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 xuzhougeng/ScientificFigureLibrary --skill figure-descriptiongit clone --depth 1 https://github.com/xuzhougeng/ScientificFigureLibraryWrote 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/xuzhougeng/scientificfigurelibrary/figure-description)<a href="https://agentmods.dev/skills/xuzhougeng/scientificfigurelibrary/figure-description"><img src="https://agentmods.dev/badge/skills/xuzhougeng/scientificfigurelibrary/figure-description/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/xuzhougeng/scientificfigurelibrary/figure-description"><img src="https://agentmods.dev/badge/skills/xuzhougeng/scientificfigurelibrary/figure-description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Privilege Escalation · line 14 Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
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 | $0.00057 | $0.00764 |
| Opus 5 | $0.00028 | $0.00382 |
| Sonnet 5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
figure-description 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 4d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figure Description
Help a researcher choose a template and clarify what they want to draw. Write useful, concrete prose, not an execution manual or a field inventory. Default to Chinese with necessary English scientific terms.
Inspect and distinguish evidence
Inspect the actual figure and supplied code/data as text. Use the user's information rather than inventing samples, genes, diseases, statistics or results. A screenshot-only scaffold is not a reproduced analysis.
If a source link is provided, use available Host tools to verify that it corresponds to this figure/panel and read relevant legend/results, not necessarily the whole paper. A tutorial is not a paper. If unavailable or mismatched, say so; do not invent source findings or bypass access restrictions.
If no source/background was provided, ask once whether the user has a link, legend or experimental context; explain that skipping is allowed. Wait for an answer. If the user already says none or skips, proceed without repeating the question or searching for a speculative original. Distinguish user-provided context, read source facts and generic applicability inference in existing provenance/agent notes. Never label inferred scenarios as original results.
Write separate fields
- description: a concise paragraph explaining the research/visualization need and the relationship this plot displays.
- application: normally two or three specific use cases, each one or two sentences explaining the biological context, comparison and desired observation. Use Markdown bullets or subheadings as useful. Make the scientific question concrete, not just a chart name.
- scientificQuestion: a short core question for search/Agent use; its meaning must also appear naturally in description/application, not as a third repeated long section.
- dataProfile: a concise factual data-shape description. Name columns/ranges only if actually inspected; do not create a data-preparation tutorial.
- visualProfile: observed axes, encodings, panel structure and labels, separately from applicability.
What ships with it
3 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.
- 4d ago First seen · 37 lines · 57 tokens per session scan A 0e1ddc60460e
figure-description is a skill published in the GitHub repository xuzhougeng/ScientificFigureLibrary (56 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 764 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
svg-editor
Open and surgically edit SVG scientific figures in the SVG Editor MCP App. Use when the user wants to change text, colors, fonts, positions, legends, or panel letters in an existing SVG by hand, or by selecting elements and instructing the host assistant.
agent-figure-gallery
Query visual scientific figure references, show candidates for human preference selection, export selected reference bundles, and guide plotting agents from human-selected visual examples to code action.
cnsplots
Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise physical figure dimensions…
bio-differential-expression-batch-correction
Handles batch effects in bulk RNA-seq via design-matrix inclusion (the correct path for DE), ComBat/ComBat-seq for visualization, SVA for unknown latent factors, RUVSeq for negative-control-gene-anchored unwanted variation, and limma::removeBatchEffect for plotting only. Encodes the Nygaard 2016 cardinal sin against…
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
admet_genetic
ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and write candidate triage reports.