nature-figure
Skill0 starsChanged 2 months agoMITView on GitHub
Create, revise, audit, and export submission-grade scientific figures for Nature-family and other high-impact venues in Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap), including multi-panel plots, figures4papers-style work, and journal-ready SVG/PDF/TIFF outputs. Use for paper or scientific plots, manuscript data visualization, 论文配图、学术写作配图、科研绘图、科研作图、画图、作图、出图、论文图表、可视化. Define the conclusion, evidence logic, data integrity, template compatibility, export needs, and reviewer risks before plotting; honor or persist the Python/R backend choice. Also use the separate OpenRouter GPT Image 2 route for explicit AI-generated graphical abstracts, mechanism diagrams, concept schematics, 论文示意图、机制示意图、图形摘要; this route skips backend choice and treats outputs as drafts. Do not use for interactive dashboards, statistics-only analysis, data cleaning, literature review, code debugging, pure photo editing, or Illustrator/Figma-first infographics without manuscript-figure intent.
15 other projects use a version of this, 10 of them edited.
Adopted by
Most recently taken up by
- AfonsoZhang/auto-research-systemedited, first seen Nov 15, 2026
- denghuipan/nature-portfolio-skillsedited, first seen Nov 15, 2026
- apattichis/agentic-research-toolkitedited, first seen Nov 8, 2026
- dragonadam/nature-skillsedited, first seen Oct 25, 2026
- Luooops/skillsedited, first seen Oct 13, 2026
- Boom5426/Nature-Paper-Skillsedited, first seen Oct 9, 2026
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 10
- Yuan1z0825/nature-skills★ 54k84% same
- Boom5426/Nature-Paper-Skills★ 66161% same
- yanjumlinnb-boop/nature-skills★ 1467% same
- yjz211/MathModeling-AI-Solver-Skills★ 577% same
- dragonadam/nature-skills★ 471% same
- denghuipan/nature-portfolio-skills★ 267% same
- AfonsoZhang/auto-research-system★ 172% same
- apattichis/agentic-research-toolkit★ 184% same
- Luooops/skills★ 188% same
- zh123012/claude-skills★ 192% same
Wrote their own version · 5
- Chanw-research/claude-code-paper-writing★ 42same name
- Yang1Bai/nature-paper-hub★ 20same name
- Delagong950/nature-skills★ 4same name
- vcis-wangchenxu/agent_nature-skills★ 4same name
- Lling0000/nature-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- journal-style-learnSkill
- nature-academic-searchSkill
- nature-citationSkill
- nature-dataSkill
- nature-downloaderSkill
- nature-experiment-logSkill
- nature-figure-prompt-onlySkill
- nature-image2pptSkill
- nature-literature-pipelineSkill
- nature-paper2pptSkill
- nature-paper-cardSkill
- nature-paper-to-patentSkill
- nature-polishingSkill
- researchwriteSkill
- nature-readerSkill
- nature-ref-verifierSkill
- nature-responseSkill
- nature-reviewerSkill
- nature-sharedSkill
- nature-statisticsSkill
- nature-writingSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
20 rules. 0 are common, 10 are distinctive, and 10 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
When the target is Expert Systems with Applications (ESWA or Expert Syst.
- Very specific: line 26
Use its artwork, composite-figure, caption and AI-disclosure rules before setting the figure contract.
- Distinctive: line 37
Do not try to apply the figure logic from memory or from this router.
- Distinctive: line 41
Follow these steps every time the skill is invoked.
- Distinctive: line 53
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.
- Distinctive: line 56
If the user explicitly asks to generate a manuscript schematic, graphical abstract, mechanism diagram, concept illustration, or paper …
- Very specific: line 60
Read manifest.yaml and the always_load files.
- Very specific: line 63
Use scripts/generate_openrouter_schematic.py when the user wants a real API call or a reproducible payload.
- Distinctive: line 64
Treat output as a draft schematic / graphical abstract, not as a quantitative data panel.
- Distinctive: line 66
Only continue to the Python/R backend gate for plotting, charting, data visualization, or manuscript figure assembly tasks that are not …
- Very specific: line 70
Read manifest.yaml. It declares the backend axis, the allowed values, and the file paths each value maps to.
- Very specific: line 78
If the current request explicitly chooses Python or R, use that backend and save it with scripts/nature_figure_backend.py set python or …
- Distinctive: line 79
If the request provides a clearly language-specific input file/workflow, use that backend and save it.
- Distinctive: line 81
If no saved preference exists, ask exactly one concise question — Python or R?
- Very specific: line 90
After the backend is resolved, Read the mapped fragment (static/fragments/backend/python.md or static/fragments/backend/r.md).
- Very specific: line 98
Default stance (core/stance.md) — archetype-first composition, hero panel, restrained palette, statistics/integrity as part of the figure.
- Distinctive: line 122
After every generated or revised Python/R scientific figure, export the final PDF and run the collision audit again.
- Very specific: line 145
When the target is the flagship journal Nature, also load references/nature-article-requirements.md.
- Very specific: line 150
When the target is Nature Machine Intelligence, instead load ../nature-shared/journal-formats/nature-machine-intelligence.md.
- Distinctive: line 167
Do not infer flagship Nature or NMI requirements from a Nature Communications corpus or from the visual-style examples in this skill.
“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Nature Figure Making — Router
Additional configured journals
For Applied Soft Computing (ASC), Engineering Applications of Artificial
Intelligence (EAAI), ISA Transactions, Knowledge-Based Systems (KBS),
Measurement, Neurocomputing, or IEEE Transactions on Reliability, use
../nature-shared/journal-formats/index.md to resolve the exact journal.
Preserve this skill’s task workflow and evidence safeguards. Apply only the
selected reference’s relevant scope; do not impose flagship-Nature significance
or import another journal’s numerical, citation, or production defaults.
These seven profiles do not yet establish verified official submission limits;
verify the target’s current official source when such requirements affect work.
ESWA journal context
When the target is Expert Systems with Applications (ESWA or
Expert Syst. Appl., case-insensitive), read
../nature-shared/journal-formats/eswa.md before applying journal-specific defaults.
Use its artwork, composite-figure, caption and AI-disclosure rules before
setting the figure contract. For ML/RUL visual planning, also read
../nature-shared/core/eswa-ml-rul-style.md. Keep the existing plotting/backend workflow;
ESWA rules override incompatible Nature/NMI export defaults.
This skill is split into two layers:
- A static layer under
static/that holds versioned, reusable content fragments (the figure contract and default stance, plus a per-backend quick-start for Python and R). - A dynamic layer (this file plus
manifest.yaml) that detects the plotting backend and loads only the fragment needed for the current job. The large design, API, pattern, and QA material lives in on-demand references.
Do not try to apply the figure logic from memory or from this router. Always load fragments from disk as described below.
Routing protocol
Follow these steps every time the skill is invoked.
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:
- Read manifest.yaml and the
always_loadfiles. - Read references/ai-graphical-abstract-workflow.md.
- Read references/openrouter-image-generation.md.
- Use scripts/generate_openrouter_schematic.py when the user wants a real API call or a reproducible payload.
- 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 backend — a blocking gate
Backend selection blocks plotting tasks, but it should not annoy the same user forever. Decide the backend value in this order:
- If the current request explicitly chooses Python or R, use that backend and save it with
scripts/nature_figure_backend.py set pythonorscripts/nature_figure_backend.py set r. - If the request provides a clearly language-specific input file/workflow, use that backend and save it.
- Otherwise run
scripts/nature_figure_backend.py get. If it returnspythonorr, use the saved preference. - If no saved preference exists, ask exactly one concise question — Python or R? I will remember this as your default. — and stop. 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:
- Figure contract (
core/contract.md) — write the core conclusion, map the evidence chain, classify the archetype, set the journal/export contract, before any code. - 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. - Default stance (
core/stance.md) — archetype-first composition, hero panel, restrained palette, statistics/integrity as part of the figure. - Backend fragment — the exclusive Python or R quick-start and execution rule.
- Template adaptation — when reusing built-in original examples, licensed external material, or user-provided plotting code, load
references/asset-adaptation.mdbefore mapping data or changing the script. - 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.pyon the plotting source,scripts/audit_pdf_text.pyon the exported PDF, andscripts/audit_figure_collisions.pyon 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:
python skills/nature-figure/scripts/audit_figure_collisions.py figure.pdf \
--json-out figure.collision-audit.json \
--overlay-pdf figure.collision-audit.pdfFIX BEFORE DELIVERYor exit code1: repair the figure, re-export with the selected plotting backend, and rerun all rendered QA.REVIEW REQUIRED: inspect every WARN at final physical size; record why an intentional overlay is acceptable. Use--strictwhen WARN must block.NOT AUDITABLEor exit code2: report the dependency/PDF blocker and do not claim collision validation. Installrequirements.txtwhen PyMuPDF is absent.
The collision audit reads PDF geometry for both Python and R output. It does not redraw the scientific figure or authorize cross-backend plotting. Its optional marked PDF is a QA-only diagnostic artifact and must never replace the selected backend's source or submission files.
When the target is the flagship journal Nature, also load
references/nature-article-requirements.md. It separates initial-review files
from accepted-in-principle main and Extended Data production contracts and owns
the flagship legend limit.
When the target is Nature Machine Intelligence, instead load
../nature-shared/journal-formats/nature-machine-intelligence.md. Apply its
combined six-item main display budget, ten-item Extended Data maximum,
initial-versus-production boundary, 300-dpi/180-mm production checks and source-
data contract. NMI's current live pages do not assign a standalone per-legend
number, but its official 2018 brief guide set a historical advisory ceiling of
fewer than 300 English words per complete figure legend. Count the whole legend,
not each panel; aim for 150–250 words and keep it below 300 unless the live
submission system or editor gives a newer instruction. Do not import flagship
Nature's limit.
The chart serves the scientific logic; aesthetic polish is subordinate to making the core conclusion clear, defensible, and reviewable.
5. Reach for references only when needed
The files under references/ are deep references, not defaults. Open them on demand per the references.on_demand table in the manifest — for example references/figure-contract.md to build the contract, references/multipanel-evidence-architecture.md to turn one Results-level question into complementary panel roles and a claim-escalating figure sequence, references/asset-adaptation.md to reuse a plotting template safely, references/template-catalog.md for validated Python CSV templates, references/api.md for the Python palette and numerical/layout safety helpers, references/r-workflow.md for R, references/design-theory.md for color/typography/export rationale, references/common-patterns.md and references/chart-types.md for layout/chart recipes, references/nature-2026-observations.md for real Nature page archetypes, references/qa-contract.md before final delivery, references/nature-article-requirements.md for exact flagship Nature stage and upload rules, ../nature-shared/journal-formats/nature-machine-intelligence.md for exact NMI figure rules, references/ai-graphical-abstract-workflow.md for AI-assisted graphical-abstract planning, policy gating, human verification, and provenance, and references/tutorials.md / references/demos.md for worked examples.
Do not infer flagship Nature or NMI requirements from a Nature Communications corpus or from the visual-style examples in this skill.
Why this split
- The static layer is versioned and reviewable. The backend gate is now explicit in the manifest rather than buried in prose.
- The dynamic layer keeps each invocation cheap: only the selected backend's quick-start enters context, and the 2,600+ lines of reference depth load only when a step needs them.
- The router itself is short on purpose. Update fragments and references, not this file, when adding scope.
- This structure mirrors
nature-writing,nature-polishing,nature-reader, andnature-paper2ppt.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

