and related work with a citation integration target; a section writing agent drafts the remaining sections in one multimodal call and builds tables from the experimental log; and a content refinement agent runs simulated peer review under strict halt rules. Two further skills reproduce the paper benchmark and its autoraters, including citation F1 and side-by-side quality scoring. The helper scripts are purely local and offline: JSON schema validation, Levenshtein matching, BibTeX formatting, deduplication, LaTeX sanity checks and coverage gates. An optional aggregator skill reconstructs the required idea and experimental log inputs from scattered coding agent history. It targets researchers who already work inside a coding agent and want a reproducible pipeline from raw material to a submission-ready LaTeX paper.
https://github.com/Ar9av/PaperOrchestra
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.