CtrlK
BlogDocsLog inGet started
Tessl Logo

nature-figure

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.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body is well-structured as a router with a clear sequenced workflow and validation checkpoint, but its actionability and progressive disclosure are undermined because the static layer and manifest.yaml it directs Claude to load are absent from the bundle. Some meta-rationale could also be trimmed for token efficiency.

Suggestions

Ship the missing static layer the routing protocol depends on — manifest.yaml, static/core/contract.md, static/core/stance.md, and static/fragments/backend/python.md and r.md — so load steps 1, 3, and 4 are executable as written.

Inline a minimal backend quick-start (rcParams/theme snippet plus an export one-liner) as a fallback so the body stays actionable even if a fragment file is missing or fails to load.

Trim the 'Why this split' section and the closing 'aesthetic polish is subordinate' aside; they are meta-rationale that adds tokens without guiding execution.

DimensionReasoningScore

Conciseness

The router is mostly lean and points to files rather than inlining content, but the 'Why this split' section and closing aesthetic-polish aside are meta-rationale that do not guide execution and could be trimmed.

2 / 3

Actionability

It gives concrete executable commands (e.g. 'scripts/nature_figure_backend.py set python', 'scripts/validate_figure.py'), but the core load targets — manifest.yaml, static/core/contract.md, stance.md, and the backend fragments — are missing from the bundle, so steps 1, 3, and 4 cannot be followed as written.

2 / 3

Workflow Clarity

The routing protocol (steps 0-5) is a clearly sequenced multi-step process with a blocking backend gate and an explicit delivery preflight checkpoint that runs validate_figure.py before inspecting outputs.

3 / 3

Progressive Disclosure

Structure and signaling are good — a short router with one-level-deep markdown-linked references — but the central static/ layer and manifest.yaml referenced throughout do not exist in the bundle, so navigation to the primary content is broken.

2 / 3

Total

9

/

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.

The description is strong across all dimensions: specific actions, rich natural trigger terms in two languages, explicit what/when guidance, and a well-scoped niche with exclusions. Its only weakness is verbosity, which the description rubric does not directly penalize.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'Create, revise, audit, and export submission-grade scientific figures', 'multi-panel plots', 'journal-ready SVG/PDF/TIFF outputs' — matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (figure creation/audit/export pipeline) and when ('Use for paper or scientific plots...'; 'Also use the separate OpenRouter GPT Image 2 route for...'), plus a 'Do not use for...' exclusion clause.

3 / 3

Trigger Term Quality

Covers natural user phrasings in English ('paper or scientific plots', 'manuscript data visualization', 'graphical abstracts', 'mechanism diagrams') and Chinese ('论文配图', '科研绘图', '图形摘要'), giving broad coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (Nature-family manuscript figures in Python/R) with distinct triggers and explicit exclusions ('Do not use for interactive dashboards, statistics-only analysis...'), making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
Yuan1z0825/nature-skills
Reviewed

Table of Contents

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.