Token导航 LogoToken导航

Agent Skill · 研究检索

test-reviewer(测试评审员)

用于辅助测试设计、自动化测试、用例整理和回归验证。它适合让 Agent 编写单元测试、端到端测试、测试计划或根据失败日志定位问题。使用时需要确认项目测试框架、运行命令和夹具数据,避免为了通过测试而改坏真实逻辑;涉及浏览器或外部服务时,应区分本地模拟、测试环境和生产环境。

test-reviewer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 71,596。

总安装 194周安装 8GitHub Stars 37下载 63核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:test-reviewer(测试评审员)
来源仓库:https://github.com/majesticlabs-dev/majestic-marketplace
仓库路径:skills/test-reviewer
安装命令:
npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill test-reviewer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill test-reviewer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于辅助测试设计、自动化测试、用例整理和回归验证。适合编写单元测试、端到端测试、测试计划或根据失败日志定位问题。使用时需确认项目测试框架、运行命令和夹具数据,避免修改真实逻辑。涉及浏览器或外部服务时,应区分本地模拟、测试环境和生产环境。安装方式:通过 npx skills add 命令从指定 GitHub 仓库添加。

来源仓库内路径:skills/test-reviewer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

test-reviewer 怎么安装?

在终端执行 npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill test-revie…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

test-reviewer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

test-reviewer 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

test-reviewer 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

test-reviewer 用的人多吗?

公开数据是累计安装 194 次,近一周安装 8 次,下载 63 次,GitHub 37 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

test-reviewer 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
test-reviewer

测试评审员 · 本页

19437操作浏览器未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Test Reviewer

Audience: Developers reviewing test suites for quality and completeness.

Goal: Analyze automated tests for coverage completeness, assertion quality, and adherence to testing best practices.

Review Steps

1. Identify Test Context

  • Run git status and git diff to identify changed files and their corresponding test files
  • Use Grep and Glob to locate test files related to the changed code
  • Identify the testing framework (RSpec, Minitest, Jest, Playwright)

2. Map Implementation to Tests

  • Read the implementation files being tested
  • Identify all public methods, endpoints, and behaviors that should have test coverage
  • Create a coverage matrix mapping implementation features to test cases

3. Analyze Test Coverage

For each implementation feature, check if tests exist for:

  • Happy Path: Normal successful execution flows
  • Sad Path: Error conditions, validation failures, edge cases
  • Boundary Conditions: Empty values, nil/null, maximum limits
  • State Transitions: Before/after states, side effects
  • Authorization: Permission checks (if applicable)
  • Integration Points: External service calls, database operations

4. Evaluate Test Quality

  • Assertion Quality:

- Are assertions specific and meaningful? - Do tests verify behavior, not implementation? - Are error messages helpful for debugging?

  • Test Isolation:

- Do tests depend on execution order? - Are external services properly mocked? - Is test data properly set up and torn down?

  • AAA Pattern:

- Clear Arrange (setup) section - Single Act (execution) - Focused Assert (verification)

  • Test Names:

- Do names describe expected behavior? - Would someone understand the test without reading code?

5. Check Test Patterns

  • Framework Compliance:

- RSpec: Proper use of describe, context, it, let, before - Minitest: Proper use of setup, test, fixtures - Jest: Proper use of describe, it, beforeEach, mocks

  • Project Conventions:

- Do tests follow existing patterns in the codebase? - Are shared examples/contexts used where appropriate? - Is test data handled consistently (fixtures vs factories)?

6. Identify Missing Scenarios

Look for common gaps:

  • Nil/Empty Handling: What happens with nil, empty strings, empty arrays?
  • Error Cases: Network failures, database errors, validation failures
  • Concurrency: Race conditions, parallel execution
  • Edge Cases: First/last items, exactly at limits, off-by-one
  • Security: Input sanitization, authorization bypasses
  • Performance: Large data sets, timeout scenarios

7. Check for Test Anti-Patterns

  • Skipped/pending tests without justification
  • Tests with sleep or hardcoded delays (flaky test smell)
  • Tests with non-deterministic data (random values without seeds)
  • Over-reliance on allow_any_instance_of or similar broad mocks

Note: This skill performs static analysis only. Test execution is handled separately to avoid redundant test runs.

Red Flags to Watch For:

  • Tests that always pass (no real assertions)
  • Tests that test Rails/framework behavior, not application code
  • Overly complex test setup indicating design issues
  • Mocking too much (testing mocks, not real behavior)
  • No error case coverage
  • Tests tightly coupled to implementation details
  • Missing database state verification
  • Frozen fixture assertions: Exact collection comparisons (assert_equal [a, b], scope or expect(scope).to eq([a, b])) that break when unrelated fixtures are added. Recommend assert_includes/expect(...).to include(...) instead.

Test Quality Review Report

Provide your findings in this structure:

Test Coverage Summary

  • Implementation Files Reviewed: [count]
  • Test Files Reviewed: [count]
  • Coverage Gaps Identified: [count]
  • Quality Issues Found: [count]

Coverage Matrix

Feature/MethodHappy PathSad PathEdge CasesStatus
[method_name]pass/failpass/failpass/fail[Complete/Gaps]

Critical Coverage Gaps

[List features/methods with missing test coverage, prioritized by risk]

  1. [Feature/Method Name] - [file:line]

- Missing: [what scenarios are not tested] - Risk: [why this gap matters] - Recommended: [specific test to add]

Test Quality Issues

High Priority:

  • [Issue description with file:line reference]
  • Recommendation: [how to fix]

Medium Priority:

  • [Issue description]
  • Recommendation: [how to fix]

Low Priority:

  • [Issue description]
  • Recommendation: [how to fix]

Missing Edge Cases

[List specific edge case scenarios that should be tested]

  1. [Scenario]: [why it matters] → [file to add test]

Pattern Violations

[Tests that don't follow project conventions or best practices]

Recommendations

  1. [Prioritized actionable recommendations]
  2. [Include specific test examples where helpful]
  3. [Reference project patterns to follow]

Overall Assessment

  • Test Suite Health: [Excellent/Good/Needs Work/Critical Gaps]
  • Confidence Level: [High/Medium/Low] - Can we ship with current tests?
  • Priority Actions: [Top 3 things to fix before merging]

Note: All file paths should be absolute. Focus on actionable feedback that improves test quality and coverage.

平台分布

Codex

33.7%
按下载量换算21

Claude

28.84%
按下载量换算18

Cursor

19.49%
按下载量换算12

Gemini CLI

8.27%
按下载量换算5

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills