synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.
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 skills add synthetic-sciences/openscience --skill paper-writinggit clone --depth 1 https://github.com/synthetic-sciences/openscienceWrote 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/synthetic-sciences/openscience/paper-writing)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/paper-writing"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/paper-writing/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/synthetic-sciences/openscience/paper-writing"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/paper-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00102 | $0.02076 |
| Opus 5.5 | $0.00041 | $0.00830 |
| Sonnet 5.5 | $0.00020 | $0.00415 |
| Haiku 4.5 | $0.00010 | $0.00208 |
Grade A, and why
paper-writing 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper writing
A paper is an argument with evidence attached, written for a reader who is busy and skeptical. The draft succeeds when a reviewer can state the claim, the evidence, and the limits after one read, and cannot find a sentence the results do not support.
Non-negotiables
- Write the file, not an outline in chat. Create or edit the manuscript in the working
folder (
paper.tex,paper.md, or the user's file) and link it. An outline in chat gives the user nothing to render or send. - Every claim traces to a result or a source. Numbers come from the project's outputs (tables, logs, tracked runs), quoted with their units, precision and conditions. Prior work is cited only after reading it; the citations skill resolves and verifies the references, never memory.
- Prose, not lists. Sections are paragraphs, each with one point stated in its first sentence. Bullets belong in supplementary checklists, not in the body.
- Preserve what exists. When revising a manuscript, keep its claims, structure, figures and voice unless the user asked for those to change. Improve the sentence, not the science, unless the science is wrong, and then say so.
- State the limits where the claim is. Scope, sample, assumptions and failure cases go in the results and discussion, not only in a limitations paragraph at the end.
- Match the venue. Length, section order, abstract form, reference style and figure
rules come from the target;
references/journals-formatting.mdand the style files below carry the common ones.
Workflow
- Fix the target: venue or document type, length, audience, deadline, template.
- Inventory the evidence: results, figures, data, methods, prior drafts, notes.
- Write the argument in one paragraph before the sections.
- Draft sections in evidence order: methods, results, discussion, introduction, abstract.
- Verify every number and citation against its source; compile; read the PDF yourself.
- Hand over with the open questions listed.
What ships with it
11 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.
- assets/report-template.tex 15 KB
- assets/scientific_report.sty 16 KB
- references/cell-press-style.md 14 KB
- references/figures-tables.md 28 KB
- references/imrad-structure.md 26 KB
- references/journals-formatting.md 18 KB
- references/medical-journal-styles.md 16 KB
- references/nature-science-style.md 13 KB
- references/reporting-guidelines.md 25 KB
- references/writing-principles.md 27 KB
- scripts/validate_format.py 9.2 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.
- 1mo ago Changed · +21 lines c07323d94237
- 1mo ago First seen · 126 lines · 102 tokens per session scan A e38417b7a54a
paper-writing is a skill published in the GitHub repository synthetic-sciences/openscience (4,025 stars, last pushed today), licensed Apache-2.0. It adds 102 tokens to every session and 2,076 once invoked, about $0.0004 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 2026-09-14.
Other skills, from other repositories
songsee
Audio spectrograms/features (mel, chroma, MFCC) via CLI.
arxiv
Search arXiv papers by keyword, author, category, or ID.
research-paper-writing
Write ML papers for NeurIPS/ICML/ICLR: design→submit.
paper-revision-author
Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.
paper-plot-stub
Plot a results CSV (x, ybaseline, yours) as a two-line matplotlib chart and write a PDF. Demo-only.
knowledge-extension-ecosystem-lsp-code-intelligence
A codebase guide to LSP, the standard protocol behind editor features such as symbol queries, file diagnostics, and language-aware code information.