ResearchStudio: a collection of skills covering the entire research lifecycle

Microsoft released ResearchStudio, an open-source collection of research-lifecycle skills that run on Claude Code and Codex, with the pre-paper half ResearchStudio-Idea released 2026-07-03 and the post-paper half ResearchStudio-Reel released 2026-07-08. ResearchStudio-Idea turns an under-specified research direction into an implementable idea grounded in a taxonomy induced from ICLR, ICML and NeurIPS submissions, while ResearchStudio-Reel converts a finished paper PDF into a print-ready poster, narrated walkthrough video, bilingual blog post and interactive reel viewer. The project recommends model versions claude-opus-4.6 or gpt-5.5, installs via install.sh or an npx installer, and adds pptx2video, open-sourced 2026-09-15, to turn editable PowerPoint slides into narrated videos.

Our AI co-author, from research problem to final publication. ResearchStudio is a collection of skills covering the entire research lifecycle — from an under-specified research direction to a published paper. The skills run on Claude Code https://docs.claude.com/en/docs/claude-code/overview and Codex https://developers.openai.com/codex . <sub Presenting an all-in-one interactive reel.</sub <sub IdeaSpark runs the full pipeline end-to-end.</sub - 2026-09-15 release pptx2video https://github.com/ai-nuts/pptx2video is now open source — turn editable PowerPoint slides into narrated videos with animations and captions. Use it as a skill or run the CLI without an LLM. - 2026-08-25 release Trending Paper https://microsoft.github.io/ResearchStudio/trending-paper is released — meet the trending research through ResearchStudio Reels. - 2026-08-13 feature IdeaSpark https://github.com/microsoft/ResearchStudio/blob/main/ResearchStudio-Idea keeps the whole user query — the user query is persisted verbatim and read by every phase that reasons about intent; papers named in it without a link are resolved and deep-read; and a stated solution direction reaches idea selection, which must record whether it followed or departed from that direction, and why. - 2026-07-08 release ResearchStudio-Reel https://github.com/microsoft/ResearchStudio/blob/main/ResearchStudio-Reel is released — the post-paper half: turn a finished paper PDF into the artifacts a publication needs — a print-ready poster, a narrated walkthrough video, a bilingual blog post, and an interactive reel viewer. - 2026-07-03 release ResearchStudio-Idea https://github.com/microsoft/ResearchStudio/blob/main/ResearchStudio-Idea is released — the pre-paper half: turn an under-specified research direction into a reviewer-defensible, implementable idea, grounded in an empirical taxonomy induced from a large-scale corpus of ICLR / ICML / NeurIPS submissions. We recommend creating an isolated environment first, using either conda or uv: Option 1 — conda: conda create -n researchstudio "python =3.10" -y conda activate researchstudio Option 2 — uv: uv venv --python 3.10 source .venv/bin/activate For Windows PowerShell: .venv\Scripts\Activate.ps1 Then pick one of the two install paths below: Option 1 — clone and run install.sh installs native tools, Python deps, symlinks the skills from a local clone and scaffolds .env : git clone https://github.com/microsoft/ResearchStudio.git && cd ResearchStudio bash install.sh Option 2 — interactive npx installer choose which plugins to install, enter your API keys when prompted, and it writes .env : npx github:microsoft/ResearchStudio For usage, see Idea https://github.com/microsoft/ResearchStudio/blob/main/ResearchStudio-Idea/ usage and Reel https://github.com/microsoft/ResearchStudio/blob/main/ResearchStudio-Reel/ usage . We recommend using these skills with model versions claude-opus-4.6 or gpt-5.5 . If ResearchStudio helps your research workflow, please cite: @article{xiao2026researchstudioreel, title = {ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog}, author = {Lingao Xiao and Yalun Dai and Yangyu Huang and Qihao Zhao and Wenshan Wu and Hugo He and Ruishuo Chen and Jin Jiang and Qianli Ma and Jiahuan Zhang and Xin Zhang and Ying Xin and Yang Ou and Yan Xia and Scarlett Li and Longbo Huang and Zhipeng Zhang and Yang He and Yap Kim Hui and Yan Lu}, journal = {arXiv preprint arXiv:2607.04438}, year = {2026}, url = {https://arxiv.org/abs/2607.04438} } @article{zhao2026researchstudioidea, title = {ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes}, author = {Qihao Zhao and Yangyu Huang and Yalun Dai and Lingao Xiao and Jianjun Gao and Xin Zhang and Wenshan Wu and Scarlett Li and Yang He and Yan Lu and Yap Kim Hui}, journal = {arXiv preprint arXiv:2607.04439}, year = {2026}, url = {https://arxiv.org/abs/2607.04439} }