cpp-testing
Official仅用于编写/更新/修复C++测试、配置GoogleTest/CTest、诊断失败或不稳定的测试,或添加覆盖率/消毒器时使用。
What this skill does
When applied, it prepends a system prompt before your request is sent — no extra calls and no change to how you are billed beyond the added tokens.
---
name: cpp-testing
description: 仅用于编写/更新/修复C++测试、配置GoogleTest/CTest、诊断失败或不稳定的测试,或添加覆盖率/消毒器时使用。
origin: ECC
---
# C++ 测试(代理技能)
针对现代 C++(C++17/20)的代理导向测试工作流,使用 GoogleTest/GoogleMock 和 CMake/CTest。
## 使用时机
* 编写新的 C++ 测试或修复现有测试
* 为 C++ 组件设计单元/集成测试覆盖
* 添加测试覆盖、CI 门控或回归保护
* 配置 CMake/CTest 工作流以实现一致的执行
* 调查测试失败或偶发性行为
* 启用用于内存/竞态诊断的消毒剂
### 不适用时机
* 在不修改测试的情况下实现新的产品功能
* 与测试覆盖或失败无关的大规模重构
* 没有测试回归需要验证的性能调优
* 非 C++ 项目或非测试任务
## 核心概念
* **TDD 循环**:红 → 绿 → 重构(先写测试,最小化修复,然后清理)。
* **隔离**:优先使用依赖注入和仿制品,而非全局状态。
* **测试布局**:`tests/unit`、`tests/integration`、`tests/testdata`。
* **Mock 与 Fake**:Mock 用于交互,Fake 用于有状态行为。
* **CTest 发现**:使用 `gtest_discover_tests()` 进行稳定的测试发现。
* **CI 信号**:先运行子集,然后使用 `--output-on-failure` 运行完整套件。
## TDD 工作流
遵循 RED → GREEN → REFACTOR 循环:
1. **RED**:编写一个捕获新行为的失败测试
2. **GREEN**:实现最小的更改以使其通过
3. **REFACTOR**:在测试保持通过的同时进行清理
```cpp
// tests/add_test.cpp
#include <gtest/gtest.h>
int Add(int a, int b); // Provided by production code.
TEST(AddTest, AddsTwoNumbers) { // RED
EXPECT_EQ(Add(2, 3), 5);
}
// src/add.cpp
int Add(int a, int b) { // GREEN
return a + b;
}
// REFACTOR: simplify/rename once tests pass
```
## 代码示例
### 基础单元测试 (gtest)
```cpp
// tests/calculator_test.cpp
#include <gtest/gtest.h>
int Add(int a, int b); // Provided by production code.
TEST(CalculatorTest, AddsTwoNumbers) {
EXPECT_EQ(Add(2, 3), 5);
}
```
### 夹具 (gtest)
```cpp
// tests/user_store_test.cpp
// Pseudocode stub: replace UserStore/User with project types.
#include <gtest/gtest.h>
#include <memory>
#include <optional>
#include <string>
struct User { std::string name; };
class UserStore {
public:
explicit UserStore(std::string /*path*/) {}
void Seed(std::initializer_list<User> /*users*/) {}
std::optional<User> Find(const std::string &/*name*/) { return User{"alice"}; }
};
class UserStoreTest : public ::testing::Test {
protected:
void SetUp() override {
store = std::make_unique<UserStore>(":memory:");
store->Seed({{"alice"}, {"bob"}});
Use this skill
Add a "skill" field with the skill’s ID to your chat completion request. It is applied server-side before your prompt is sent — no extra calls.
{
"model": "gpt-4o-mini",
"skill": "imp-8025bd80-cf3e-42ae-b9c1-bca396b16d3f",
"messages": [{ "role": "user", "content": "…" }]
}Install the skill, enable it in your dashboard and (optionally) limit it to specific models. It then applies automatically to every matching request — with no "skill" field to send each time.
Set it up in your dashboardMore skills
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search and analyze your own session logs (older/parent conversations) using jq.
Create, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.
Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
List, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.
Create, search, and manage Bear notes via grizzly CLI.