microsoft/ResearchStudio

ResearchStudio: Our AI co-author, from research problem to final publication.

What it solves

ResearchStudio automates the end-to-end academic research lifecycle, addressing the difficulty of both generating viable research ideas from vague directions and producing the necessary promotional deliverables (posters, videos, blogs) once a paper is finished.

How it works

It provides a collection of AI skills that run on Claude Code and Codex. The system is split into two primary phases:

  1. Pre-paper (ResearchStudio-Idea): Uses a pipeline called IdeaSpark to transform under-specified research directions into implementable, reviewer-defensible "idea cards." This process is grounded in an empirical taxonomy derived from a large corpus of submissions to major ML conferences like ICLR, ICML, and NeurIPS.
  2. Post-paper (ResearchStudio-Reel): Converts a finished research paper PDF into a suite of publication artifacts, including a print-ready poster, a narrated walkthrough video, a bilingual blog post, and an interactive reel viewer.

Who it’s for

Researchers and academics who want to accelerate the ideation phase of their work or automate the creation of presentation materials for their published papers.

Highlights

  • IdeaSpark: End-to-end pipeline for turning vague research directions into grounded, defensible ideas.
  • Paper2Reel: Automates the "last mile" of research by generating posters, videos, and blogs from a PDF.
  • pptx2video: A tool to convert editable PowerPoint slides into narrated videos with captions and animations.
  • Conference Grounding: Ideation is based on real-world data from top-tier ML conference submissions.

Related

  • Project
    skyllwt/AutoSci

    A memory-centric AI research agent that automates the full scientific lifecycle, from literature ingestion and experiment execution to manuscript writing.

  • Project
    aiming-lab/AutoResearchClaw

    An autonomous, collaborative research pipeline that turns a research idea into a conference-ready academic paper with real citations and sandbox experiments.

  • Project
    Galaxy-Dawn/claude-scholar

    Claude Scholar is an open‑source, Claude‑Code‑compatible research assistant that provides a library of skills, agents, hooks and rules for literature management (Zotero), knowledge‑base syncing (Obsidian), experiment tracking, analysis, and scientific writing. It offers full, minimal, selective, or plugin‑based installation, supports multiple CLIs (Claude, Codex, Kimi, OpenCode), and is aimed at CS/AI researchers who want a structured, human‑centered workflow without building the tooling from scratch.

  • Project
    HKUSTDial/Supervisor-Skills

    A collection of structured AI skills and theoretical guides that distill senior academic experience into LLM prompts to assist researchers with idea evaluation, paper writing, and peer review.

  • Project
    synthetic-sciences/openscience

    OpenScience is an open‑source AI research workbench that lets users describe scientific tasks in plain language. The built‑in agent plans, searches literature, writes and runs code (Python/R/shell), executes experiments on local or remote compute, and produces a reproducible report, with every step logged. Available as a desktop app, web workspace, or CLI, it supports custom LLMs, a large library of domain‑specific skills, and extensible plugins.