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 fmschulz/omics-skills --skill beautiful-data-vizgit clone --depth 1 https://github.com/fmschulz/omics-skillsWrote 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/fmschulz/omics-skills/beautiful-data-viz)<a href="https://agentmods.dev/skills/fmschulz/omics-skills/beautiful-data-viz"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/beautiful-data-viz/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/fmschulz/omics-skills/beautiful-data-viz"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/beautiful-data-viz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Memory Poisoning · line 37 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00037 | $0.01410 |
| Opus 5 | $0.00018 | $0.00705 |
| Sonnet 5 | $0.00007 | $0.00282 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
beautiful-data-viz 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beautiful Data Viz
Create polished, publication-ready visualizations in Python/Jupyter with strong typography, clean layout, accessible color choices, and high data-ink. The default style is restrained: show the data, remove non-data decoration, label directly when possible, and add only the context needed to interpret the finding.
Instructions
- Clarify the message, comparison context, audience, and medium (notebook/paper/slides). If the data is one or two values, prefer a sentence; if it is a short lookup list, prefer a table.
- Choose the simplest chart type that answers the question. Prefer horizontal bars for ranked categories, small multiples for >4 series or dual-axis temptations, slopegraphs for before/after changes, and sparklines for compact trend context.
- Start gray-first: neutral series by default, one accent for the finding, and no rainbow palettes. Select an appropriate palette type only when color is carrying real information.
- Remove chart junk before styling: no 3D, pie charts only if explicitly requested, no decorative borders, no heavy grids, no gradient fills, no dual y-axes.
- Use direct labels instead of legends when series count and space allow. Keep legends only when direct labels would collide or obscure data.
- For manuscript/paper figures, do not add in-plot titles or subtitles; use axis labels, legends/direct labels, panel letters, and the manuscript caption instead.
- Place the figure caption/legend text BELOW the figure, directly under it — never above. In a notebook this means the figure (code) cell comes first and the caption (markdown) cell immediately follows it; in a document the caption goes beneath the image. A reader sees the figure, then its legend. (Journal convention: legends sit below the figure.)
- Apply the shared style helpers, then build the plot.
- Validate readability, accessibility, and export quality at the target size.
- Use
pixi.tomlfor a project figure environment, or scripts/export_fixture.py — a PEP 723 script with exact version pins — for a reproducible smoke test. Annotation helpers inherit the active light/dark text color unless an explicit color is supplied.
What ships with it
8 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.
- 3d ago Changed 7cfab0efb94e
- 9d ago First seen · 114 lines · 37 tokens per session scan A 59c704e5bc5d
beautiful-data-viz is a skill published in the GitHub repository fmschulz/omics-skills (7 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 1,410 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly…
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when…
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…
statistical-analysis
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…
tamarind
Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design…