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 schematicsgit 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/schematics)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/schematics"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/schematics/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/schematics"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/schematics.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 | $0.00134 | $0.02384 |
| Opus 5.5 | $0.00054 | $0.00954 |
| Sonnet 5 | $0.00027 | $0.00477 |
| Haiku 4.5 | $0.00013 | $0.00238 |
Grade A, and why
schematics 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 12d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schematics
A methodology diagram carries the paper's central idea in one glance, and it is the figure most often faked: outdated palettes, boxes that say nothing, arrows that go the wrong way, components the text never mentions. Image models draw clean diagrams with legible text when they are told the publication standards on every call and their output is judged against a rubric, not admired. This skill is that loop: describe the diagram precisely, render it under the standards, score it, and re-render once from the critique.
The medium
generate_imagewithpurpose: "schematic"is the medium for every diagram. The tool prepends the publication framing (white background, one sans-serif face, Okabe-Ito palette with one accent, one reading direction, verbatim labels, no invented parts, no figure numbers or captions inside the image) to your description, so you write the content, not the house style. It renders with Nano Banana Pro through Ace or the user's own Gemini key, or GPT Image 2 through the user's own OpenAI key; the environment line names the route.- Use
image_size: "1K"while iterating and"2K"for the accepted render of anything printed; setaspect_ratiofrom the page slot (16:9 or 21:9 for a full-width overview, 4:3 or 1:1 for a column). Score the 1K render; the 2K file is written for the manuscript and is not read back. It weighs several megabytes, and a request carrying a few of them is too large for the Ace gateway (images over 2 MB are not sent on that route at all). Passreference_pathswhen the paper's earlier figures or a cited paper's diagram set the style (up to 14 on a Gemini or OpenAI key; Ace takes one image per request). Output is raster at print resolution;\includegraphicstakes the PNG. - Do not hand-draw a schematic as TikZ, SVG, Graphviz, Mermaid or matplotlib shapes, and do not offer that as a fallback: language models draw these badly and the result reads as an unfinished figure. Exact labels are handled by giving the model the exact labels and checking them, not by switching medium.
- Plots of numbers are never image-generated (hallucinated values, repeated elements). Load the figures skill for data.
- If the environment says image generation is unavailable, stop before drawing: tell the
user once that schematics need Ace, or a Gemini or OpenAI key connected in Customize →
Models, leave an
\fbox{}placeholder with the planned caption in the manuscript if one is being written, and continue with the rest of the request.
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.
- 12d ago Changed · +28 lines · +37 tokens per session 274780e6776b
- 15d ago First seen · 126 lines · 97 tokens per session scan A 8b4b58cbb1f8
schematics is a skill published in the GitHub repository synthetic-sciences/openscience (3,808 stars, last pushed today), licensed Apache-2.0. It adds 134 tokens to every session and 2,384 once invoked, about $0.0005 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
design-skill
Use BEFORE building or restyling anything a user will see — web/mobile UIs, landing pages, dashboards, components, emails, AND creative work like Three.js/WebGL/canvas/SVG scenes, data-viz, games, and animations — to make it look intentional and polished, not generic; covers tokens, type, color, layout, motion…
composition
Create high-quality visual compositions with Jazz's createcomposition tool. Use whenever a user asks for a chart, graph, dashboard, visual explanation, interactive calculator, diagram, tracker, planner, simulation, small game, polished HTML page, or an artifact/visualization that would communicate better than prose…
beautiful-mermaid
Build publication-grade Mermaid diagrams with consistent styling and SVG-first export for manuscript assets.
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
design-md
Author/validate/export Google's DESIGN.md token spec files.