4drawio

数学建模非数据型图示绘制阶段。根据 ANALYSIS_MODELING_REPORT.md、RESULTS_REPORT.md 和已有 figures/ 生成技术路线图、子问题求解流程图、模型结构图、数据处理流程图等 DrawIO 图，并导出论文可引用 PDF。

Quality

70%

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/4drawio/SKILL.md

Quality

Content

81%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.

The body is a well-structured, actionable workflow with explicit validation and a fix-retry loop, scoring high on workflow clarity and actionability. Minor conciseness repetition and a skeleton XML example keep conciseness and actionability at 4.

Suggestions

Consolidate the repeated 'don't pad figures / data charts belong to 3coding-visual' guidance into a single boundary statement to tighten conciseness.

Expand the Step 3 XML example with one or two concrete mxCell nodes (not just a placeholder comment) to make the template fully copy-paste-ready.

Note in the body that the referenced '../_references/math_modeling_norms.md' lives outside the skill bundle so the dependency is explicit to readers.

Dimension	Reasoning	Score
Conciseness	Uses efficient tables, checklists, and code blocks and assumes Claude's competence without explaining what DrawIO or flowcharts are; the 'don't pad figures / data charts belong to 3coding-visual' guidance is repeated across several sections and could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready bash for writing the .drawio XML (heredoc) and exporting PDF with a missing-binary fallback, plus a report template; the XML example uses a '<!-- nodes and edges -->' placeholder rather than full node markup, leaving a minor gap.	4 / 5
Workflow Clarity	Six clearly sequenced steps with an explicit self-check checklist (Step 5) and a fix-and-re-export feedback loop ('发现问题要修 .drawio 并重新导出'), satisfying the validation requirement for this batch operation.	5 / 5
Progressive Disclosure	Well-organized into clear sections with one clearly-signaled one-level-deep external reference ('../_references/math_modeling_norms.md'); no bundle files exist to navigate, and the single-file workflow is appropriately placed, with only minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

58%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.

The description clearly states what the skill produces and carves a distinct non-data-diagram niche, but lacks an explicit 'Use when…' trigger and has only partial natural-keyword coverage. Adding a concrete trigger clause would lift completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when…' clause (e.g., 'Use when the paper needs non-data diagrams such as roadmaps, flowcharts, or model-structure figures') to raise completeness above 3.

Add natural user-facing synonyms/variants ('示意图', 'diagram', '画图', '.drawio') to broaden trigger-term coverage.

Name the sibling boundary inline ('数据图请用 3coding-visual') to further reduce conflict risk with the related data-chart skill.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete outputs ('技术路线图、子问题求解流程图、模型结构图、数据处理流程图') plus '导出论文可引用 PDF'; the trailing '等' leaves coverage slightly open rather than fully comprehensive.	4 / 5
Completeness	The 'what' is clear (generate non-data DrawIO diagrams and export PDF), but there is no explicit 'Use when…' trigger clause; the 'when' is only weakly implied by '阶段', which caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('DrawIO', '技术路线图', '流程图', 'PDF') but omits common natural variations and synonyms a user would actually say, so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	The '非数据型' qualifier carves a clear niche distinct from the sibling data-chart skill, but the two are closely related so minor overlap risk remains.	4 / 5
	Total	14 / 20 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/4drawio/SKILL.md
Commit: 83d8783

Reviewed: 12 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.