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

71%

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

71%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 instruction skill with sequenced steps, report templates, and quality gates. Its main weakness is progressive disclosure: it signals an external reference file that is absent, and no bundle files exist to absorb the inlined template bulk.

Suggestions

Create the referenced '../_references/math_modeling_norms.md' (or remove the dangling reference) so signaled navigation actually resolves.

Move the large report-template and table-schema code blocks into a reference file (e.g. references/report_templates.md) and link to it from the main body to reduce inline bulk.

Make the validation feedback loop explicit as numbered checkpoints (validate assumption -> if marginal effect is null, adjust interpretation -> re-check) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient: concrete report templates, table schemas, and per-step deliverables with little concept padding; minor redundancy where the recommended structure repeats items already described in earlier steps.	4 / 5
Actionability	Provides concrete, copy-paste-ready report templates (markdown code blocks, a 代码实现任务清单 table schema, required subsections per subproblem); templates contain placeholders and the referenced norm file does not exist, leaving minor gaps.	4 / 5
Workflow Clarity	Five clearly sequenced Steps with explicit per-step deliverables and a quality-requirements section; a feedback loop exists ('如果某个假设会让后续问题的新增条件没有边际效果，要回头调整解释') but recovery checkpoints are somewhat implicit rather than enumerated.	4 / 5
Progressive Disclosure	Well-organized into sections and points to one external norm file with clear scoping, but that reference ('../_references/math_modeling_norms.md') does not exist and no bundle directory is present, creating a navigation gap for a ~135-line skill.	3 / 5
	Total	15 / 20 Passed

Description

71%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 is specific and lists comprehensive concrete actions, but it omits any explicit 'Use when...' trigger guidance, leaving the activation context only weakly implied. Adding a concrete trigger clause would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause naming concrete activation phrases, e.g. '用于数学建模赛题的分析与建模设计阶段' with concrete user utterances.

Include natural synonyms/variations (e.g. '数学模型', '赛题建模', 'problem modeling') to broaden trigger-term coverage.

Reframe in third-person action voice consistently and ensure the 'when' clause names specific situations (reading 题面/附件, 子问题拆解).

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions covering the modeling stage comprehensively: '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' and a '可交给代码实现的建模报告'.	5 / 5
Completeness	Clearly answers 'what' with a long action list, but provides no explicit 'Use when...' trigger clause; the 'when' is only weakly implied by domain framing, which caps completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	Includes natural domain terms users would say ('数学建模', '赛题分析', '建模设计') with good coverage, but lacks common synonyms or English/variation phrasings that round out the set.	4 / 5
Distinctiveness Conflict Risk	Targets a distinct niche (merged analysis+modeling stage of a math modeling competition) with mostly clear triggers; minor overlap risk with a sister code-implementation stage.	4 / 5
	Total	16 / 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/2analysis-modeling/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.