Scientific Visualization
Designscientific-visualizationScientific Visualization is an Agent Skill for design published in the tsinghua-fib-lab/AgentSociety repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Publication-quality chart patterns for agentsociety-analysis Stage 4 refine — Okabe-Ito palettes, seaborn CI bands, small multiples, error bars, grayscale-safe encoding. Use when writing run-code chart scripts or reviewing chart QA failures.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/tsinghua-fib-lab/AgentSociety/blob/HEAD/extension/skills/agentsociety-analysis/v1.0.0/support/scientific-visualization/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/scientific-visualization, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Scientific Visualization (bundled support)
Active only during agentsociety-analysis explore/refine/produce. Does not replace figure contracts or harness gates.
When to read
- Writing
charts/chart_NN_*.pyviarun-code - Chart failed squint test or
validate-chart - User asks for better-looking or clearer plots
Read order
references/charts.mdreferences/chart-recipes.mdassets/chart_scaffold.reference.pyreferences/api.md
Absorbed sources (patterns only — no external deps required)
| Source | Absorbed |
|---|---|
| K-Dense scientific-visualization | Okabe-Ito, CI/error bars, multi-panel labels, grayscale test |
| seaborn | set_theme(ticks, paper, colorblind), lineplot CI, boxplot+stripplot |
| Observable Plot | Defaults-first workflow, faceting, shared scales |
| Tufte | Small multiples, chart junk removal |
| Cursor canvas | Mandatory metric titles, axis units, source in caption |
AgentSociety overrides
- English-only legend text
- matplotlib
Aggrequired - Simulation caveats — no overstated significance
- Semantic palette locked per condition across report
- PNG in
assets/required; interactive HTML optional
Quick invoke
Copy scaffold → pick recipe letter (A–G) → fill SQL/pandas → save_chart_bundle → rubric → compose-figure if needed.