Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/microsoft/researchstudio/paper2assetsnpx skills add microsoft/ResearchStudio --skill paper2assetsgit clone --depth 1 https://github.com/microsoft/ResearchStudioWhat 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 | $0.00223 | $0.15604 |
| Opus 5 | $0.00112 | $0.07802 |
| Sonnet 5 | $0.00045 | $0.03121 |
| Haiku 4.5 | $0.00022 | $0.01560 |
Grade A, and why
paper2assets 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 3d 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 — 734 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper2assets — paper PDF → reusable assets
One paper PDF in, a single <outdir>/ of poster-agnostic assets out, ready for any downstream renderer.
Output Contract (the shared layout every paper2* skill follows)
paper2assets defines the on-disk shape of every deliverable bundle in the pipeline. paper2poster, html2pptx, paper2blog, paper2video, and paper2reel all read from and write to a bundle laid out this way — a teammate adding or changing a downstream skill conforms to this contract.
Rules
- The bundle directory is named after the paper.
- The bundle's top level holds ONLY that skill's deliverable FILES — no loose intermediates, and as few folders as possible.
- Every dependency and intermediate (figures, logos, qr, audio, fonts, captions, slides, the spec / json / txt) lives under one
assets/container.
Layout
<paper-name>/
|-- <deliverable files> # see the per-skill table below
|-- manifest.json # package index (root-relative paths); the one allowed top-level non-deliverable
`-- assets/
|-- figures/ logos/ qr/ audio/ fonts/ # runtime deps the deliverables reference
`-- meta/ # build intermediates
|-- paper_spec.md sections.json narration.json
`-- captions.json figures.json metadata.json text.txt
Deliverables reference assets with root-relative src paths -- assets/figures/..., assets/logos/..., assets/qr/..., assets/audio/... -- so the bundle is self-contained and movable (no absolute paths leak in). The path / file fields in figures.json, fetch_logos.py, and make_qr.py output already carry the assets/ prefix; downstream drops them into src verbatim.
Per-skill deliverables (top-level FILES):
| Skill | Top-level deliverable files |
|---|---|
| paper2assets | manifest.json (+ the whole assets/ package) |
| paper2poster | poster.html, poster.pdf, poster.png, poster.pptx |
| paper2blog | blog_zh.docx, blog_en.docx |
| paper2video | video.mp4, video_no_subtitles.mp4 |
| paper2reel | reel.html |
What ships with it
13 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.
- README.md 5.0 KB
- scripts/build_package.py 23 KB runs code
- scripts/crop_figure.py 39 KB runs code
- scripts/extract_pdf.py 48 KB runs code
- scripts/fetch_conf_logo.py 9.9 KB runs code
- scripts/fetch_logos.py 54 KB runs code
- scripts/figure_semantics.py 32 KB runs code
- scripts/make_qr.py 12 KB runs code
- scripts/source_figures.py 25 KB runs code
- scripts/utils/__init__.py 0 B runs code
- scripts/utils/layout.py 3.5 KB runs code
- scripts/utils/logo_quality.py 12 KB runs code
- scripts/utils/logo_trim.py 6.4 KB runs code
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.
- 3d ago First seen · 734 lines · 0 tokens per session scan A c6baee00cc58
paper2assets is a skill published in the GitHub repository microsoft/ResearchStudio (2,614 stars, last pushed 4d ago), licensed MIT. It adds 223 tokens to every session and 15,604 once invoked, about $0.0011 per session on Opus 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
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
document-gen-resilient
Multi-path document generation with tool checks, Unicode handling, and Python fallbacks.
pdf-explore
Read, extract, and cross-check content across scientific PDFs. Use when a task needs methods, figures, tables, citations, accessions, or claims from multiple places in one or more papers.
make-resume
中文可编辑简历制作技能：根据用户经历选择或复刻模板，生成可编辑 HTML 简历并提供 PDF 导出；当用户输入“/make-resume”或要求制作、修改、复刻简历文件时使用。.
paper-reader
Use when user asks to "read paper", "analyze paper", "summarize paper", "读论文", "分析文献", "帮我看一下这篇paper", "论文笔记", or provides a PDF file that appears to be an academic paper. Specialized for CV/DL papers. Also supports Zotero integration: "读一下这篇论文 ...", "快速看一下这篇论文 ...", "批判性分析这篇论文 ...", "读一下 Zotero 里的 XXX", "批量读一下 Zotero…
decrypt4pdf
对加密的 PDF 文件进行解密。当用户提到 PDF 解密、解除 PDF 密码、解 PDF 时使用。.