nature-figure

Submission-grade Nature/high-impact journal figure workflow for Python or R. Use whenever the user asks to create, revise, audit, or polish manuscript figures, multi-panel scientific plots, or journal-ready SVG/PDF/TIFF outputs, especially for Nature-family or other high-impact journals. Before plotting, define the figure's conclusion, evidence logic, export needs, and review risks. If the user has not chosen Python or R, ask "Python or R?" and stop. Use only the selected backend for figure generation, previewing, exporting, and QA. Supports matplotlib/seaborn and ggplot2/patchwork/ComplexHeatmap. Not for dashboards or Illustrator/Figma-first infographics.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured body with executable code for both Python and R, a clearly sequenced figure-contract workflow with explicit gates, and a clean one-level-deep reference table. The only weakness is repetition of the backend-exclusivity and privacy rules, which inflates token count.

Suggestions

Consolidate the backend-exclusivity rule into a single authoritative statement; the rule is currently restated ~4 times across the 'First move' gate, the 'Python-only execution rule' section, and the contract step list.

Merge the top-level 'User-facing privacy rule' section with the brief privacy note near the top to avoid echoing the same guidance twice.

Move the detailed render-inspect-revise QA loop inline (or ensure qa-contract.md is invoked explicitly in the contract steps) so the validation feedback loop is visible in the main workflow rather than only referenced.

Dimension	Reasoning	Score
Conciseness	Mostly efficient (tight rcParams/theme code, bullet stances) but the backend-exclusivity rule is restated ~4 times across 'First move', 'Python-only execution rule', and contract steps, and the privacy rule is echoed, so it could be tightened rather than earning 'every token earns its place'.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code for both backends (Python rcParams + save_pub_py exporting svg/pdf/tiff; R theme_set + save_pub_r using svglite/cairo_pdf/ragg::agg_tiff) with specific archetypes and formats, matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	Clear sequenced 5-step figure contract with explicit blocking gate ('ask Python or R? Then stop') and a missing-runtime checkpoint ('stop before rendering and report the exact blocker'), matching the 'clear sequence with explicit validation steps; feedback loops' anchor.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview with a well-signaled one-level-deep 'Related files' table of 11 real reference files (all verified present), each with an 'Open when' trigger, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that specifies concrete figure-making actions, natural trigger terms, explicit when-to-use guidance, and a clear niche with negative-scope boundaries. No voice violations or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('create, revise, audit, or polish manuscript figures', 'multi-panel scientific plots', 'journal-ready SVG/PDF/TIFF outputs', 'figure generation, previewing, exporting, and QA') plus named libraries, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (submission-grade figure workflow) and when ('Use whenever the user asks to create, revise, audit, or polish...'), plus explicit negative scope, matching the what-AND-when-with-explicit-triggers anchor.	3 / 3
Trigger Term Quality	Covers natural phrasings users would say ('manuscript figures', 'multi-panel scientific plots', 'journal-ready SVG/PDF/TIFF', 'Python or R') with good coverage of common variations, matching the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	Clear niche (Nature/high-impact journal figures, Python/R) with distinct triggers and an explicit exclusion ('Not for dashboards or Illustrator/Figma-first infographics') that reduces conflict, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: ResearAI/DeepScientist
Path: src/skills/nature-figure/SKILL.md
Commit: b366244

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.