Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

claude-code-skills-zh

skill · laolaoshiren/claude-code-skills-zhMIT licenceAudited 31 Oct 2026 · source 43b910b4e214

★ 899pushed 5 days ago
✓SAFEGrade B · 89/100 · 31 Oct 2026 · 43b910b
899repo stars · whole laolaoshiren/claude-code-skills-zh

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 43b910b4e214 and observed network access and no hard-coded secrets. What it does: 依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时;区分“生成测试”和“执行请求”的授权,不猜测状态码、响应结构或 SLA,不在未确认环境中发送写请求。

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “claude-code-skills-zh (laolaoshiren/claude-code-skills-zh)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/laolaoshiren/claude-code-skills-zh

Trust audit

Audit 0.4.1 · source read 31 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkDeclared2 observations
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS1
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

LOWInventory / provenanceinv.hidden_file · .markdownlint.json
F-13 Inventory / provenanceCWE-1104Layer L0
.markdownlint.json
Why
hidden member outside the usual dotfiles
Fix
review its purpose

Audit 0.4.1 · source sha 43b910b4e214 · 31 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherlaolaoshiren GitHub userOwner of the repository this skill is read from
  • Source folderlaolaoshiren/claude-code-skills-zhThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict43b910b4e214A new audit runs when the source changes
  • Repository statusNot archivedLast push 5 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: 依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时;区分“生成测试”和“执行请求”的授权,不猜测状态码、响应结构或 SLA,不在未确认环境中发送写请求。

---
name: api-tester
description: 依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时;区分“生成测试”和“执行请求”的授权,不猜测状态码、响应结构或 SLA,不在未确认环境中发送写请求。
---

# API 测试助手

## 核心原则

- 只把可核验的 OpenAPI、代码、类型、调用方或现有测试当作契约证据。
- 生成测试不等于执行测试;读取接口定义不等于可以访问真实服务。
- 保护现有数据、凭据和用户修改,优先使用隔离且可清理的测试环境。

## 工作流程

### 1. 读取项目与接口证据

先读取适用的仓库规则、测试说明、Git 状态和项目脚本,再按实际存在情况检查:

- OpenAPI / Swagger 文件及其引用的 Schema。
- 路由、controller、handler、DTO、验证器和错误处理中间件。
- 客户端类型、调用方、公开文档和现有 API 测试。
- 测试配置、fixture、认证方式、环境变量模板和数据清理机制。

记录规范、实现与现有测试之间的不一致。无法确定哪个行为才是期望契约时,列出证据并请求确认,不用新测试固化猜测。

### 2. 建立契约矩阵

为目标 endpoint 记录:

| 项目 | 证据 |
|------|------|
| method 与 path | OpenAPI 或路由位置 |
| 认证与权限 | security scheme、中间件或调用方 |
| 请求参数与约束 | Schema、DTO 或验证器 |
| 已声明响应 | 状态码、响应结构与 header |
| 副作用与幂等性 | 实现、文档或调用链 |
| 测试环境与清理 | fixture、事务或 teardown |

不要默认每个接口都应返回 `400`、`401`、`403`、`404`、`422` 或 `500`。只有契约已声明或代码路径真实可达时才生成对应断言。

### 3. 明确环境与授权

在执行任何请求前确认:

- Base URL、环境归属以及是否为 local、test、staging 或 production。
- 测试账号、权限范围和凭据来源。
- 是否允许执行 POST、PUT、PATCH、DELETE、上传、支付、通知等有副作用操作。
- 测试数据隔离、唯一标识、清理或事务回滚方案。

用户只要求“生成测试”时只产出代码。生产环境、共享 staging、第三方服务及任何可能改变真实数据的执行都必须获得明确授权。GET 也不能仅凭 method 判定无副作用。

### 4. 选择项目锁定的工具

- 优先运行仓库已有的 test、OpenAPI lint 或 contract test script。
- 读取 package manager、lockfile 和已安装版本后再选择命令。
- 不用裸 `npx`、全局工具或临时下载的最新版解析规范。
- 缺少依赖时先报告;安装工具、更新 lockfile 或修改测试配置需要单独授权。
- 使用真正的 YAML / JSON / OpenAPI 解析器,不用 `grep` 推断嵌套 Schema。

### 5. 设计有依据的用例

按目标契约选择必要场景:

- 成功路径:使用最小合法输入验证状态、结构和关键语义。
- 边界路径:只测试 Schema 或实现中真实存在的长度、范围、枚举、格式和必填约束。
- 认证与权限:只覆盖已声明的身份、角色和资源归属规则。
- 失败与回归:覆盖可达错误路径、已知缺陷或兼容性要求。
- 幂等、分页、并发、重试与超时:仅在接口契约包含这些语义时测试。

断言外部可观察行为,避免绑定内部函数调用。随机数据应固定 seed,并避免真实个人信息、客户数据和生产标识。

### 6. 实现最小测试

- 沿用项目现有框架、目录、fixture、命名和断言风格。
- 单元测试可隔离网络、时间和第三方服务;集成测试使用受控服务或临时资源。
- 对写操作使用唯一数据,并在成功、失败和中断路径都执行清理。
- 不为让测试通过而擅自修改生产代码、接口规范或认证配置。
- 使用跨平台路径和项目脚本;平台专属命令需说明 Windows / Linux 适用范围。

### 7. 执行与复验

1. 先检查命令是否会下载依赖、访问外部服务或改变共享状态。
2. 运行最小目标测试,记录命令、环境、退出状态和真实响应摘要。
3. 按风险运行相关测试、类型检查或完整测试。
4. 检查 Git diff 和环境状态,确认没有残留测试数据、快照、日志、Token 或无关生成物。
5. 将基线已有失败与本轮新增失败分开报告。

没有实际运行时,只能说明“已生成、未验证”。没有明确 SLA 和受控测量条件时,不添加固定耗时断言或声称性能达标。

## 安全边界

- 不在命令、日志、fixture 或报告中写入真实 Token、Cookie、密码和个人数据。
- 未经明确授权,不访问生产环境、真实客户账号、付费 API 或受监管系统。
- 压测、模糊测试、大批量数据生成和安全探测需要单独授权及限流方案。
- 遇到权限不足、环境不明、清理方案缺失或响应可能含敏感信息时停止执行并报告。

## 输出

```markdown
## API 测试结果

- 目标接口与契约证据:
- 环境与授权范围:
- 新增或修改文件:

## 用例

| 场景 | 契约依据 | 是否执行 | 结果 |
|------|----------|----------|------|

## 验证

- 实际命令与退出状态:
- 数据清理:
- 基线已有失败:
- 未确认契约与限制:
```

Excerpt, first 2,453 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 43b910b

Download folder ↗
git clone https://github.com/laolaoshiren/claude-code-skills-zh.git
git clone https://gh-proxy.com/https://github.com/laolaoshiren/claude-code-skills-zh.git

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 43b910b4e214 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
GitHub CopilotMentioned in its text, not testedSkills for GitHub Copilot · About GitHub Copilot
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
Gemini CLIMentioned in its text, not testedSkills for Gemini CLI · About Gemini CLI
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
WindsurfMentioned in its text, not testedSkills for Windsurf · About Windsurf
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 43b910b4e214

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/laolaoshiren/claude-code-skills-zh/badge.svg)](https://modelsatlas.com/skills/laolaoshiren/claude-code-skills-zh/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/laolaoshiren/claude-code-skills-zh/badge.svg)](https://modelsatlas.com/skills/laolaoshiren/claude-code-skills-zh/)

Questions about claude-code-skills-zh

What does the claude-code-skills-zh skill do?
面向中文开发者的 Claude Code Skills / Agents / Plugins 精选与原创技能库|按场景分类|复制即装|持续更新
Is claude-code-skills-zh safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can claude-code-skills-zh access on my machine?
The audit observed that it reaches the network. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does claude-code-skills-zh work with?
Its documentation mentions claude-code, codex, copilot, cursor, gemini-cli, openclaw and windsurf. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (43b910b4e214), read on 2026-10-31. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.