doctor

环境检查与安装向导。检查数学建模工作流所需的全部依赖是否已安装，对缺失项提供安装命令，并在用户确认后执行安装。手动触发。

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/doctor/SKILL.md

Quality

Content

82%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, highly actionable environment-check skill with executable detection/install commands, a clear sequenced workflow, and an explicit confirmation-plus-verification loop; its only weaknesses are minor redundancy across tool listings and light error-recovery guidance.

Suggestions

Add a brief fix-and-retry note in Step 5 for when an install command fails (e.g., re-run the command, check permissions, then re-verify) to close the error-recovery gap.

Consolidate the tool list so each tool appears once in a single source-of-truth table and the Step 2 / install sections reference it, reducing repetition.

Consider moving the large per-platform install-command tables into a references/ file referenced from SKILL.md to tighten the overview, though the current self-contained layout is acceptable.

Dimension	Reasoning	Score
Conciseness	Content is mostly lean tables and executable code with little concept over-explanation; the only trimming opportunity is the tool list recurring across the checklist, Step 2, and the per-platform install tables, which keeps it just below the 'lean, every token earns its place' anchor of 5.	4 / 5
Actionability	Detection commands, a complete check_cmd shell function, an inline Python import/version probe, and per-platform install commands are all copy-paste ready and cover the common cases, matching the 'fully executable' anchor.	5 / 5
Workflow Clarity	Six steps are clearly sequenced with an explicit user-confirmation gate (Step 5) and a re-run-Step-2 verification loop after install, but explicit error-recovery guidance (fix-and-retry on a failed install step) is only implied, placing it just below the 5 anchor.	4 / 5
Progressive Disclosure	Sections are well-organized with a clear overview and grouped install tables; no bundle files are present or needed, and the self-contained structure is appropriate, though the lengthy per-platform install tables could conceptually be split into a reference file.	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 does with several concrete actions and a distinct math-modeling niche, but its trigger guidance is weak — '手动触发' is not an explicit 'Use when…' clause and natural trigger synonyms are thin.

Suggestions

Add an explicit 'Use when…' clause naming concrete triggers, e.g. 'Use when setting up or verifying the math modeling workflow, or when dependency/environment errors appear.'

Include natural user-facing synonyms such as 环境配置/依赖检查/安装缺失依赖 alongside 环境检查 to improve trigger-term coverage.

Keep the third-person voice but consider leading with the trigger condition so the 'when' is as prominent as the 'what'.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — '检查…依赖是否已安装', '对缺失项提供安装命令', '在用户确认后执行安装' — with only minor coverage gaps, matching the 'several specific actions' anchor rather than the narrower 1-2 actions of score 3.	4 / 5
Completeness	The 'what' is clear, but 'when' is only weakly implied via '手动触发' — there is no 'Use when…' clause with concrete trigger phrases, so per the judging guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords (环境检查, 安装向导, 依赖, 数学建模) but misses common variations and synonyms a user would naturally say (e.g. 环境配置/依赖检查/setup), fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The math-modeling-workflow niche ('数学建模工作流所需的全部依赖') gives it a clear, mostly-distinct scope with only minor overlap risk against generic environment-setup skills.	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/doctor/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.