figure-composer

Bundled with dsh-science-workbench — adapted from Anthropic Claude Science's built-in skills (extracted via the AcademicForge project), Apache-2.0.

Integration in this workbench: compose publication-grade multi-panel figures as bio_run_cell output. The helper kernel.py ships beside this SKILL.md — copy it into the project's code/ once: cp <this-skill-dir>/kernel.py <project>/code/figure-composer-kernel.py, then in each cell exec(open("code/figure-composer-kernel.py").read()). Run the workflow below one panel at a time; figure-style (also bundled) is loaded alongside.

Figure Composer — narrative → panels → compose → adversarial loop

Compose ONE publication-grade multi-panel figure: turn a one-sentence claim plus data files into an outline, render each panel, tile them into a composite, and harden it through an adversarial self-review loop.

Setup (any agent, no API key)

This is a pure skill — kernel.py is deterministic Python (PIL geometry plus schema/prompt builders) and you (the base model) do all the reasoning: reverse-engineering an outline from a figure, rendering panels, and the adversarial composite review. There is no host runtime and no LLM API. Load the helpers once per session in a Python cell:

exec(open("figure-composer/kernel.py").read())

Nothing auto-loads it outside Claude Science. Then call the helpers (panel_task, compose_figure, compose_crops, composite_review_task, derive_outline_prompt, …) directly; if one raises NameError, you have not exec'd kernel.py. Dependencies: pip install pillow matplotlib.

Step 0. Load figure-style alongside this skill — that is the design rules (and apply_figure_style() + helpers). You need it in context to write the outline, render the panels, and review the composite. Each panel is rendered against those same rules — whether you draw it yourself or hand it to a sub-agent (see §2), the maker loads figure-style first.