3coding-visual

数学建模编程实现与数据图表生成阶段。根据 ANALYSIS_MODELING_REPORT.md 编写可复现代码、运行求解、验证约束、输出 RESULTS_REPORT.md 并生成论文可用的数据驱动图表 PDF。

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/3coding-visual/SKILL.md

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.

The body is concise, actionable, and well-sequenced with explicit validation checkpoints. The main weakness is progressive disclosure: the one referenced bundle file does not actually exist, leaving a dangling pointer.

Suggestions

Create the referenced ../_references/math_modeling_norms.md (or correct the path) so the signaled knowledge-base reference resolves to a real file.

Confirm whether the math_modeling_norms reference should be a bundle file under references/ shipped with the skill rather than a sibling _references/ path outside it.

Dimension	Reasoning	Score
Conciseness	The body is lean: it jumps straight into stage boundaries, a 4-step workflow, a per-subproblem checklist, and a report skeleton, without padding concepts Claude already knows about math modeling or plotting libraries.	3 / 3
Actionability	Guidance is concrete and specific — named file paths (code/, figures/, reports/RESULTS_REPORT.md), a 6-item per-subproblem checklist, a report structure template, and per-problem-type chart requirements — which is actionable for an instruction-orchestrating skill even without literal code blocks.	3 / 3
Workflow Clarity	A clearly sequenced 4-step process with an explicit validation checkpoint (Step 2 item 3 '验证约束') plus problem-specific validation rules (feasible-before-optimize, train/validation split, metric-direction checks), satisfying the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	Sections are well organized and it signals a single one-level-deep reference, but that reference (../_references/math_modeling_norms.md) does not exist on disk, so navigation is partially broken and organization 'could be better'.	2 / 3
	Total	11 / 12 Passed

Description

67%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.

The description is specific about capabilities and occupies a clear niche, but it omits any explicit 'when to use' trigger guidance, which limits trigger-term quality and completeness. Adding a 'Use when…' clause would lift the two capped dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when entering the coding/figure stage of a math-modeling competition after ANALYSIS_MODELING_REPORT.md exists, to produce reproducible code, results, and data-driven figure PDFs.'

Add natural user-facing terms users would actually say (数学建模编程、出图、结果求解、复现代码) so the description matches common invocation phrasing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "编写可复现代码" (write reproducible code), "运行求解" (run the solver), "验证约束" (verify constraints), "输出 RESULTS_REPORT.md", "生成…数据驱动图表 PDF" — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does, but never states when to use it; there is no explicit trigger clause, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Names relevant domain terms (数学建模, 编程, 数据图表) but provides no natural user-facing trigger phrasing such as "Use when…", so it sits at 'some relevant keywords but missing common variations' rather than the full-coverage level.	2 / 3
Distinctiveness Conflict Risk	It carves a distinct niche — the coding/figure-generation stage of a staged math-modeling pipeline — and the body explicitly fences it off from sibling stages (2analysis-modeling, 4drawio, 5writing), making conflict unlikely.	3 / 3
	Total	10 / 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/3coding-visual/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.