ResearchStudio is a collection of skills that helps researchers develop an initial research direction into a paper and its related publication materials. It is used with Claude Code and Codex to create outputs such as papers, posters, videos, blogs, and reels. The catalogue entries are its own workflow skills for different stages of the research lifecycle.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/ResearchStudionpx agentmods add skills/microsoft/researchstudio/paper2videoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/researchstudio/paper2video)<a href="https://agentmods.dev/skills/microsoft/researchstudio/paper2video"><img src="https://agentmods.dev/badge/skills/microsoft/researchstudio/paper2video/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/researchstudio/paper2video"><img src="https://agentmods.dev/badge/skills/microsoft/researchstudio/paper2video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 502 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium MCP Rug Pull · line 117 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 118 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00157 | $0.06731 |
| Opus 5.5 | $0.00063 | $0.02692 |
| Sonnet 5.5 | $0.00031 | $0.01346 |
| Haiku 4.5 | $0.00016 | $0.00673 |
Grade A, and why
paper2video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper2video - paper/assets -> ppt-master deck -> pptx2video render -> narrated MP4
paper2video is a thin orchestrator with exactly one supported path. It does
not author slides itself, does not synthesize audio itself, does not
composite video itself, and does not gate QA itself. It resolves inputs and
one shared trigger decision, then fully delegates:
paper.pdf
-> skills/paper2assets/scripts/build_package.py (shared package)
-> assets/meta/paper_spec.md + assets/meta/narration.json
-> ppt_options_contract.py resolve-ppt-trigger (ONE trigger decision)
-> installed ppt-master skill (full workflow, receives the trigger)
-> installed pptx2video skill / CLI `bootstrap` then `render` (full workflow, receives the trigger)
-> ppt_stage_validator.py audit-final-pptx-trigger (proves the handoff held)
-> video.mp4, video_no_subtitles.mp4, video.pptx
There is only one route. An earlier version of this skill had a second,
self-implemented "Route A" that called private narration, duration, and
visual-cue scripts and invoked python -m pptx2video.render_video /
pptx2video.build_timeline / pptx2video.check_video_package as if they were
importable submodules of the installed public package. Those modules do not
exist at that import path in the public pptx2video CLI; the entry
points are the pptx2video render, pptx2video doctor, and pptx2video bootstrap subcommands. Do not recreate that shortcut. Do not hand-assemble a
narration script, a visual-cue file, or a "simplified" render pipeline that
skips the installed pptx2video skill. Do not invoke any private submodule
path under pptx2video.*. Every render goes through /pptx2video (the
installed skill) or the exact pptx2video render CLI invocation in Step 5;
there is no lower-effort fallback for a rushed or low-context session.
Why full delegation is mandatory
pptx2video render is not a smoke-test wrapper. Its own CLI (cli.py
_render()) always runs the QA pass and always writes
assets/meta/reports/video_qa_report.json; there is no --no-qa flag and no
way to skip the check itself. A hand-rolled call into an internal module could
skip that gate entirely, which is why every render goes through the Step 5
command.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 547 lines · 157 tokens per session scan A ec80baf41b35
paper2video is a skill published in the GitHub repository microsoft/ResearchStudio (3,378 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 6,731 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sciatlas-idea-evaluate
Use only the current SciAtlas automated review workflow (reviewpipeline) to take a novice user from zero setup to a final automated review of a research idea or paper, including setup, registration guidance, workflow configuration, retrieval, artifact reading, and synthesis. Trigger when the user asks whether an idea…
sciatlas-literature-review
Use only the current SciAtlas literature-review workflow (literaturereviewpipeline) to take a novice user from zero setup to a final evidence-grounded survey outline, paper map, or literature review, including setup, registration guidance, workflow configuration, SciAtlas backend retrieval, artifact reading, and…
sciatlas-idea-grounding
Use only SciAtlas search-papers to take a novice user from zero setup to final prior-art grounding for a research idea, including setup, registration guidance, configuration, retrieval, artifact reading, and synthesis. Trigger when the user gives an idea and asks for similar work, differentiation evidence, related…
sciatlas-trend-report
Use only SciAtlas search-papers to take a novice user from zero setup to a final timeline-oriented research trend report, including setup, registration guidance, configuration, retrieval, artifact reading, and synthesis. Trigger when the user asks for topic history, field evolution, recent trends, representative…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…