CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-5

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

A well-structured, actionable body with executable commands and good file organization. The main gap is the absence of an explicit output-verification checkpoint in the batch render workflow, which limits workflow clarity.

Suggestions

Add a verification checkpoint after rendering, e.g. 'Confirm 绘图复刻/outputs/<template>_replica.png/.pdf/.svg exist before returning paths; if missing, re-run and inspect script stderr.'

Trim the opening paragraph that restates the bundle location already implied by the Fast Path commands to reduce token overlap with the description.

Consider noting how to handle a failed render (missing dependency, matplotlib backend error) as a short feedback loop in the Fast Path.

DimensionReasoningScore

Conciseness

Mostly lean with executable commands and no concept re-explanation, but the opening 'This skill is bundled into the LaTeX sandbox at ...' and a few restated contract lines mildly overlap the description; efficient with minor trimmable instances.

4 / 5

Actionability

Copy-paste-ready commands (render_template.py with an id, --list), explicit output paths, a complete template-id list, and concrete customization guardrails (MPLCONFIGDIR, deterministic seeds, PNG/PDF/SVG export) cover the common cases fully.

5 / 5

Workflow Clarity

Fast Path gives a clear 4-step sequence, but this batch/file-writing workflow has no explicit verification step confirming outputs were generated before returning their paths; the rubric caps batch operations lacking validation at 3.

3 / 5

Progressive Disclosure

SKILL.md is a concise overview with well-signaled one-level-deep references to references/figure-catalog.md and references/plot-recipes.md (both verified to exist), plus bundled scripts and preview assets appropriately split out for easy navigation.

5 / 5

Total

17

/

20

Passed

Description

90%Weight 40%Scale 1-5

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-scoped description with comprehensive bilingual trigger terms and an explicit 'Use when...' clause. The only weaker dimension is specificity, which names the domain and one action rather than enumerating several distinct capabilities.

DimensionReasoningScore

Specificity

Names the domain ('reproduce built-in scientific visualization templates') and a concrete action ('ready-to-run Python scripts bundled inside the skill'), but lists template names rather than enumerating multiple distinct actions, which fits 'names domain and 1-2 concrete actions' better than the 4-anchor's 'several specific actions'.

3 / 5

Completeness

Explicitly answers both: 'what' (provides ready-to-run Python scripts to reproduce visualization templates) and 'when' ('Use this skill ... when the user asks to reproduce built-in scientific visualization templates, especially prompts from the Improve tab mentioning ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural triggers including the Improve-tab token '$mathmodel-figure-templates', the umbrella term '科研绘图模板', and a long list of specific CJK figure names users would say, giving full synonym/variant coverage.

5 / 5

Distinctiveness Conflict Risk

Scoped to the MathModel LaTeX sandbox with a unique token and named figure templates, forming a clear niche with minimal overlap risk against generic plotting skills.

5 / 5

Total

18

/

20

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
jihe520/MathModelAgent
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.