Plot Is All You Need skill
plot-is-all-you-need
Plot Is All You Need teaches an agent to draw scientific figures from gallery samples instead of a style description in words
- 291 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill draws figures and writes Python scripts; trust them after review.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/plot-is-all-you-needDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill draws figures and writes Python scripts; trust them after review.
This is third-party code. Review the repository files before installing.
What it does
A skill with a gallery of 95 figures: 14 drawn by the author with code and 81 taken from open-access papers. Each sample has a review card. The agent picks candidates for your data, builds 4–6 drafts and assembles them into a sample sheet to choose from. You can name a pick ("B" or "layout B with the colours of E") and the agent redraws the figure on your data, then shows it beside the sample for acceptance. The gallery is editable: removed samples drop out of the choice and added ones shift the taste.
Who it is for. Researchers and graduate students who have data but no time to polish figures to journal quality.
Good fit when
- A paper needs a figure and you cannot describe the target style in words.
- You want the layout of one sample and the palette of another.
- A figure should be compared with a sample before journal submission.
- A team wants a shared gallery of preferred styles.
Not a fit when
- You need an interactive dashboard rather than a static publication figure.
- The licences of samples from open papers do not suit your reuse.
- The environment has no Python: figures are drawn with it.
Example request
Draw a model results figure from this data, show 5 styling options from the gallery and wait for my pick.Limitations
Installation clones the repository into a skills directory and installs dependencies with `pip install -r requirements.txt`, so Python is required. 81 samples come from open-access papers, their terms are in `THIRD_PARTY_NOTICES.md` and should be read before publishing. Output quality depends on the taste of the gallery and on the model's ability to read images. Sample descriptions are mostly in Chinese, and an English README exists.
How to disable. Delete the `plot-is-all-you-need` directory from `~/.claude/skills` or `~/.agents/skills`. Remove Python dependencies separately.
FAQ
How does the sample sheet differ from the gallery?
It holds drafts on your data: the agent draws your figure in several styles and notes which sample each follows.
What if I have no data yet?
The agent shows gallery samples as they are so you can choose a direction.
How do I steer the agent after choosing?
Name a pick or a mix, for example "B layout and E palette". The agent redraws and shows the result beside the sample.
Where do gallery samples come from?
14 samples were drawn by the author with code and 81 come from open-access papers.
Can I use Codex?
Yes. Clone the repository into `~/.agents/skills/` and invoke `$plot-is-all-you-need`.
Discussion
No questions or reviews yet.
Related
SkillsA skill that builds scientific figures from a table: it offers 2–3 chart candidates, assembles panels and checks image reuse.
A plugin that teaches agents to make clear, honest charts and checks each before you see it: takeaway title, axes, labels, colors.
A scientific plotting skill: from data checks and statistics to R and Python charts, curated palettes and journal-ready export.
A skill for scientific figures to Nature, Cell and Science standards: 29 figure types, data checks and vector PDF output.
A Python and R skill for publication figures with a contract, layout QA and independent export, plus the FigureForge editor
A scientific graphics skill with 148 chart templates, 196 SVG architecture assets and export to editable PowerPoint
README in short
A skill with a 95-sample gallery where taste is set by pictures and style rules give way to choosing by sight.