‹ 首页

debugging-wizard

@jeffallan · 收录于 1 周前 · 上游提交 1 个月前

Parses error messages, traces execution flow through stack traces, correlates log entries to identify failure points, and applies systematic hypothesis-driven methodology to isolate and resolve bugs. Use when investigating errors, analyzing stack traces, finding root causes of unexpected behavior, troubleshooting crashes, or performing log analysis, error investigation, or root cause analysis.

适合你,如果经常需要从堆栈跟踪和日志中找出代码问题的根源

/ 下载安装
debugging-wizard.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add jeffallan/claude-skills/debugging-wizard
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- jeffallan/claude-skills/debugging-wizard
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify jeffallan/claude-skills/debugging-wizard
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
10501GitHub stars
~751最小装载
~5.7K含声明引用
~5.7K文本包总量
镜像托管

怎么用

商店整理自技能原文 · 版本 e8be415 · 表述以原文为准
它做什么

装上后,Claude 会像专业调试员一样分析错误信息、追踪堆栈、关联日志,用假设驱动的方法一步步找出并修复代码中的 bug。

什么时候触发

当你描述错误、异常、崩溃或代码不工作时,Claude 会主动启动调试流程。

装好后可以这样说
Claude 会解析错误并给出调试步骤。
Claude 会指导你使用 git bisect。
Claude 会关联日志并定位故障点。
技能原文 SKILL.md作者撰写 · MIT · e8be415

Debugging Wizard

Expert debugger applying systematic methodology to isolate and resolve issues in any codebase.

Core Workflow
  1. Reproduce - Establish consistent reproduction steps
  2. Isolate - Narrow down to smallest failing case
  3. Hypothesize and test - Form testable theories, verify/disprove each one
  4. Fix - Implement and verify solution
  5. Prevent - Add tests/safeguards against regression
Reference Guide

Load detailed guidance based on context:

<!-- Systematic Debugging row adapted from obra/superpowers by Jesse Vincent (@obra), MIT License -->

| Topic | Reference | Load When | |-------|-----------|-----------| | Debugging Tools | references/debugging-tools.md | Setting up debuggers by language | | Common Patterns | references/common-patterns.md | Recognizing bug patterns | | Strategies | references/strategies.md | Binary search, git bisect, time travel | | Quick Fixes | references/quick-fixes.md | Common error solutions | | Systematic Debugging | references/systematic-debugging.md | Complex bugs, multiple failed fixes, root cause analysis |

Constraints
MUST DO
  • Reproduce the issue first
  • Gather complete error messages and stack traces
  • Test one hypothesis at a time
  • Document findings for future reference
  • Add regression tests after fixing
  • Remove all debug code before committing
MUST NOT DO
  • Guess without testing
  • Make multiple changes at once
  • Skip reproduction steps
  • Assume you know the cause
  • Debug in production without safeguards
  • Leave console.log/debugger statements in code
Common Debugging Commands

Python (pdb)

python -m pdb script.py          # launch debugger
# inside pdb:
# b 42          — set breakpoint at line 42
# n             — step over
# s             — step into
# p some_var    — print variable
# bt            — print full traceback

JavaScript (Node.js)

node --inspect-brk script.js     # pause at first line, attach Chrome DevTools
# In Chrome: open chrome://inspect → click "inspect"
# Sources panel: add breakpoints, watch expressions, step through

Git bisect (regression hunting)

git bisect start
git bisect bad                   # current commit is broken
git bisect good v1.2.0           # last known good tag/commit
# Git checks out midpoint — test, then:
git bisect good   # or: git bisect bad
# Repeat until git identifies the first bad commit
git bisect reset

Go (delve)

dlv debug ./cmd/server           # build & attach
# (dlv) break main.go:55
# (dlv) continue
# (dlv) print myVar
Output Templates

When debugging, provide:

  1. Root Cause: What specifically caused the issue
  2. Evidence: Stack trace, logs, or test that proves it
  3. Fix: Code change that resolves it
  4. Prevention: Test or safeguard to prevent recurrence

Documentation

按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。