← Back to Skills Marketplace
218
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install code-debug
Description
Diagnose errors or crashes in local code, identify root causes, and provide the minimal fix with verification steps.
README (SKILL.md)
调试修复
先找根因，再动代码。
工作流
- 能复现就先复现，不能复现就尽量缩小到最小场景。
- 先判断错误类别：语法、运行时、逻辑、异步顺序、类型、边界、依赖、配置或资源处理。
- 优先检查常见问题：off-by-one、空值处理、过期状态、竞争条件、输入假设错误、资源未释放。
- 用代码、日志或执行结果锁定根因，不做玄学猜测。
- 用最小安全修复解决真正的根因。
- 非必要不夹带重构；结构太差影响修复时再单独说明。
- 用最短可靠方式验证修复结果。
输出
- 根因
- 影响范围
- 最小复现场景，如果能给出
- 修复方向或补丁
- 验证方法
Usage Guidance
This skill is coherent and instruction-only, but remember: for it to debug effectively it will need to read your workspace files, logs, and may run tests or code — which can execute untrusted code or touch sensitive data. Before using: (1) run it only on code you trust or inside an isolated sandbox/container, (2) back up or use version control so you can review and approve patches before applying, (3) avoid exposing secrets in the workspace while debugging, and (4) if you prefer manual review, disable autonomous invocation or require user confirmation before applying fixes.
Capability Analysis
Type: OpenClaw Skill
Name: code-debug
Version: 0.1.0
The skill bundle is a standard utility for code debugging and root-cause analysis. The instructions in SKILL.md outline a logical workflow for reproducing errors and implementing minimal fixes without any evidence of malicious intent, data exfiltration, or unauthorized execution. All files, including agents/openai.yaml and _meta.json, are consistent with the stated purpose of diagnosing software defects.
Capability Assessment
Purpose & Capability
Name and description match the SKILL.md: it is an instruction-only debugging helper for diagnosing and producing minimal fixes to local code. It requests no binaries, env vars, installs, or external services, which is proportional for the stated purpose.
Instruction Scope
The instructions direct the agent to reproduce failures, inspect code, logs, and execution results, and produce minimal fixes and verification steps. That scope is appropriate for debugging, but implies the agent may read project files, logs, and run tests or code in the workspace — actions the user should be aware of because they can execute untrusted code or access sensitive files.
Install Mechanism
No install spec or code files are present (instruction-only). This minimizes supply-chain risk because nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no environment variables, credentials, or config paths. There are no requests for unrelated secrets or credentials, which is appropriate for a local debugging assistant.
Persistence & Privilege
The skill does not request always: true and has default invocation settings. It does not modify other skills or system-wide settings. Autonomous invocation is permitted by default (platform default) but is not combined with other high-risk factors here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install code-debug - After installation, invoke the skill by name or use
/code-debug - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
initial release
Metadata
Frequently Asked Questions
What is Code Debug?
Diagnose errors or crashes in local code, identify root causes, and provide the minimal fix with verification steps. It is an AI Agent Skill for Claude Code / OpenClaw, with 218 downloads so far.
How do I install Code Debug?
Run "/install code-debug" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Code Debug free?
Yes, Code Debug is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Code Debug support?
Code Debug is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Code Debug?
It is built and maintained by sf0799 (@sf0799); the current version is v0.1.0.
More Skills