← 返回 Skills 市场
zlszhonglongshen

code-debug-companion

作者 zlszhonglongshen · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
64
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install code-debug-companion
功能描述
AI 驱动的智能代码调试助手,自动诊断错误、搜索解决方案、修复代码并验证。
使用说明 (SKILL.md)

Code Debug Companion - AI 智能代码调试助手

概述

这是一个完整的代码调试工作流,将错误捕获、解决方案研究、代码修复和测试验证串联起来,帮助开发者快速定位并解决 Bug。

工作流程

[错误信息/截图]
       ↓
[Code Review 分析错误原因]
       ↓
[Web Search 搜索类似问题/解决方案]
       ↓
[生成修复方案 + 单元测试]
       ↓
[写入修复代码 + 测试报告]

核心 Skill 编排

Skill 职责
code-review 分析错误类型、定位根因、识别代码问题
brave-search 搜索 StackOverflow/GitHub/文档中的类似问题
setup-unit-test 生成修复验证的单元测试用例
github-issues 有用的解决方案创建 Issue 跟踪

使用方法

场景 1:粘贴错误信息调试

调试以下错误:
TypeError: Cannot read property 'map' of undefined
  at Array.reduce (src/utils.ts:42:18)
  at processData (src/handlers.ts:15:7)

场景 2:截图调试

直接发送错误截图或终端输出,助手自动解析并开始调试流程。

场景 3:批量调试

粘贴整个错误堆栈,助手按优先级排序后逐个修复。

输出格式

修复完成后输出:

🐛 问题诊断:[错误类型 + 根因分析]
🔍 类似问题:搜索到 N 条相关讨论
✅ 修复方案:[具体修改内容]
🧪 测试用例:已生成 N 个测试覆盖此场景
📁 修改文件:列出所有变更文件

支持语言

JavaScript / TypeScript / Python / Go / Rust / Java / C++

示例对话

用户: 调试这个错误:AssertionError: expected function to throw Error

助手: 分析 → 搜索 → 修复 → 测试,一站式完成。

安全使用建议
Install only if you are comfortable with a debugging assistant that may search externally and propose or make project changes. Use it in a version-controlled workspace, review diffs before accepting edits, avoid sending proprietary stack traces or secrets to search, and require confirmation before file writes or GitHub issue creation.
能力评估
Purpose & Capability
The stated purpose matches the workflow: diagnose errors, search for fixes, generate repairs, create tests, and report changed files. The same workflow includes state-changing code/test generation and possibly GitHub issue creation.
Instruction Scope
Triggers such as debug, 修复, and 报错 are broad for a workflow that may proceed into code changes, test-file creation, web search, and issue tracking without clearly requiring explicit user approval first.
Install Mechanism
The artifact contains markdown and JSON only, with no executable installer, dependency package, background service, or package-install step.
Credentials
External search is coherent for debugging, but the artifact does not define redaction or opt-in boundaries for stack traces, paths, logs, code snippets, or internal identifiers that may be used as search input.
Persistence & Privilege
No persistence, privilege escalation, credential harvesting, or background execution is shown. The notable authority is project mutation and possible external issue creation, not durable local persistence.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install code-debug-companion
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /code-debug-companion 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of code-debug-companion: - Provides an AI-driven workflow for automatic code error diagnosis, solution research, code fixing, and validation. - Supports error handling via pasted messages, screenshots, or full error stacks. - Integrates code review, web search, unit test generation, and GitHub issue tracking skills. - Outputs concise diagnosis, related discussions, fix details, test coverage, and affected files. - Supports multiple programming languages including JavaScript, TypeScript, Python, Go, Rust, Java, and C++.
元数据
Slug code-debug-companion
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

code-debug-companion 是什么?

AI 驱动的智能代码调试助手,自动诊断错误、搜索解决方案、修复代码并验证。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 64 次。

如何安装 code-debug-companion?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install code-debug-companion」即可一键安装,无需额外配置。

code-debug-companion 是免费的吗?

是的,code-debug-companion 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

code-debug-companion 支持哪些平台?

code-debug-companion 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 code-debug-companion?

由 zlszhonglongshen(@zlszhonglongshen)开发并维护,当前版本 v1.0.0。

💬 留言讨论