microsoft/ResearchStudio

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

What it solves

ResearchStudio automates the tedious and complex stages of the academic research lifecycle, specifically the "pre-paper" phase of generating viable research ideas and the "post-paper" phase of creating promotional materials for a publication.

How it works

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

  1. ResearchStudio-Idea (IdeaSpark): Transforms a vague research direction into a concrete, implementable, and reviewer-defensible "idea card." It does this by grounding the process in an empirical taxonomy derived from a large corpus of submissions to major ML conferences like ICLR, ICML, and NeurIPS.
  2. ResearchStudio-Reel: Takes a finished research paper PDF and automatically generates a suite of deliverables, 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 in the machine learning and AI space who want to accelerate the ideation process or automate the creation of publication artifacts.

Highlights

  • End-to-end ideation: Converts under-specified directions into grounded research ideas.
  • Automated publication assets: Generates posters, videos, and blogs from a single PDF.
  • Conference-grounded: Uses data from top-tier ML conferences to ensure idea quality.
  • Interactive presentation: Includes a specialized interactive reel viewer for presenting research.

Related

  • Project
    Imbad0202/academic-research-skills-codex

    ARS‑Codex is a Codex‑native plugin that bundles the full Academic Research Skills workflow (question refinement, literature‑review planning, paper drafting, peer‑review simulation, and end‑to‑end research‑to‑paper pipelines). Install it via the Codex marketplace or directly as a skill, then invoke `$academic‑research‑suite` (or `ars‑*` aliases) to let the router pick the appropriate workflow. The repo provides setup docs, architecture notes, and a full‑runtime adapter (disabled by default). It is an AI‑driven research assistant, not a generic tutorial list.

  • Project
    pedrohcgs/claude-code-my-workflow

    A ready-to-fork foundation for AI-assisted academic work that uses specialized agents and quality gates to automate the creation and review of papers, slides, and data analysis.

  • Project
    luwill/research-skills

    A collection of Claude Code skills designed to automate academic research workflows, including exhaustive literature retrieval, verified proposal writing, and high-fidelity slide generation.

  • Project
    Yuan1z0825/nature-skills

    A library of reusable research skills for AI agents to automate high-impact academic workflows, from paper reading and Nature-style polishing to peer review simulation and patent drafting.

  • Project
    claesbackman/AI-research-feedback

    A collection of Claude Code skills that provide multi-agent academic reviews for research papers, grant proposals, and pre-analysis plans, including paper-code reproducibility checks.