OpenParable
Skip to content
← Back to skills

Scientific Visualization

Design
scientific-visualization

Scientific 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.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
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_*.py via run-code
  • Chart failed squint test or validate-chart
  • User asks for better-looking or clearer plots

Read order

  1. references/charts.md
  2. references/chart-recipes.md
  3. assets/chart_scaffold.reference.py
  4. references/api.md

Absorbed sources (patterns only — no external deps required)

SourceAbsorbed
K-Dense scientific-visualizationOkabe-Ito, CI/error bars, multi-panel labels, grayscale test
seabornset_theme(ticks, paper, colorblind), lineplot CI, boxplot+stripplot
Observable PlotDefaults-first workflow, faceting, shared scales
TufteSmall multiples, chart junk removal
Cursor canvasMandatory metric titles, axis units, source in caption

AgentSociety overrides

  • English-only legend text
  • matplotlib Agg required
  • 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.