Figure Composer
Documentsfigure-composerFigure Composer is an Agent Skill for documents published in the companion-inc/feynman repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task needs panel planning, consistent figure layout, figure review, or final figure assembly.
QUICK START
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.
Prompt to paste
Inspect the Agent Skill at https://github.com/companion-inc/feynman/blob/HEAD/skills/figure-composer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/figure-composer, 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.
Figure Composer
Use this skill for multi-panel scientific figures.
Workflow:
- State the figure's single claim and list every data artifact that supports it.
- Draft a panel plan with labels, chart types, data sources, required annotations, and what each panel proves.
- Use
figure-stylefor each plot before composing the multi-panel layout. - Render, inspect, and revise for label collisions, axis readability, color meaning, caption fit, and data-source fidelity.
- Save the final figure, source data, generation code, caption, and provenance sidecar.
Do not invent data or hide excluded data in summaries.