prismatica
Skill2 starsChanged 13 days agoMITView on GitHub
Unified scientific visualization workflow combining paper-colors with scientific-figure-making. Use for research data charts, experimental panels, method overviews, teasers, palettes, final-size layout and vector export. Coordinates the bundled modules without changing experimental results.
In this repository2 other files it gives its agents.
- paper-colorsSkill
- scientific-figure-makingSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Read scientific-figure-making for the common layout, data-integrity and export workflow.
- Distinctive: line 22
Read paper-colors when choosing, changing or checking colors.
- Very specific: line 63
Keep the sibling folder names unchanged: historical example imports rely on that layout.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prismatica
Coordinate the two bundled sibling skills. They are installed together by the repository installer; do not copy this entrypoint alone. Read only the references relevant to the requested output.
Combined workflow
- Read scientific-figure-making for the common layout, data-integrity and export workflow. Establish the intended claim, input data/assets, venue dimensions and deliverable type.
- Read paper-colors when choosing, changing or checking colors. Reuse the project's registered theme or exported palette; color-book data stays in the user's own data directory. Never infer a book code from an approximate screenshot or recollection.
- Choose the composition below. Data experiments use manuscript-sized charts; a method overview uses actual components; teasers use actual result assets.
- Apply colors by semantic role. Preserve run/item pairing, statistical units, uncertainty definitions, category order, metric directions and all results. A brand palette is not automatically a suitable multi-series data palette.
- Export editable SVG/PDF plus PNG. Inspect the result at insertion size and check grayscale/series distinguishability. Explain remaining limitations.
- Deliver source code, provenance and the definition of every uncertainty interval. Distinguish synthetic fixtures, local demo experiments, published numerical redraws and original paper excerpts.
Composition routes
| Output | Reference |
| CS training, alignment, diffusion evaluation | Paper data |
| Ablations, condition conflicts, sampler quality/cost | Paper comparisons |
| Biological data: OncoPrint, spatial omics, annotated trees, genomic Circos, Sashimi | Bioinformatics |
| Set membership, shared cores, petal summaries, UpSet, Jaccard | Set overlap |
| All statistical/complex charts: clustering, correlation, Sankey, spatial, survival, ROC/PR | Full catalog |
| Method overview / central loop / mechanism details | Overview |
| Benchmark radial bars, iterations and correlation matrices | Benchmark figures |
| Model internals and diagnostic compositions | Analysis, diagnostics |
| Image-led multimodal, video, 3D and robotics teasers | CS editorial, sequences |
| Published multimodal and diffusion reference layouts | Multimodal, recent |
| Atmospheric warm–cool composition and selective detail | Landscape aesthetic reference |
| Architectural framing, material contrast, light and fine connections | Architectural aesthetic reference |
| Generative visual systems: state colors, choreographed light, discrete form | Gamma, SKALAR, Pointillisme studies |
| Optional Nature profile | Nature |
For existing figures, preserve the project's code-native representation and data loading. The galleries are reference implementations, not a reason to replace real inputs with fixture data. Keep original author/source attribution when using published examples. Never fabricate intermediate frames or significance.
Color and layout handoff
Keep the sibling folder names unchanged: historical example imports rely on
that layout. paper-colors owns color selection/export and scientific-figure-making
owns composition/export. Their independent entrypoints remain usable. Refer to
the skill scripts by their resolved installed paths rather than a developer's
local absolute paths.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

