点网

人工智能 社区

技能解读

当前原文的自动摘译,尚未人工审校。

何时使用此技能

不断地使用这个技能。每次 LLM(包括 Claude)对以下内容进行更改时: C# 源文件 (.cs) 项目文件 (.csproj) Props 文件(Directory.Build.props、Directory.Packages.props) 测试文件

什么是坡度?

“Slop”是指法学硕士在没有真正解决根本问题的情况下使测试通过或构建成功的捷径。这些都是奖励黑客行为——法学硕士针对表面上的成功进行优化,而不是真正的修复。

常见的坡度模式

模式 · 示例 · 为什么不好 禁用测试 · [Fact(Skip="flaky")] · 隐藏故障而不是修复它们 警告抑制 · #pragma warning disable CS8618 · 沉默编译器而不修复问题 空 catch 块 · catch (Exception) { } · 吞没错误,隐藏错误 任意延迟 · await Task.Delay(1000); · 掩盖竞争条件,使测试变慢

作为本地工具(推荐)

添加到.config/dotnet-tools.json:然后恢复:

首次设置:建立基线

在现有项目上使用 slopwatch 之前,请创建当前问题的基线:为什么要创建基线?旧代码可能存在问题。基线确保 slopwatch 只捕获引入的新 slop,而不是预先存在的技术债务。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
人工智能
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@Aaronontheweb · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
Linux
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Slopwatch: LLM Anti-Cheat for .NET

## When to Use This Skill

**Use this skill constantly.** Every time an LLM (including Claude) makes changes to:
- C# source files (.cs)
- Project files (.csproj)
- Props files (Directory.Build.props, Directory.Packages.props)
- Test files

Run slopwatch to validate the changes don't introduce "slop."

## What is Slop?

"Slop" refers to shortcuts LLMs take that make tests pass or builds succeed without actually solving the underlying problem. These are reward hacking behaviors - the LLM optimizes for apparent success rather than real fixes.

### Common Slop Patterns

| Pattern | Example | Why It's Bad |
|---------|---------|--------------|
| Disabled tests | `[Fact(Skip="flaky")]` | Hides failures instead of fixing them |
| Warning suppression | `#pragma warning disable CS8618` | Silences compiler without fixing issue |
| Empty catch blocks | `catch (Exception) { }` | Swallows errors, hides bugs |
| Arbitrary delays | `await Task.Delay(1000);` | Masks race conditions, makes tests slow |
| Project-level suppression | `<NoWarn>CS1591</NoWarn>` | Disables warnings project-wide |
| CPM bypass | `Version="1.0.0"` inline | Undermines central package management |

**Never accept these patterns.** If an LLM introduces slop, reject the change and require a proper fix.

---

## Installation

### As a Local Tool (Recommended)

Add to `.config/dotnet-tools.json`:

```json
{
  "version": 1,
  "isRoot": true,
  "tools": {
    "slopwatch.cmd": {
      "version": "0.2.0",
      "commands": ["slopwatch"],
      "rollForward": false
    }
  }
}
```

Then restore:
```bash
dotnet tool restore
```

### As a Global Tool

```bash
dotnet tool install --global Slopwatch.Cmd
```

---

## First-Time Setup: Establish a Baseline

Before using slopwatch on an existing project, create a baseline of current issues:

```bash
# Initialize baseline from existing code
slopwatch init

# This creates .slopwatch/baseline.json
git add .slopwatch/baseline.json
git commit -m "Add slopwatch baseline"
```

**Why baseline?** Legacy code may have existing issues. The baseline ensures slopwatch only catches **new** slop being introduced, not pre-existing technical debt.

---

## Usage During LLM Sessions

### After Every Code Change

Run slopwatch after any LLM-generated code modification:

```bash
# Analyze for new issues (uses baseline)
slopwatch analyze

# Use strict mode - fail on warnings too
slopwatch analyze --fail-on warning
```

### When Slopwatch Flags an Issue

**Do not ignore it.** Instead:

1. **Understand why** the LLM took the shortcut
2. **Request a proper fix** - be specific about what's wrong
3. **Verify the fix** doesn't introduce different slop

```
# Example: LLM disabled a test
❌ SW001 [Error]: Disabled test detected
   File: tests/MyApp.Tests/OrderTests.cs:45
   Pattern: [Fact(Skip="Test is flaky")]

# Correct response: Ask for actual fix
"This test was disabled instead of fixed. Please investigate why
it's flaky and fix the underlying timing/race condition issue."
```

### Updating the Baseline (Rare)

Only update the baseline when slop is **truly justified** and documented:

```bash
# Add current detections to baseline (use sparingly!)
slopwatch analyze --update-baseline
```

**Justification examples:**
- Third-party library forces a pattern (e.g., must suppress specific warning)
- Intentional delay for rate limiting (not test flakiness)
- Generated code that can't be modified

Document why in a code comment when updating baseline.

---

## Claude Code Hook Integration

Add slopwatch as a hook to automatically validate every edit. Create or update `.claude/settings.json`:

```json
{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write|Edit|MultiEdit",
        "hooks": [
          {
            "type": "command",
            "command": "slopwatch analyze -d . --hook",
            "timeout": 60000
          }
        ]
      }
    ]
  }
}
```

The `--hook` flag:
- Only analyzes **git dirty files** (fast, even on large repos)
- Outputs errors to stderr in readable format
- Blocks the edit on warnings/errors (exit code 2)
- Claude sees the error and can fix it immediately

---

## CI/CD Integration

Add slopwatch to your CI pipeline as a quality gate:

### GitHub Actions

```yaml
jobs:
  slopwatch:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Setup .NET
        uses: actions/setup-dotnet@v4
        with:
          dotnet-version: '9.0.x'

      - name: Install Slopwatch
        run: dotnet tool install --global Slopwatch.Cmd

      - name: Run Slopwatch
        run: slopwatch analyze -d . --fail-on warning
```

### Azure Pipelines

```yaml
- task: DotNetCoreCLI@2
  displayName: 'Install Slopwatch'
  inputs:
    command: 'custom'
    custom: 'tool'
    arguments: 'install --global Slopwatch.Cmd'

- script: slopwatch analyze -d . --fail-on warning
  displayName: 'Slopwatch Analysis'
```

---

## Detection Rules

| Rule | Severity | What It Catches |
|------|----------|-----------------|
| SW001 | Error | Disabled tests (`Skip=`, `Ignore`, `#if false`) |
| SW002 | Warning | Warning suppression (`#pragma warning disable`, `SuppressMessage`) |
| SW003 | Error | Empty catch blocks that swallow exceptions |
| SW004 | Warning | Arbitrary delays in tests (`Task.Delay`, `Thread.Sleep`) |
| SW005 | Warning | Project file slop (`NoWarn`, `TreatWarningsAsErrors=false`) |
| SW006 | Warning | CPM bypass (`VersionOverride`, inline `Version` attributes) |

---

## Configuration

Create `.slopwatch/slopwatch.json` to customize:

```json
{
  "minSeverity": "warning",
  "rules": {
    "SW001": { "enabled": true, "severity": "error" },
    "SW002": { "enabled": true, "severity": "warning" },
    "SW003": { "enabled": true, "severity": "error" },
    "SW004": { "enabled": true, "severity": "warning" },
    "SW005": { "enabled": true, "severity": "warning" },
    "SW006": { "enabled": true, "severity": "warning" }
  },
  "exclude": [
    "**/Generated/**",
    "**/obj/**",
    "**/bin/**"
  ]
}
```

### Strict Mode (Recommended for LLM Sessions)

For maximum protection during LLM coding sessions, elevate all rules to errors:

```json
{
  "minSeverity": "warning",
  "rules": {
    "SW001": { "enabled": true, "severity": "error" },
    "SW002": { "enabled": true, "severity": "error" },
    "SW003": { "enabled": true, "severity": "error" },
    "SW004": { "enabled": true, "severity": "error" },
    "SW005": { "enabled": true, "severity": "error" },
    "SW006": { "enabled": true, "severity": "error" }
  }
}
```

---

## The Philosophy: Zero Tolerance for New Slop

1. **Baseline captures legacy** - Existing issues are acknowledged but isolated
2. **New slop is blocked** - Any new shortcut fails the build/edit
3. **Exceptions require justification** - If you must update baseline, document why
4. **LLMs are not special** - The same rules apply to human and AI-generated code

The goal is to prevent the gradual accumulation of technical debt that occurs when LLMs optimize for "make the test pass" rather than "fix the actual problem."

---

## Quick Reference

```bash
# First time setup
slopwatch init
git add .slopwatch/baseline.json

# After every LLM code change
slopwatch analyze

# Strict mode (recommended)
slopwatch analyze --fail-on warning

# With stats (performance debugging)
slopwatch analyze --stats

# Update baseline (rare, document why)
slopwatch analyze --update-baseline

# JSON output for tooling
slopwatch analyze --output json
```

---

## When to Override (Almost Never)

The only valid reasons to update baseline or disable a rule:

| Scenario | Action | Required |
|----------|--------|----------|
| Third-party forces pattern | Update baseline | Code comment explaining why |
| Generated code (not editable) | Add to exclude list | Document in config |
| Intentional rate limiting delay | Update baseline | Code comment, not in test |
| Legacy code cleanup | One-time baseline update | PR description |

**Invalid reasons:**
- "The test is flaky" → Fix the flakiness
- "The warning is annoying" → Fix the code
- "It works on my machine" → Fix the race condition
- "We'll fix it later" → Fix it now

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。