skill-quality-reviewer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Skill Quality Reviewer

Skill 质量审查器

Overview

概述

A meta-skill for evaluating the quality of Claude Skills. Perform comprehensive analysis across four key dimensions—description quality (25%), content organization (30%), writing style (20%), and structural integrity (25%)—to generate weighted scores, letter grades, and actionable improvement plans.

Use this skill to validate skills before sharing, identify improvement opportunities, or ensure compliance with skill development best practices.

这是一款用于评估Claude Skill质量的元Skill，会从四个核心维度开展全面分析——描述质量（25%）、内容组织（30%）、写作风格（20%）、结构完整性（25%），最终生成加权得分、等级评定和可落地的改进方案。

你可以在分享Skill前用它做校验、识别可优化点，或者确保Skill符合开发最佳实践。

When to Use This Skill

何时使用本Skill

Invoke this skill when:

Analyzing a skill's quality before distribution
Reviewing skill documentation for best practices
Evaluating adherence to skill development standards
Generating improvement recommendations for existing skills
Validating skill structure and completeness

Trigger phrases:

"Analyze skill quality for ./my-skill"
"Evaluate this skill: ~/.claude/skills/api-helper"
"Review skill quality of git-workflow"
"Check my skill for best practices"
"Generate quality report for this skill"

满足以下场景时可调用本Skill：

分发Skill前分析其质量
审查Skill文档是否符合最佳实践
评估Skill是否符合开发标准
为现有Skill生成改进建议
校验Skill的结构和完整性

触发短语：

"Analyze skill quality for ./my-skill"
"Evaluate this skill: ~/.claude/skills/api-helper"
"Review skill quality of git-workflow"
"Check my skill for best practices"
"Generate quality report for this skill"

Analysis Workflow

分析工作流

Step 1: Load the Skill

步骤1：加载Skill

Accept skill path as input. Verify the path exists and contains

SKILL.md

. Read the complete skill directory structure.

bash

undefined

接收Skill路径作为输入，校验路径是否存在且包含

SKILL.md

，读取完整的Skill目录结构。

bash

undefined

Example invocation

ls -la ~/.claude/skills/target-skill/


**Validate:**
- SKILL.md exists
- Directory is readable
- Path points to a valid skill

ls -la ~/.claude/skills/target-skill/


**校验项：**
- SKILL.md文件存在
- 目录可读
- 路径指向有效的Skill

Step 2: Parse YAML Frontmatter

步骤2：解析YAML头部元数据

Extract and validate the YAML frontmatter from SKILL.md.

Required fields:

```
name
```
- Skill identifier
```
description
```
- Trigger description with phrases

Check for:

Valid YAML syntax
No prohibited fields
Proper formatting

从SKILL.md中提取并校验YAML头部元数据。

必填字段：

```
name
```
- Skill唯一标识
```
description
```
- 包含触发短语的调用描述

检查项：

YAML语法合法
无禁用字段
格式规范

Step 3: Evaluate Description Quality (25%)

步骤3：评估描述质量（25%）

Assess the quality and effectiveness of the frontmatter description.

Scoring breakdown:

Criterion	Points	Evaluation
Trigger phrases clarity	25	3-5 specific user phrases present
Third-person format	25	Uses "This skill should be used when..."
Description length	25	100-300 characters optimal
Specific scenarios	25	Concrete use cases, not vague

Red flags:

Vague triggers like "helps with tasks"
Second-person descriptions ("Use this when you...")
Missing or generic descriptions
No actionable trigger phrases

Reference:

references/examples-good.md

for exemplary descriptions

评估头部元数据中描述的质量和有效性。

评分细则：

评估维度	分值	评估标准
触发短语清晰度	25	包含3-5条具体的用户触发短语
第三人称格式	25	使用「This skill should be used when...」格式
描述长度	25	最优长度为100-300字符
场景明确度	25	提供具体使用场景，无模糊表述

风险提示：

模糊触发语，比如「helps with tasks」
第二人称描述，比如「Use this when you...」
描述缺失或过于通用
无可用的触发短语

参考文档：
references/examples-good.md
可查看优秀描述示例

Step 4: Evaluate Content Organization (30%)

步骤4：评估内容组织（30%）

Assess adherence to progressive disclosure principles.

Scoring breakdown:

Criterion	Points	Evaluation
Progressive disclosure	30	SKILL.md lean, details in references/
SKILL.md length	25	Under 5,000 words (1,500-2,000 ideal)
References/ usage	25	Detailed content properly moved
Logical organization	20	Clear sections, good flow

Check:

SKILL.md body is concise and focused
Detailed content moved to
```
references/
```
Examples and templates in appropriate directories
No information duplication across files

Reference:

references/scoring-criteria.md

for detailed rubrics

评估内容是否符合渐进式披露原则。

评分细则：

评估维度	分值	评估标准
渐进式披露	30	SKILL.md内容精简，详细信息放在references/目录下
SKILL.md长度	25	字数低于5000（最优为1500-2000字）
references/目录使用规范	25	详细内容已合理迁移至该目录
逻辑组织	20	章节清晰，流程顺畅

检查项：

SKILL.md正文简洁聚焦
详细内容已迁移至
```
references/
```
目录
示例和模板存放在对应目录下
无跨文件的信息重复

参考文档：
references/scoring-criteria.md
可查看详细评分规则

Step 5: Evaluate Writing Style (20%)

步骤5：评估写作风格（20%）

Verify adherence to skill writing conventions.

Scoring breakdown:

Criterion	Points	Evaluation
Imperative form	40	Verb-first instructions throughout
No second person	30	Avoids "you", "your", "should"
Objective language	30	Factual, instructional tone

Check for:

Imperative verbs: "Create the file", "Validate input", "Check structure"
Absence of: "You should", "You can", "You need to"
Objective, instructional language
Consistent style throughout

Good examples:

Create the skill directory structure.
Validate the YAML frontmatter.
Check for required fields.

Bad examples:

You should create the directory.
You need to validate the frontmatter.
Check if the fields are there.

校验内容是否符合Skill写作规范。

评分细则：

评估维度	分值	评估标准
祈使句式	40	所有操作指引均以动词开头
无第二人称	30	避免使用「you」、「your」、「should」
客观表述	30	采用事实性、指引性的语气

检查项：

使用祈使动词：「Create the file」、「Validate input」、「Check structure」
无以下表述：「You should」、「You can」、「You need to」
采用客观、指引性的表述
整体风格统一

正面示例：

Create the skill directory structure.
Validate the YAML frontmatter.
Check for required fields.

反面示例：

You should create the directory.
You need to validate the frontmatter.
Check if the fields are there.

Step 6: Evaluate Structural Integrity (25%)

步骤6：评估结构完整性（25%）

Verify the skill's physical structure and completeness.

Scoring breakdown:

Criterion	Points	Evaluation
YAML frontmatter	30	All required fields present
Directory structure	30	Proper organization
Resource references	40	All referenced files exist

Validate:

YAML frontmatter contains
```
name
```
and
```
description
```

Directory structure follows conventions:

skill-name/
├── SKILL.md
├── references/ (optional)
├── examples/ (optional)
└── scripts/ (optional)

All files referenced in SKILL.md actually exist
Examples are complete and working
Scripts are executable

校验Skill的物理结构和完整性。

评分细则：

评估维度	分值	评估标准
YAML头部元数据	30	所有必填字段齐全
目录结构	30	组织规范
资源引用	40	所有引用的文件均存在

校验项：

YAML头部元数据包含
```
name
```
和
```
description
```
字段

目录结构符合规范：

skill-name/
├── SKILL.md
├── references/ (optional)
├── examples/ (optional)
└── scripts/ (optional)

SKILL.md中引用的所有文件真实存在
示例完整可运行
脚本具备可执行权限

Step 7: Calculate Weighted Score

步骤7：计算加权得分

Compute the overall quality score using weighted dimensions.

Formula:

Overall Score = (Description × 0.25) + (Organization × 0.30) +
                (Style × 0.20) + (Structure × 0.25)

Letter grade mapping:

Score Range	Grade	Meaning
97-100	A+	Exemplary
93-96	A	Excellent
90-92	A-	Very Good
87-89	B+	Good
83-86	B	Above Average
80-82	B-	Solid
77-79	C+	Acceptable
73-76	C	Satisfactory
70-72	C-	Minimal Acceptable
67-69	D+	Below Standard
63-66	D	Poor
60-62	D-	Very Poor
0-59	F	Fail

使用各维度权重计算整体质量得分。

计算公式：

Overall Score = (Description × 0.25) + (Organization × 0.30) +
                (Style × 0.20) + (Structure × 0.25)

等级映射规则：

得分范围	等级	含义
97-100	A+	卓越
93-96	A	优秀
90-92	A-	很好
87-89	B+	良好
83-86	B	高于平均
80-82	B-	扎实
77-79	C+	可接受
73-76	C	达标
70-72	C-	最低可接受
67-69	D+	低于标准
63-66	D	差
60-62	D-	很差
0-59	F	不合格

Step 8: Generate Reports

步骤8：生成报告

Create two output documents in the current working directory.

1. Quality Report (

quality-report-{skill-name}.md

)

Executive summary with overall score and grade
Dimension-by-dimension breakdown
Strengths and weaknesses for each dimension
Grade breakdown table
Link to improvement plan

2. Improvement Plan (

improvement-plan-{skill-name}.md

)

Prioritized improvement list (High/Medium/Low)
Specific file locations and line numbers for issues
Current vs. suggested content comparisons
Estimated impact on scores
Time estimates for fixes
Expected score improvement

在当前工作目录下生成两份输出文档。

1. 质量报告（

quality-report-{skill-name}.md

）

包含整体得分和等级的执行摘要
各维度得分明细
各维度的优势和不足
等级划分表
改进方案链接

2. 改进方案（

improvement-plan-{skill-name}.md

）

按优先级排序的改进清单（高/中/低）
问题对应的具体文件路径和行号
当前内容与建议内容的对比
改動对得分的预估影响
修复耗时预估
预期得分提升幅度

Output Templates

输出模板

Quality Report Template

质量报告模板

markdown

undefined

markdown

undefined

Skill Quality Report: {skill-name}

Executive Summary

执行摘要

Overall Score: X/100 ({Grade})
Evaluated: {Date}
Skill Path: {path}

整体得分: X/100 ({Grade})
评估时间: {Date}
Skill路径: {path}

Dimension Scores

各维度得分

1. Description Quality (25%)

1. 描述质量 (25%)

Score: X/100

Strengths:

✅ {specific strength}

Weaknesses:

❌ {specific weakness}

Recommendations:

{actionable recommendation}

[Repeat for other dimensions...]

得分: X/100

优势:

✅ {具体优势}

不足:

❌ {具体不足}

建议:

{可落地的改进建议}

[其他维度重复上述结构...]

Grade Breakdown

等级明细

Dimension	Score	Weight	Contribution
Description	X/100	25%	X.X
Organization	X/100	30%	X.X
Style	X/100	20%	X.X
Structure	X/100	25%	X.X
Overall	X/100	100%	X.X ({Grade})

维度	得分	权重	贡献分
描述质量	X/100	25%	X.X
内容组织	X/100	30%	X.X
写作风格	X/100	20%	X.X
结构完整性	X/100	25%	X.X
整体	X/100	100%	X.X ({Grade})

Next Steps

后续步骤

See

improvement-plan-{skill-name}.md

for detailed improvement suggestions.

undefined

查看

improvement-plan-{skill-name}.md

获取详细改进建议。

undefined

Improvement Plan Template

改进方案模板

markdown

undefined

markdown

undefined

Skill Improvement Plan: {skill-name}

Skill 改进方案: {skill-name}

Priority Summary

优先级汇总

High Priority: {count} items
Medium Priority: {count} items
Low Priority: {count} items

高优先级: {count} 项
中优先级: {count} 项
低优先级: {count} 项

High Priority Improvements

高优先级改进项

1. [Issue Title]

1. [问题标题]

File: SKILL.md:line:line Dimension: Description Quality Impact: +X points

Current:

yaml

{current content}

Suggested:

yaml

{suggested content}

Reason: {why this improves quality}

[Continue with all issues...]

文件: SKILL.md:line:line 所属维度: 描述质量 得分提升: +X 分

当前内容:

yaml

{current content}

建议内容:

yaml

{suggested content}

原因: {说明改動为何能提升质量}

[其他问题按上述结构罗列...]

Quick Wins (Easy Fixes)

快速优化项（易修复）

{quick fix}
{quick fix}

{快速修复项}
{快速修复项}

Estimated Time to Complete

预计完成时长

High Priority: X hours
Medium Priority: X hours
Low Priority: X hours
Total: X hours

高优先级: X 小时
中优先级: X 小时
低优先级: X 小时
总计: X 小时

Expected Score Improvement

预期得分提升

Current: X/100 ({Grade})
After High Priority: X/100 ({Grade})
After All: X/100 ({Grade})

undefined

当前得分: X/100 ({Grade})
修复高优先级项后: X/100 ({Grade})
修复所有项后: X/100 ({Grade})

undefined

Additional Resources

额外资源

Reference Files

参考文件

For detailed evaluation criteria and examples, consult:

references/scoring-criteria.md
- Comprehensive scoring rubrics for each dimension
references/examples-good.md
- Exemplary skills demonstrating best practices
references/examples-bad.md
- Common anti-patterns to avoid

如需了解详细评估标准和示例，可查阅：

references/scoring-criteria.md
- 各维度的完整评分规则
references/examples-good.md
- 符合最佳实践的优秀Skill示例
references/examples-bad.md
- 需要避免的常见反模式

Scripts

脚本

scripts/extract-yaml.sh
- Utility for extracting YAML frontmatter from SKILL.md

scripts/extract-yaml.sh
- 从SKILL.md中提取YAML头部元数据的工具

Related Skills

Best Practices

最佳实践

When Analyzing Skills

分析Skill时的注意事项

Be objective and specific - Base scores on observable criteria, not opinions
Provide actionable feedback - Each recommendation should be concrete and implementable
Include examples - Show current vs. suggested content for clarity
Estimate impact - Help users understand which changes matter most
Be constructive - Frame feedback as opportunities for improvement

客观具体 - 基于可观测的标准评分，避免主观判断
提供可落地的反馈 - 每条建议都要具体可执行
包含示例 - 对比展示当前内容和建议内容，提升清晰度
预估影响 - 帮助用户理解哪些改動价值最高
保持建设性 - 将反馈定位为改进机会

Common Quality Issues

常见质量问题

Description Quality:

Vague or generic trigger phrases
Second-person descriptions
Missing concrete use cases

Content Organization:

SKILL.md too long (>5,000 words)
Detailed content not moved to references/
Poor information hierarchy

Writing Style:

Second-person language ("you", "your")
Mixed imperative and descriptive styles
Subjective or conversational tone

Structural Integrity:

Missing required YAML fields
Referenced files don't exist
Incomplete examples or broken scripts

描述质量问题：

触发短语模糊或过于通用
使用第二人称描述
缺失具体使用场景

内容组织问题：

SKILL.md篇幅过长（>5000字）
详细内容未迁移至references/目录
信息层级混乱

写作风格问题：

使用第二人称表述（"you", "your"）
祈使句式和描述句式混用
语气主观或过于口语化

结构完整性问题：

缺失YAML必填字段
引用的文件不存在
示例不完整或脚本无法运行

Grade Benchmarks

等级基准

A grade (90-100): Exemplary skills serving as templates for others

All dimensions score 85+
Clear, specific descriptions
Excellent progressive disclosure
Consistent imperative style
Complete, well-organized structure

B grade (80-89): High-quality skills with minor improvements needed

Most dimensions score 75+
Good descriptions and organization
Generally follows best practices
May have minor style inconsistencies

C grade (70-79): Acceptable skills requiring moderate improvements

Key areas meet minimum standards
Some weaknesses in organization or style
Functional but not exemplary

D/F grade (below 70): Skills needing significant work

Multiple dimensions below 70
Major structural or style issues
Requires comprehensive revision

A级（90-100）：可作为范本的卓越Skill

所有维度得分均高于85
描述清晰具体
渐进式披露做得非常好
祈使句式风格统一
结构完整、组织规范

B级（80-89）：高质量Skill，仅需小幅优化

大部分维度得分高于75
描述和组织情况良好
整体符合最佳实践
可能存在少量风格不统一的问题

C级（70-79）：可接受的Skill，需要中等幅度优化

核心领域满足最低标准
内容组织或风格存在部分不足
功能可用但不够优秀

D/F级（低于70）：需要大量优化的Skill

多个维度得分低于70
存在严重的结构或风格问题
需要全面重构

Usage Examples

使用示例

Example 1: Analyze a local skill

User: "Analyze skill quality for ~/.claude/skills/git-workflow"

[Claude executes the 8-step workflow and generates:]
- quality-report-git-workflow.md
- improvement-plan-git-workflow.md

Example 2: Review before sharing

User: "Review my new skill before I publish it"

[Claude analyzes the skill and provides:]
- Detailed quality assessment
- Specific improvement recommendations
- Expected score after implementing fixes

Example 3: Quality check for existing skill

User: "Check skill quality of api-helper"

[Claude evaluates and reports:]
- Current grade and score
- Top improvement opportunities
- Quick wins for easy score gains

示例1：分析本地Skill

用户: "Analyze skill quality for ~/.claude/skills/git-workflow"

[Claude执行8步工作流，生成：]
- quality-report-git-workflow.md
- improvement-plan-git-workflow.md

示例2：分享前审查

用户: "Review my new skill before I publish it"

[Claude分析Skill后提供：]
- 详细质量评估
- 具体改进建议
- 修复后的预期得分

示例3：现有Skill质量检查

用户: "Check skill quality of api-helper"

[Claude评估后输出：]
- 当前等级和得分
- 核心改进点
- 可快速提升得分的优化项

skill-quality-reviewer

Original

Translation

Skill Quality Reviewer

Skill 质量审查器

Overview

概述

When to Use This Skill

何时使用本Skill

Analysis Workflow

分析工作流

Step 1: Load the Skill

步骤1：加载Skill

Example invocation

Example invocation

Step 2: Parse YAML Frontmatter

步骤2：解析YAML头部元数据

Step 3: Evaluate Description Quality (25%)

步骤3：评估描述质量（25%）

Step 4: Evaluate Content Organization (30%)

步骤4：评估内容组织（30%）

Step 5: Evaluate Writing Style (20%)

步骤5：评估写作风格（20%）

Step 6: Evaluate Structural Integrity (25%)

步骤6：评估结构完整性（25%）

Step 7: Calculate Weighted Score

步骤7：计算加权得分

Step 8: Generate Reports

步骤8：生成报告

Output Templates

输出模板

Quality Report Template

质量报告模板

Skill Quality Report: {skill-name}

Skill Quality Report: {skill-name}

Executive Summary

执行摘要

Dimension Scores

各维度得分

1. Description Quality (25%)

1. 描述质量 (25%)

Grade Breakdown

等级明细

Next Steps

后续步骤

Improvement Plan Template

改进方案模板

Skill Improvement Plan: {skill-name}

Skill 改进方案: {skill-name}

Priority Summary

优先级汇总

High Priority Improvements

高优先级改进项

1. [Issue Title]

1. [问题标题]

Quick Wins (Easy Fixes)

快速优化项（易修复）

Estimated Time to Complete

预计完成时长

Expected Score Improvement

预期得分提升

Additional Resources

额外资源

Reference Files

参考文件

Scripts

脚本

Related Skills

相关Skill

Best Practices

最佳实践

When Analyzing Skills

分析Skill时的注意事项

Common Quality Issues

常见质量问题

Grade Benchmarks

等级基准

Usage Examples

使用示例