figures-python

Use when creating data visualizations for papers - generates publication-quality plots with top-journal color schemes

Quality

91%

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

92%Weight 40%Scale 1-3

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

A thorough, highly actionable plotting skill with executable code, clear workflow, and efficient structure. Its main weakness is that everything lives inline in one file rather than being progressively disclosed into reference files.

Suggestions

Extract the palette definitions and the full code template into referenced files (e.g., references/palettes.md, references/template.py) so SKILL.md stays a concise overview with one-level-deep links.

Split the '常用图表类型' snippets into a separate reference and link to it, keeping only the most common example inline.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-structured with tables, checklists, and executable code; it assumes Claude's competence and avoids explaining basic plotting or library concepts.	3 / 3
Actionability	Provides a complete, copy-paste-ready code template plus concrete per-chart-type snippets, real file paths, and exact rcParams — fully executable guidance.	3 / 3
Workflow Clarity	An opening checklist, numbered sections, and a closing quality-check checklist give a clear generation sequence with an explicit verification step before output is considered final.	3 / 3
Progressive Disclosure	The skill is a single monolithic SKILL.md with no bundle files; color palettes, the code template, and the chart-type snippets could be split into one-level-deep reference files for better navigation.	2 / 3
	Total	11 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 concise, third-person description with an explicit 'Use when' trigger and clear niche. It is strong on trigger terms, completeness, and distinctiveness, but the specificity could be higher by enumerating multiple concrete actions.

Suggestions

Add one or two more concrete actions (e.g., 'exports PNG and SVG at 450 DPI', 'applies Nature/Cell/colorblind-safe palettes') to lift specificity to 3.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('generates publication-quality plots with top-journal color schemes') but lists only one primary action rather than multiple specific concrete actions.	2 / 3
Completeness	Explicitly answers both 'what' ('generates publication-quality plots with top-journal color schemes') and 'when' ('Use when creating data visualizations for papers').	3 / 3
Trigger Term Quality	Includes natural user-facing terms like 'creating data visualizations for papers', 'publication-quality plots', and 'top-journal color schemes' that a user would realistically say.	3 / 3
Distinctiveness Conflict Risk	The paper-figure / top-journal-color niche is distinct from generic plotting skills and unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Norman-bury/research-writing-skill
Path: skills/figures-python/SKILL.md
Commit: 6f79595

Reviewed: 10 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.