mathmodel-figure-templates

Use this skill in the MathModel LaTeX sandbox when the user asks to reproduce built-in scientific visualization templates, especially prompts from the Improve tab mentioning $mathmodel-figure-templates, 科研绘图模板, SHAP蜂群柱状图, 配对云雨图, 交叉验证ROC, 泰勒图, 相关矩阵组合图, 预测真实值边缘分布图, TPE调参3D曲面, 下三角相关矩阵半边小提琴图, 分组环形热图, 城市公园降温组合图, or Nature和弦图. It provides ready-to-run Python scripts bundled inside the skill.

Quality

88%

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

87%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 tight, highly actionable skill body with well-organized progressive disclosure. The single gap is workflow clarity: the render workflow lacks an explicit verification checkpoint for confirming outputs were produced.

Suggestions

Add an explicit verification step to the Fast Path, e.g. after rendering confirm that "绘图复刻/outputs/<template>_replica.png/.pdf/.svg" exist before returning paths, and re-run or debug the copied script if any are missing.

Note how to detect renderer failure (non-zero exit / missing outputs) and the recovery action (inspect the copied script in 绘图复刻/scripts/ or rerun render_template.py) to close the feedback loop for batch file-writing.

Optionally state where render logs/errors are written so validation can be checked deterministically.

Dimension	Reasoning	Score
Conciseness	Lean body with no concept-explanation padding; each section (Fast Path, Output Contract, Template Ids, When Customizing) earns its place, and the deterministic-simulated-data caveat is genuinely non-obvious. Matches anchor 3; not 2 because there is no unnecessary explanation to trim.	3 / 3
Actionability	Provides copy-paste-ready commands with full paths ("python3 /home/user/.claude/skills/mathmodel-figure-templates/scripts/render_template.py paired-raincloud"), the "--list" flag, concrete output paths, and a full template-id list. Matches anchor 3; not 2 because the code/commands are executable and complete.	3 / 3
Workflow Clarity	The Fast Path gives a clear numbered sequence (match → run → renderer copies/runs → return paths), but there is no explicit validation/verification checkpoint (e.g., confirm the PNG/PDF/SVG were written or inspect the script exit status). For a file-writing/batch render operation, the missing feedback loop caps this at anchor 2; not 3 because checkpoints are absent, not 1 because the sequence is clearly ordered.	2 / 3
Progressive Disclosure	Body is an overview that signals one-level-deep references ("references/figure-catalog.md", "references/plot-recipes.md"), and the bundle structure matches (real scripts/templates/, assets/previews/, references/ files). Matches anchor 3; not 2 because references are clearly signaled and content is appropriately split.	3 / 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 strong, well-targeted description with explicit 'when' guidance and rich natural trigger terms. Its only weakness is specificity: it states one deliverable (ready-to-run scripts) rather than enumerating multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Quotes "provides ready-to-run Python scripts" and "reproduce built-in scientific visualization templates" name the domain and one deliverable, but do not enumerate multiple distinct concrete actions. Not 3 (no list of several specific actions like extract/fill/merge); not 1 because it is not vague.	2 / 3
Completeness	Explicitly answers what ("It provides ready-to-run Python scripts bundled inside the skill") and when ("Use this skill ... when the user asks to reproduce built-in scientific visualization templates, especially prompts from the Improve tab mentioning..."). Matches anchor 3 with an explicit trigger clause; not 2 because the when is explicit, not implied.	3 / 3
Trigger Term Quality	Quotes many natural trigger terms users would say — "科研绘图模板", "SHAP蜂群柱状图", "配对云雨图", "泰勒图" — plus the "$mathmodel-figure-templates" token, matching Improve-tab phrasing. Broad, multilingual coverage fits anchor 3; not 2 because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to the MathModel LaTeX sandbox with figure-template-specific triggers, making conflict with other skills unlikely. Matches anchor 3 (clear niche with distinct triggers); not 2 because it would not overlap with generic skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: jihe520/MathModelAgent
Path: skills/mathmodel-figure-templates/SKILL.md
Commit: 11f3862

Reviewed: 9 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.