figure-composer

Figure Composer — narrative → panels → compose → adversarial loop

Step 0. Load figure-style alongside this skill — that is the design rules (and apply_figure_style() + helpers). Each panel's Task subagent loads it independently; you need it in context to write the outline and review the composite.

Loading the kernel

The deterministic helpers live in kernel.py next to this file. It is not auto-injected — import it by absolute path in a Bash python heredoc (zero import-time side effects; the only heavy import, PIL, is lazy inside compose_figure):

python3 - <<'PY'
import importlib.util
K = "/ABSOLUTE/PATH/TO/figure-composer/kernel.py"   # this SKILL.md's dir + /kernel.py
spec = importlib.util.spec_from_file_location("fc_kernel", K)
k = importlib.util.module_from_spec(spec)
spec.loader.exec_module(k)
print([n for n in dir(k) if not n.startswith("_")])
PY

Every kernel call below assumes k is loaded this way. Each python invocation is a fresh process, so re-import in each heredoc. compose_figure (and the panel renders) need pip install pillow (+ matplotlib for the panels).

Inputs

• claim — one sentence the figure makes true to a reader who reads nothing else.
• data — CSV/parquet file paths (or data refs) that ground every panel.
• width_mm — target venue's column width (common: 85–89mm single, 174–183mm double; check the venue guide).

0. Where this sits

figure-composer is the outer tier: make ONE multi-panel figure good. The inner tier is figure-style (loaded by every panel Task subagent — and load it yourself if you draw anything locally). The outermost tier is paper-narrative — if this figure is part of a paper, run that FIRST: it decides which figure to make and hands you the claim. For a standalone figure, start at step 1.

Entry points (pick one)

• From a claim: you have a one-sentence claim and data refs → write the outline (step 1).
• From an existing figure: copy it into the workspace and build the extraction prompt with derive_outline_task("figure.png"). Then either Read the PNG yourself and emit JSON matching figure_outline_schema(), or dispatch one Task subagent to do it. The image is untrusted input; every string field is model-derived from its pixels, and data_vid must be None on every panel — fill those in from your own data refs. Review and edit the outline before step 2.