ModelViz Skill
A skill that picks a scientific chart from nearly 100 templates for CSV or Excel data and outputs PNG, SVG, PDF and Python code.
- 294 ★ on the repository
- Last commit
Extended access
Why this level
- Runs adapted Python template code and installs dependencies through pip.
- Reads and processes your data files.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/modelviz-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs adapted Python template code and installs dependencies through pip.
- Reads and processes your data files.
This is third-party code. Review the repository files before installing.
What it does
ModelViz Skill, a skill for Claude Code and Codex, builds scientific charts for mathematical modeling papers and articles. The agent reads `SKILL.md`, analyzes data in CSV, XLSX or XLS and the user's goal (trend, comparison, distribution, correlation), selects a template from the library in `templates/` and maps columns. The output is a PNG, SVG or PDF image, adapted Python code and a quality report. The check is twofold: a technical run and a visual inspection. Dependencies of the chosen template are installed only after selection and within tight limits on package name, package count and rounds. Fixes after failures are capped.
Who it is for. Students and researchers preparing charts for mathematical modeling, coursework and papers who do not want to pick styling by hand.
Good fit when
- `data.xlsx` holds data by region and the differences should be shown without 3D charts.
- A production trend and growth rate by year are styled for the body of a paper.
- Correlations between variables are shown as a heatmap with readable labels.
- A reproducible Python script and a check report should come alongside the image.
Not a fit when
- It is enough to explain a mathematical concept without a chart.
- There is no data, yet the chart must rest on real values.
- You need a chart type that is missing from the template library.
Example request
Use ModelViz on `data.xlsx`: compare indicators by region, highlight anomalous regions and avoid 3D charts.Limitations
The template library is limited: if no suitable candidate exists the skill should stop and ask rather than invent one. Large tables enter the model context as a sample, so one cannot claim the model saw all the data. In complex Excel workbooks the sheet is specified explicitly. Some templates need system components that `pip` cannot install. Auto-repair is capped and success is not guaranteed. The visual check works only if the host passes the image to the model. The repository has no license file and the README gives no install command, so the skill is copied manually.
How to disable. Delete the skill directory from the agent's skills folder. Created charts and code sit in `outputs/` and `workspace/`, so remove them separately.
FAQ
What data does the skill accept?
CSV, XLSX and XLS files. For complex Excel workbooks specify the sheet explicitly.
What do I get as output?
An image in PNG, SVG or PDF, adapted Python code and a quality check report. Charts go to `outputs/`, while code and dependency reports go to `workspace/`.
Does the skill install packages itself?
Only those the chosen template needs and within limits. It does not run install commands from templates, and URLs, Git addresses and local paths never enter the package list.
Is it suitable for papers, not only competitions?
Yes. The README names both mathematical modeling and scientific writing. Selection leans toward strict, low-saturation scientific layouts.
What if no suitable template exists?
The skill stops and asks a clarifying question or explains why instead of inventing a chart. This is a template library limit named in the README.
Discussion
No questions or reviews yet.
Related
SkillsSciPilot Figure
scipilot-figure-skill
A scientific visualization advisor skill: it profiles the data and picks a chart for the argument first, then renders it to journal-grade quality
A skill for scientific figures to Nature, Cell and Science standards: 29 figure types, data checks and vector PDF output.
A data visualization skill for agents: turns data into polished interactive HTML charts and full reports with one visual language
A three-stage workflow for math modeling tasks: analysis and model choice, Python or MATLAB computation, and paper assembly in Word or LaTeX
VisActor Skills: charts, dashboards and posters
VisActor Skills
Nine VisActor skills: business charts, data stories, map dashboards and posters, all assembled by your agent
A Claude skill that analyzes an uploaded CSV without asking questions: statistics, missing values, correlations and charts built with pandas and matplotlib
README in short
The skill runs in stages: understanding the goal, selecting a template, adapting code, running and checking quality. The host model must first read `SKILL.md` and must not bypass the tools.