Nature Figure

Nature Figure Making — Router

Routing protocol

For a new task, load the core and matching resources below. Reuse already loaded guidance on follow-ups; load more only when the task needs it.

0. Check for graphical-abstract and AI-schematic routes

For every graphical-abstract planning, generation, revision, or audit task that uses AI, read references/ai-graphical-abstract-workflow.md first. It owns the message/audience brief, composition and palette workflow, policy gate, human scientific review, disclosure boundary, and provenance requirements. A Nature Careers article is practitioner advice, not submission clearance; verify the current official policy for the exact target journal.

If the request is planning or auditing only, do not ask for Python or R unless the user also asks to render or revise a data-driven figure.

If the user explicitly asks to generate a manuscript schematic, graphical abstract, mechanism diagram, concept illustration, or paper schematic with OpenRouter, GPT Image 2, an image-generation API, or similar wording, do not ask "Python or R?". This is a non-plotting AI-schematic route.

For this route:

1. Read manifest.yaml and the always_load files.
2. Read references/ai-graphical-abstract-workflow.md.
3. Read references/openrouter-image-generation.md.
4. Use scripts/generate_openrouter_schematic.py when the user wants a real API call or a reproducible payload.
5. Treat output as a draft schematic / graphical abstract, not as a quantitative data panel. Do not invent experimental values, author logos, institutional marks, or unsupported mechanisms. Keep internal usefulness separate from submission eligibility.

Only continue to the Python/R backend gate for plotting, charting, data visualization, or manuscript figure assembly tasks that are not explicit OpenRouter AI image-generation requests.

1. Load the manifest and the core layer

Read manifest.yaml. It declares the backend axis, the allowed values, and the file paths each value maps to.

Also read every file listed under always_load (static/core/contract.md and static/core/stance.md). These hold the figure contract, the backend gate, the missing-runtime rule, the privacy rule, and the default operating stance that apply to every figure job.

2. Resolve the plotting backend

Backend selection applies only to rendering or editing plotting code. Reuse a choice already established in the same task and its follow-ups; do not ask again merely because a new message omits the language. Read-only figure review and backend-independent data inspection may proceed without this choice. If the backend remains unresolved, retain the one-time Python/R question and pause only dependent plotting steps. Explicit approval requirements and backend exclusivity remain in force.

Resolve the plotting backend from the current task before consulting the saved default. Decide the backend value in this order:

1. If the current request explicitly chooses Python or R, use that backend and save it with scripts/nature_figure_backend.py set python or scripts/nature_figure_backend.py set r.
2. If the request provides a clearly language-specific input file/workflow, use that backend and save it.
3. Otherwise reuse a Python/R choice already established in this task. If none exists, run scripts/nature_figure_backend.py get and use a returned python or r preference.
4. If neither a task choice nor a saved preference exists, ask exactly one concise question — Python or R? I will remember this as your default. — and pause only dependent plotting steps. After the user answers, save the answer before proceeding.

• python — matplotlib / seaborn.
• r — ggplot2 / patchwork / ComplexHeatmap.

Do not guess or choose a backend by aesthetics alone. Only recommend a backend when the user explicitly asks you to choose; then use references/backend-selection.md, state the reason, save the selected backend, and proceed. Once selected, the backend is exclusive for all drawing, previewing, exporting, and visual QA (see core/contract.md). This gate does not apply to the explicit OpenRouter AI-schematic route above.

3. Load the matching backend fragment

After the backend is resolved, Read the mapped fragment (static/fragments/backend/python.md or static/fragments/backend/r.md). It carries the backend-only execution rule and the publication quick-start (rcParams/theme and export helper). Do not load the other backend's fragment.

4. Build the figure using the loaded material

Apply the loaded material in this order:

1. Figure contract (core/contract.md) — write the core conclusion, map the evidence chain, classify the archetype, set the journal/export contract, before any code.
2. Multi-panel evidence architecture — when planning, restructuring, or auditing a labelled multi-panel figure, load references/multipanel-evidence-architecture.md. Make the figure answer one Results-level scientific question; assign panels different inferential roles, not merely different metrics. When figure order must follow the manuscript argument, also load ../nature-shared/core/nature-results-discussion.md.
3. Default stance (core/stance.md) — archetype-first composition, hero panel, restrained palette, statistics/integrity as part of the figure.
4. Backend fragment — the exclusive Python or R quick-start and execution rule.
5. Template adaptation — when reusing built-in original examples, licensed external material, or user-provided plotting code, load references/asset-adaptation.md before mapping data or changing the script.
6. Rendered QA and delivery preflight — load references/qa-contract.md, run the render-time panel-alignment gate for every multi-panel figure, scripts/validate_figure.py on the plotting source, scripts/audit_pdf_text.py on the exported PDF, and scripts/audit_figure_collisions.py on the same final PDF. Then inspect every panel and the complete figure at final physical size. Automated checks do not replace the panel-by-panel uncertainty, salience, spacing, and ambiguity audit.

For every figure containing two or more comparable panels, measure the final rendered plot-area rectangles before export and preserve the alignment JSON. Python figures must call require_matplotlib_panel_alignment() from scripts/audit_panel_alignment.py after the final layout draw. R/patchwork figures must source scripts/panel_alignment.R, write the patchwork layout manifest at the final export dimensions, and run the same backend-neutral JSON auditor. Use a default physical tolerance of 1.5 pt for shared edges, widths, heights, panel-label anchors and repeated gutters. FIX BEFORE DELIVERY or exit code 1 blocks export; NOT AUDITABLE or exit code 2 blocks any claim that alignment passed. A horizontal row of three or four equal-grid-span panels must have equal final plot-area widths as well as equal heights and gutters; an intentional unequal-width design requires a recorded panel-width exemption. Structured unequal-span grids—including two stacked panels beside one panel spanning both rows, in either column—must be inferred from shared grid start/stop boundaries and checked automatically. Nested grids, free-positioned hero panels, insets and colorbars may be excluded only through explicit comparable groups or a recorded exemption with a reason. Do not weaken the global tolerance to hide one intentional exception.

After every generated or revised Python/R scientific figure, export the final PDF and run the collision audit again; this is mandatory after any change to data geometry, text, fonts, legends, annotations, axes, error bars, panel size or layout, not only at final submission. Use: