2analysis-modeling

数学建模赛题分析与建模设计合并阶段。用于读取题面和附件，完成子问题拆解、数据理解、假设预检、变量定义、模型公式、目标函数、约束条件、求解策略和可交给代码实现的建模报告。

Quality

73%

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/2analysis-modeling/SKILL.md

Quality

Content

80%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, well-structured, and highly actionable with concrete report templates and a task-checklist format, but its workflow validation checkpoints are implicit and its sole external reference is a dead link. Tightening validation gates and fixing the missing reference file would raise the two weaker dimensions.

Suggestions

Add explicit validation checkpoints as a validate→fix→retry gate, e.g. after Step 2 and Step 4 require a self-check pass before proceeding, to strengthen workflow clarity.

Fix the broken reference: either create ../_references/math_modeling_norms.md or remove the pointer, so progressive-disclosure navigation resolves to real files.

Optionally split the large report-structure templates into a referenced scaffold file to keep SKILL.md as a tighter overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and procedural with tight templates and code fences, and it avoids explaining concepts Claude already knows; it assumes Claude's competence, fitting the 'lean and efficient' anchor despite minor repeated report-name reminders.	3 / 3
Actionability	It gives concrete, copy-paste-ready structure: fixed filenames (reports/ANALYSIS_MODELING_REPORT.md), section templates, and a task-checklist table with defined columns; for an instruction-only skill this concrete guidance reaches the fully actionable anchor.	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced with feedback elements (e.g. '回头调整解释'), but validation checkpoints are implicit rather than crisp validate→fix→retry gates, which per the rubric caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Content is well-organized and points to a single one-level-deep, clearly signaled reference, but that referenced file (../_references/math_modeling_norms.md) does not exist on disk and no bundle directories are present, so the navigation it promises is broken.	2 / 3
	Total	10 / 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 and distinct, naming a clear stage niche and many concrete actions, but it omits an explicit 'Use when...' trigger and relies on somewhat procedural jargon rather than natural user keywords. Adding explicit trigger guidance and common user phrasings would lift the weaker dimensions.

Suggestions

Add an explicit 'Use when...' (使用场景) clause naming natural user triggers, e.g. 'Use when starting a math-modeling competition problem, before coding or paper writing'.

Include common user-voice keywords alongside the procedural jargon, such as '数学建模竞赛', '建模比赛', '赛题', so the description matches how users actually ask.

Keep the existing concrete action list, which is a strength for specificity.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions ('子问题拆解、数据理解、假设预检、变量定义、模型公式、目标函数、约束条件、求解策略'), matching the 'lists multiple specific concrete actions' anchor rather than the partial-action anchor at 2.	3 / 3
Completeness	It clearly states what the skill does but only implies when to use it via domain framing, with no explicit 'Use when...' clause, which per the rubric guideline caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant domain terms ('数学建模', '赛题分析', '建模设计') but leans on procedural jargon ('假设预检', '求解策略') and omits common user-voice variations, so it does not reach the good natural-term coverage of anchor 3.	2 / 3
Distinctiveness Conflict Risk	It carves a clear, specific niche — the combined analysis+modeling-design stage of a math-modeling competition — distinct from paper-writing or coding phases, making conflict with other skills 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/2analysis-modeling/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.