skill-tester

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Skill Tester

技能测试工具

The agent validates skill packages for structure compliance, tests Python scripts for syntax and stdlib-only imports, and scores quality across four dimensions (documentation, code quality, completeness, usability) with letter grades and improvement recommendations. It supports BASIC, STANDARD, and POWERFUL tier classification.

该Agent用于校验skill包的结构合规性，测试Python脚本的语法以及是否仅导入stdlib模块，从四个维度（文档、代码质量、完整性、易用性）对质量进行评分，给出字母等级和改进建议，支持BASIC、STANDARD、POWERFUL三个层级的分类校验。

Quick Start

快速开始

bash

undefined

bash

undefined

Validate skill structure and documentation

校验skill结构和文档

python skill_validator.py engineering/my-skill --tier POWERFUL --json

Test all Python scripts in a skill

测试skill内所有Python脚本

python script_tester.py engineering/my-skill --timeout 30

Score quality with improvement roadmap

质量评分并生成改进路线图

python quality_scorer.py engineering/my-skill --detailed --minimum-score 75

---

python quality_scorer.py engineering/my-skill --detailed --minimum-score 75

---

Core Workflows

核心工作流

Workflow 1: Validate a New Skill

工作流1：校验新Skill

Run
```
skill_validator.py
```
with target tier to check structure, frontmatter, required sections, and scripts
Review errors (blocking) and warnings (non-blocking) in the report
Fix all errors -- missing SKILL.md, invalid frontmatter, external imports
Validation checkpoint: Score >= 60; zero errors; all scripts pass
```
ast.parse()
```

bash

python skill_validator.py engineering/my-skill --tier STANDARD --json

运行
```
skill_validator.py
```
并指定目标层级，检查结构、前置元数据、必填章节和脚本
查看报告中的错误（阻塞性）和警告（非阻塞性）
修复所有错误：缺失SKILL.md、无效前置元数据、外部导入等
校验检查点： 评分≥60；零错误；所有脚本通过
```
ast.parse()
```
校验

bash

python skill_validator.py engineering/my-skill --tier STANDARD --json

Workflow 2: Test Skill Scripts

工作流2：测试Skill脚本

Run
```
script_tester.py
```
to execute syntax validation, import analysis, and runtime tests
Review per-script results: argparse detection,
```
--help
```
output, sample data execution
Fix failures: add
```
if __name__ == "__main__"
```
guards, replace external imports with stdlib
Validation checkpoint: All scripts pass syntax; zero external imports;
```
--help
```
exits cleanly

bash

python script_tester.py engineering/my-skill --timeout 60 --json

运行
```
script_tester.py
```
执行语法校验、导入分析和运行时测试
查看每个脚本的测试结果：argparse检测、
```
--help
```
输出、样例数据执行情况
修复失败项：添加
```
if __name__ == "__main__"
```
防护、将外部导入替换为stdlib模块
校验检查点： 所有脚本语法通过；零外部导入；
```
--help
```
命令正常退出

bash

python script_tester.py engineering/my-skill --timeout 60 --json

Workflow 3: Score and Improve Quality

工作流3：质量评分与优化

Run
```
quality_scorer.py
```
with
```
--detailed
```
for component-level breakdowns
Review the prioritized improvement roadmap (up to 5 items)
Address HIGH-priority items first (documentation gaps, missing error handling)
Re-run to verify score improvement
Validation checkpoint: Overall score >= 75; no dimension below 50%

bash

python quality_scorer.py engineering/my-skill --detailed --minimum-score 75 --json

带
```
--detailed
```
参数运行
```
quality_scorer.py
```
获取组件级评分明细
查看优先级排序的改进路线图（最多5项）
优先处理高优先级项（文档缺口、缺失错误处理等）
重新运行工具验证评分提升
校验检查点： 整体评分≥75；所有维度得分不低于50%

bash

python quality_scorer.py engineering/my-skill --detailed --minimum-score 75 --json

Tier Requirements

层级要求

Requirement	BASIC	STANDARD	POWERFUL
SKILL.md lines	100+	200+	300+
Python scripts	1 (100-300 LOC)	1-2 (300-500 LOC)	2-3 (500-800 LOC)
Argparse	Basic	Subcommands	Multiple modes
Output formats	Single	JSON + text	JSON + text + validation
Error handling	Essential	Comprehensive	Advanced recovery

要求	BASIC	STANDARD	POWERFUL
SKILL.md行数	100+	200+	300+
Python脚本	1个（100-300行代码）	1-2个（300-500行代码）	2-3个（500-800行代码）
Argparse	基础功能	子命令	多模式
输出格式	单一种类	JSON + 文本	JSON + 文本 + 校验
错误处理	基础必要	全面覆盖	高级恢复机制

Quality Scoring Dimensions

质量评分维度

Dimension	Weight	Measures
Documentation	25%	SKILL.md depth, README clarity, reference quality
Code Quality	25%	Complexity, error handling, output consistency
Completeness	25%	Required files, sample data, expected outputs
Usability	25%	Argparse help text, example clarity, ease of setup

Grades: A+ (97+) through F (<40). Exit code 0 for A+ through C-, exit code 2 for D, exit code 1 for F.

维度	权重	评估项
文档	25%	SKILL.md深度、README清晰度、参考资料质量
代码质量	25%	复杂度、错误处理、输出一致性
完整性	25%	必填文件、样例数据、预期输出
易用性	25%	Argparse帮助文本、示例清晰度、配置简易度

等级划分： A+（97分及以上）到F（40分以下）。A+到C-返回退出码0，D返回退出码2，F返回退出码1。

CI/CD Integration

CI/CD集成

yaml

undefined

yaml

undefined

GitHub Actions example

GitHub Actions示例

name: Validate Changed Skills run: | for skill in $(git diff --name-only | grep -E '^engineering/[^/]+/' | cut -d'/' -f1-2 | sort -u); do python engineering/skill-tester/scripts/skill_validator.py $skill --json python engineering/skill-tester/scripts/script_tester.py $skill python engineering/skill-tester/scripts/quality_scorer.py $skill --minimum-score 75 done

---

name: 校验变更的Skill run: | for skill in $(git diff --name-only | grep -E '^engineering/[^/]+/' | cut -d'/' -f1-2 | sort -u); do python engineering/skill-tester/scripts/skill_validator.py $skill --json python engineering/skill-tester/scripts/script_tester.py $skill python engineering/skill-tester/scripts/quality_scorer.py $skill --minimum-score 75 done

---

Anti-Patterns

反模式

Padding SKILL.md with filler -- line count thresholds measure substantive content; blank lines and boilerplate do not count
External imports disguised as stdlib -- the import allowlist is manually maintained; if a legit stdlib module is flagged, add it to
```
stdlib_modules
```
Missing argparse help strings -- usability scoring requires
```
help=
```
parameters on every argument; empty help strings score zero
No
__main__
guard -- scripts without
```
if __name__ == "__main__"
```
fail runtime tests when imported
Relying on SKILL.md for usability -- usability is scored from scripts and README independently; a detailed SKILL.md does not compensate for missing
```
--help
```
output

SKILL.md填充无效内容 -- 行数门槛统计的是实质性内容，空行和模板内容不计入统计
将外部导入伪装成stdlib模块 -- 导入允许列表是手动维护的，如果合法的stdlib模块被误标记，可以将其添加到
```
stdlib_modules
```
列表
缺失argparse帮助字符串 -- 易用性评分要求每个参数都配置
```
help=
```
参数，空帮助字符串得分为0
没有
__main__
防护 -- 没有
```
if __name__ == "__main__"
```
的脚本被导入时会运行时测试失败
依赖SKILL.md保障易用性 -- 易用性是独立根据脚本和README评分的，详细的SKILL.md不能弥补
```
--help
```
输出缺失的问题

Troubleshooting

故障排查

Problem	Cause	Solution
`SKILL.md too short` error despite sufficient content	Validator counts only non-blank lines; blank lines inflate raw line count but are excluded from the tally	Remove excessive blank lines or add more substantive content sections to meet the tier threshold
YAML frontmatter parse failure	Frontmatter contains invalid YAML syntax (unquoted colons, tabs instead of spaces, missing closing `---` )	Validate frontmatter through `yaml.safe_load()` locally; ensure the closing `---` marker is present on its own line
External import false positive	The stdlib module allowlist in `skill_validator.py` and `script_tester.py` is manually maintained and may not include every standard library module	Add the missing module name to the `stdlib_modules` set in the relevant script, or restructure the import
Script execution timeout during testing	Script requires interactive input, enters an infinite loop, or performs long-running computation	Increase `--timeout` value, add early-exit logic for missing arguments, or ensure scripts exit cleanly when no input is provided
Tier compliance check fails despite passing individual checks	`_validate_tier_compliance` only examines `skill_md_exists` , `min_scripts_count` , and `skill_md_length` ; other failures (e.g., missing directories) are reported separately	Fix the specific critical checks listed in the error message; review the `TIER_REQUIREMENTS` dictionary for the target tier
Quality scorer reports low usability despite good documentation	Usability dimension scores help text inside scripts, `README.md` usage sections, and practical example files independently of SKILL.md content	Add `argparse` help strings with `help=` parameters, include a `Usage` section in README.md, and place sample/example files in the `assets/` directory
`--json` flag produces no output	Script raised an unhandled exception before reaching the output formatter; errors are written to stderr	Run with `--verbose` to see the full traceback on stderr, then address the underlying exception

问题	原因	解决方案
内容足够但提示 `SKILL.md too short` 错误	校验器仅统计非空行，空行会增加原始行数但不计入统计	删除过多空行，或添加更多实质性内容章节以满足层级门槛
YAML前置元数据解析失败	前置元数据包含无效YAML语法（未加引号的冒号、用制表符代替空格、缺失闭合 `---` ）	本地通过 `yaml.safe_load()` 校验前置元数据，确保闭合 `---` 标记单独占一行
外部导入误报	`skill_validator.py` 和 `script_tester.py` 中的stdlib模块允许列表是手动维护的，可能未包含所有标准库模块	将缺失的模块名添加到对应脚本的 `stdlib_modules` 集合中，或调整导入结构
测试期间脚本执行超时	脚本需要交互式输入、进入无限循环或执行长时间计算	增大 `--timeout` 值、为缺失参数场景添加提前退出逻辑，或确保无输入时脚本可以正常退出
单个检查都通过但层级合规检查失败	`_validate_tier_compliance` 仅检查 `skill_md_exists` 、 `min_scripts_count` 和 `skill_md_length` ，其他失败项（如缺失目录）会单独上报	修复错误消息中列出的特定关键检查项，查看目标层级的 `TIER_REQUIREMENTS` 字典确认要求
文档完善但质量评分器提示易用性得分低	易用性维度独立评估脚本内的帮助文本、 `README.md` 使用章节和实际示例文件，与SKILL.md内容无关	为 `argparse` 参数添加带 `help=` 属性的帮助字符串，在README.md中添加 `Usage` 章节，将样例/示例文件放在 `assets/` 目录下
`--json` 参数无输出	脚本在到达输出格式化代码前触发了未处理异常，错误会输出到stderr	加上 `--verbose` 参数运行查看stderr的完整回溯信息，修复底层异常

Success Criteria

成功标准

Structure pass rate above 95%: Validated skills pass all required-file and directory-structure checks on first run in at least 95% of cases.
Script syntax zero-defect: Every Python script in a validated skill compiles without
```
SyntaxError
```
via
```
ast.parse()
```
.
Standard library compliance 100%: No external (non-stdlib) imports detected across all validated scripts.
Quality score consistency within 5 points: Re-running
```
quality_scorer.py
```
on an unchanged skill produces scores that vary by no more than 5 points across runs.
Execution time under 10 seconds per skill: Full validation, testing, and scoring pipeline completes in under 10 seconds for a single skill with up to 3 scripts.
Actionable recommendation density: Every skill scoring below 75/100 receives at least 3 prioritized improvement suggestions in the roadmap.
CI/CD gate reliability: When integrated as a GitHub Actions step, the tool exits with non-zero status for every skill that fails critical checks, blocking the merge.

结构通过率高于95%： 至少95%的已校验skill首次运行即可通过所有必填文件和目录结构检查
脚本语法零缺陷： 已校验skill中的所有Python脚本都可以通过
```
ast.parse()
```
编译，无
```
SyntaxError
```
标准库合规率100%： 所有已校验脚本中未检测到外部（非stdlib）导入
质量评分波动在5分以内： 对未改动的skill重复运行
```
quality_scorer.py
```
，多次评分差值不超过5分
单skill执行时间低于10秒： 对最多包含3个脚本的单个skill，完整校验、测试、评分流程可在10秒内完成
可操作建议密度： 所有评分低于75/100的skill，路线图中至少包含3条优先级排序的改进建议
CI/CD门禁可靠性： 作为GitHub Actions步骤集成时，所有未通过关键检查的skill都会触发非零退出码，阻止合并

Scope & Limitations

适用范围与限制

Covers:

Structural validation of skill directories against tier-specific requirements (BASIC, STANDARD, POWERFUL)
Static analysis of Python scripts including syntax checking, import validation, argparse detection, and main guard verification
Multi-dimensional quality scoring across documentation, code quality, completeness, and usability
Dual output formatting (JSON for CI/CD pipelines, human-readable for developer consumption)

Does NOT cover:

Functional correctness of script logic or algorithm accuracy — the tester verifies structure and conventions, not business logic
Performance benchmarking or memory profiling of scripts — see
```
engineering/performance-profiler
```
for runtime analysis
Security vulnerability scanning of script code — see
```
engineering/skill-security-auditor
```
for dependency and code security audits
Cross-skill dependency resolution or integration testing — skills are validated in isolation without verifying inter-skill compatibility

覆盖范围：

针对skill目录按层级要求（BASIC、STANDARD、POWERFUL）进行结构校验
Python脚本静态分析，包括语法检查、导入校验、argparse检测、主函数防护验证
多维度质量评分，覆盖文档、代码质量、完整性、易用性
双输出格式（JSON适配CI/CD流水线，可读格式适配开发者使用）

不覆盖范围：

脚本逻辑的功能正确性或算法准确性 -- 测试工具仅校验结构和规范，不校验业务逻辑
脚本的性能基准测试或内存分析 -- 运行时分析请参考
```
engineering/performance-profiler
```
脚本代码的安全漏洞扫描 -- 依赖和代码安全审计请参考
```
engineering/skill-security-auditor
```
跨skill依赖解析或集成测试 -- skill是隔离校验的，不验证skill间的兼容性

Integration Points

集成点

Skill	Integration	Data Flow
`engineering/skill-security-auditor`	Run security audit after validation passes	`skill_validator.py` confirms structure compliance, then `skill-security-auditor` scans for vulnerabilities in the same skill path
`engineering/ci-cd-pipeline-builder`	Embed skill-tester as a quality gate stage	Pipeline builder generates workflow YAML that invokes `skill_validator.py` , `script_tester.py` , and `quality_scorer.py` sequentially
`engineering/changelog-generator`	Feed quality score deltas into changelog entries	Compare `quality_scorer.py` JSON output between releases to surface quality improvements or regressions
`engineering/pr-review-expert`	Attach validation report to pull request reviews	`skill_validator.py --json` output is posted as a PR comment for reviewer context
`engineering/performance-profiler`	Complement structural testing with runtime profiling	After `script_tester.py` confirms execution succeeds, `performance-profiler` measures execution time and resource usage
`engineering/tech-debt-tracker`	Track quality score trends over time	Periodic `quality_scorer.py --json` output is ingested to detect score degradation and flag technical debt

Skill	集成方式	数据流
`engineering/skill-security-auditor`	校验通过后运行安全审计	`skill_validator.py` 确认结构合规后， `skill-security-auditor` 扫描同一路径下的skill漏洞
`engineering/ci-cd-pipeline-builder`	将skill-tester嵌入为质量门禁阶段	流水线生成器生成工作流YAML，按顺序调用 `skill_validator.py` 、 `script_tester.py` 和 `quality_scorer.py`
`engineering/changelog-generator`	将质量评分差值输入变更日志条目	对比版本间 `quality_scorer.py` 的JSON输出，展示质量提升或降级情况
`engineering/pr-review-expert`	将校验报告附加到PR评审中	`skill_validator.py --json` 的输出作为PR评论发布，为评审者提供上下文
`engineering/performance-profiler`	运行时分析作为结构测试的补充	`script_tester.py` 确认执行成功后， `performance-profiler` 测量执行时间和资源占用
`engineering/tech-debt-tracker`	跟踪长期质量评分趋势	定期采集 `quality_scorer.py --json` 的输出，检测评分下降并标记技术债务

Tool Reference

工具参考

skill_validator.py

Purpose: Validates a skill directory's structure, documentation, and Python scripts against the claude-skills ecosystem standards. Checks required files, YAML frontmatter, required SKILL.md sections, directory layout, script syntax, import compliance, and tier-specific requirements.

Usage:

bash

python skill_validator.py <skill_path> [--tier TIER] [--json] [--verbose]

Parameters:

Parameter	Type	Required	Default	Description
`skill_path`	positional	Yes	—	Path to the skill directory to validate
`--tier`	option	No	None	Target tier for validation: `BASIC` , `STANDARD` , or `POWERFUL`
`--json`	flag	No	Off	Output results in JSON format instead of human-readable text
`--verbose`	flag	No	Off	Enable verbose logging to stderr

Example:

bash

python skill_validator.py engineering/my-skill --tier POWERFUL --json

Output Formats:

Human-readable (default): Grouped report with STRUCTURE VALIDATION, SCRIPT VALIDATION, ERRORS, WARNINGS, and SUGGESTIONS sections. Displays overall score out of 100 with compliance level (EXCELLENT, GOOD, ACCEPTABLE, NEEDS_IMPROVEMENT, POOR).

JSON (
--json
): Object with keys

skill_path

timestamp

overall_score

compliance_level

checks

(dict of check name to pass/message/score),

warnings

errors

suggestions

Exit codes:

on success (score >= 60 and no errors),

on failure.

用途： 对照claude-skills生态标准校验skill目录的结构、文档和Python脚本，检查必填文件、YAML前置元数据、SKILL.md必填章节、目录布局、脚本语法、导入合规性和层级特定要求。

用法：

bash

python skill_validator.py <skill_path> [--tier TIER] [--json] [--verbose]

参数：

参数	类型	必填	默认值	说明
`skill_path`	位置参数	是	—	待校验的skill目录路径
`--tier`	选项	否	None	校验目标层级： `BASIC` 、 `STANDARD` 或 `POWERFUL`
`--json`	标记	否	关闭	输出JSON格式结果而非人类可读文本
`--verbose`	标记	否	关闭	启用输出到stderr的详细日志

示例：

bash

python skill_validator.py engineering/my-skill --tier POWERFUL --json

输出格式：

人类可读（默认）： 分组报告，包含结构校验、脚本校验、错误、警告、建议章节，展示满分100的整体评分和合规等级（优秀、良好、可接受、需改进、较差）
JSON（
--json
）：包含以下键的对象：
```
skill_path
```
、
```
timestamp
```
、
```
overall_score
```
、
```
compliance_level
```
、
```
checks
```
（检查项名称到通过状态/消息/得分的映射）、
```
warnings
```
、
```
errors
```
、
```
suggestions
```

退出码： 成功（评分≥60且无错误）返回

，失败返回

script_tester.py

Purpose: Tests all Python scripts within a skill's

scripts/

directory. Performs syntax validation via AST parsing, import analysis for stdlib compliance, argparse implementation verification, main guard detection, runtime execution with timeout protection,

--help

functionality testing, sample data processing against files in

assets/

, and output format compliance checks.

Usage:

bash

python script_tester.py <skill_path> [--timeout SECONDS] [--json] [--verbose]

Parameters:

Parameter	Type	Required	Default	Description
`skill_path`	positional	Yes	—	Path to the skill directory containing scripts to test
`--timeout`	option	No	`30`	Timeout in seconds for each script execution test
`--json`	flag	No	Off	Output results in JSON format instead of human-readable text
`--verbose`	flag	No	Off	Enable verbose logging to stderr

Example:

bash

python script_tester.py engineering/my-skill --timeout 60 --json

Output Formats:

Human-readable (default): Report with SUMMARY (total/passed/partial/failed counts), GLOBAL ERRORS, and per-script sections showing status, execution time, individual test results, errors, and warnings.

JSON (
--json
): Object with keys

skill_path

timestamp

summary

(counts and overall status),

global_errors

script_results

(dict per script with

overall_status

execution_time

tests

errors

warnings

Exit codes:

on full success,

on failure or global errors,

on partial success.

用途： 测试skill的

scripts/

目录下所有Python脚本，通过AST解析进行语法校验、stdlib合规性导入分析、argparse实现验证、主函数防护检测、带超时保护的运行时执行、

--help

功能测试、针对

assets/

目录文件的样例数据处理、输出格式合规性检查。

用法：

bash

python script_tester.py <skill_path> [--timeout SECONDS] [--json] [--verbose]

参数：

参数	类型	必填	默认值	说明
`skill_path`	位置参数	是	—	包含待测试脚本的skill目录路径
`--timeout`	选项	否	`30`	每个脚本执行测试的超时时间（秒）
`--json`	标记	否	关闭	输出JSON格式结果而非人类可读文本
`--verbose`	标记	否	关闭	启用输出到stderr的详细日志

示例：

bash

python script_tester.py engineering/my-skill --timeout 60 --json

输出格式：

人类可读（默认）： 报告包含摘要（总数/通过数/部分通过数/失败数）、全局错误、每个脚本的状态、执行时间、单个测试结果、错误和警告
JSON（
--json
）：包含以下键的对象：
```
skill_path
```
、
```
timestamp
```
、
```
summary
```
（计数和整体状态）、
```
global_errors
```
、
```
script_results
```
（每个脚本的映射，包含
```
overall_status
```
、
```
execution_time
```
、
```
tests
```
、
```
errors
```
、
```
warnings
```
）

退出码： 完全成功返回

，失败或全局错误返回

，部分成功返回

quality_scorer.py

Purpose: Provides a comprehensive multi-dimensional quality assessment for a skill. Evaluates four equally weighted dimensions — Documentation (25%), Code Quality (25%), Completeness (25%), and Usability (25%) — and produces an overall score, letter grade (A+ through F), tier recommendation, and a prioritized improvement roadmap.

Usage:

bash

python quality_scorer.py <skill_path> [--detailed] [--minimum-score SCORE] [--json] [--verbose]

Parameters:

Parameter	Type	Required	Default	Description
`skill_path`	positional	Yes	—	Path to the skill directory to assess
`--detailed`	flag	No	Off	Show detailed component scores within each dimension
`--minimum-score`	option	No	`0`	Minimum acceptable overall score; exits with error code `1` if the score falls below this threshold
`--json`	flag	No	Off	Output results in JSON format instead of human-readable text
`--verbose`	flag	No	Off	Enable verbose logging to stderr

Example:

bash

python quality_scorer.py engineering/my-skill --detailed --minimum-score 75 --json

Output Formats:

Human-readable (default): Report with overall score and letter grade, per-dimension scores with weights, summary statistics (highest/lowest dimension, dimensions above 70%, dimensions below 50%), and a prioritized improvement roadmap (up to 5 items with HIGH/MEDIUM/LOW priority). When
```
--detailed
```
is used, component-level breakdowns appear under each dimension.
JSON (
--json
): Object with keys
```
skill_path
```
,
```
timestamp
```
,
```
overall_score
```
,
```
letter_grade
```
,
```
tier_recommendation
```
,
```
summary_stats
```
,
```
dimensions
```
(per-dimension name/weight/score/details/suggestions),
```
improvement_roadmap
```
(list of priority/dimension/suggestion/current_score objects).

Exit codes:

for grades A+ through C-,

for grade F or when score is below

--minimum-score

for grade D.

用途： 为skill提供全面的多维度质量评估，评估四个权重相同的维度 -- 文档（25%）、代码质量（25%）、完整性（25%）、易用性（25%），生成整体评分、字母等级（A+到F）、层级推荐和优先级排序的改进路线图。

用法：

bash

python quality_scorer.py <skill_path> [--detailed] [--minimum-score SCORE] [--json] [--verbose]

参数：

参数	类型	必填	默认值	说明
`skill_path`	位置参数	是	—	待评估的skill目录路径
`--detailed`	标记	否	关闭	展示每个维度下的组件级详细评分
`--minimum-score`	选项	否	`0`	最低可接受整体评分，评分低于该阈值时返回错误码 `1`
`--json`	标记	否	关闭	输出JSON格式结果而非人类可读文本
`--verbose`	标记	否	关闭	启用输出到stderr的详细日志

示例：

bash

python quality_scorer.py engineering/my-skill --detailed --minimum-score 75 --json

输出格式：

人类可读（默认）： 报告包含整体评分和字母等级、带权重的各维度得分、统计摘要（最高/最低维度、70分以上维度、50分以下维度）、优先级排序的改进路线图（最多5项，分为高/中/低优先级）。使用
```
--detailed
```
参数时，每个维度下会展示组件级明细
JSON（
--json
）：包含以下键的对象：
```
skill_path
```
、
```
timestamp
```
、
```
overall_score
```
、
```
letter_grade
```
、
```
tier_recommendation
```
、
```
summary_stats
```
、
```
dimensions
```
（每个维度的名称/权重/得分/明细/建议）、
```
improvement_roadmap
```
（优先级/维度/建议/当前得分对象列表）

退出码： 等级A+到C-返回

，等级F或评分低于

--minimum-score

，等级D返回