Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问许可证需确认审计异常

deep-debug深度调试

Agent Skill

deep-debug 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,975

周安装

164

GitHub Stars

750

下载量

1,299
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:deep-debug(深度调试)
来源仓库:https://github.com/jezweb/claude-skills
仓库路径:skills/deep-debug
安装命令:
npx skills add https://github.com/jezweb/claude-skills --skill deep-debug
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/jezweb/claude-skills --skill deep-debug

简介

用于复杂 bug 的根因调查,尤其适用于浏览器交互、API 调用与状态管理问题。

  • 支持网络请求追踪、控制台日志分析与多 Agent 并行调试。
  • 提供证据驱动的调试工作流,引导逐步缩小问题范围至具体代码位置。
  • 可选依赖 Chrome MCP 工具,使用时需注意页面访问权限与数据脱敏。
  • deep-debug 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Deep Debug - Multi-Agent Investigation

Status: Production Ready Last Updated: 2026-02-03 Dependencies: Chrome MCP tools (optional), debugger agent, code-reviewer agent


When to Use

  • Going in circles - You've tried multiple fixes but nothing works
  • Browser + API interaction bugs - Need to see Network tab, console logs
  • Symptoms don't match expectations - Something deeper is wrong
  • Complex state management bugs - React hooks, closures, race conditions

Commands

CommandPurpose
/debugGuided debugging workflow with evidence gathering and parallel investigation

Quick Start

/debug [description of the bug]

Or invoke naturally:

  • "I'm stuck on this bug, can you do a deep investigation?"
  • "This bug is resisting normal debugging"
  • "I need you to really dig into this"

The Process

Phase 1: Gather Evidence (Before Hypothesizing)

For browser-related bugs, use Chrome MCP tools:

// Get network requests (look for duplicates, failures, timing)
mcp__claude-in-chrome__read_network_requests

// Get console logs (errors, warnings, debug output)
mcp__claude-in-chrome__read_console_messages

// Get page state
mcp__claude-in-chrome__read_page

For backend bugs, gather:

  • Error logs and stack traces
  • Request/response payloads
  • Database query logs
  • Timing information

Phase 2: Launch Parallel Investigation (3 Agents)

Launch these agents simultaneously with the gathered evidence:

Agent 1: Execution Tracer (debugger)

Task(subagent_type="debugger", prompt="""
EVIDENCE: [paste network/console evidence]

Trace the execution path that leads to this bug. Find:
1. Where the bug originates
2. What triggers it
3. The exact line/function causing the issue

Focus on TRACING, not guessing.
""")

Agent 2: Pattern Analyzer (code-reviewer)

Task(subagent_type="code-reviewer", prompt="""
EVIDENCE: [paste evidence]

Review the relevant code for common bug patterns:
- React useCallback/useMemo dependency issues
- Stale closures
- Race conditions
- State update ordering
- Missing error handling

Find patterns that EXPLAIN the evidence.
""")

Agent 3: Entry Point Mapper (Explore)

Task(subagent_type="Explore", prompt="""
EVIDENCE: [paste evidence]

Map all entry points that could trigger this behavior:
- All places [function] is called
- All event handlers involved
- All state updates that affect this

Find if something is being called MULTIPLE TIMES or from UNEXPECTED places.
""")

Phase 3: Cross-Reference Findings

After agents complete, look for:

SignalMeaning
All 3 agree on root causeHigh confidence - fix it
2 agree, 1 differentInvestigate the difference
All 3 differentNeed more evidence

Phase 4: Verify Fix

After implementing the fix, re-gather the same evidence to confirm:

  • Network tab shows expected behavior
  • Console has no errors
  • State updates correctly

Real Example: Duplicate API Calls Bug

Evidence Gathered

Network tab showed 2 fetch requests for the same message.

Parallel Investigation Results

AgentFinding
debuggerstate.messages in useCallback deps causes callback recreation
code-reviewerSame finding + explained React pattern causing it
ExploreVerified UI layer wasn't double-calling (ruled out)

Root Cause (Consensus)

sendMessage useCallback had state.messages in dependency array. Every state update recreated the callback, causing duplicate calls during React re-renders.

Fix

Use stateRef to access current state without including in dependencies:

const stateRef = useRef(state);
stateRef.current = state;

const sendMessage = useCallback(async (text) => {
  // Use stateRef.current instead of state
  const messages = stateRef.current.messages;
  // ...
}, [/* state.messages removed */]);

Common Bug Patterns This Catches

React Hook Issues

  • state in useCallback dependencies causing recreation
  • Missing dependencies causing stale closures
  • useEffect running multiple times

API/Network Issues

  • Duplicate requests (visible in Network tab)
  • Race conditions between requests
  • CORS failures
  • Timeout handling

State Management Issues

  • State updates not batching correctly
  • Optimistic updates conflicting with server response
  • Multiple sources of truth

Chrome Tools Quick Reference

ToolUse For
read_network_requestsSee all fetch/XHR calls, duplicates, failures
read_console_messagesErrors, warnings, debug logs
read_pageCurrent DOM state
javascript_toolExecute debug code in page context

Tips for Success

  1. Evidence first, hypotheses second - Don't guess until you have concrete data
  2. Network tab is gold - Most frontend bugs show symptoms there
  3. Parallel agents save time - 3 perspectives at once vs sequential guessing
  4. Cross-reference findings - Agreement = confidence
  5. Verify with same evidence - Confirm fix with same tools that found bug

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.33%
按下载量换算485

Claude

31.6%
按下载量换算410

Cursor

18.77%
按下载量换算244

Gemini CLI

10.09%
按下载量换算131

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills