debug — community community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for AI Agents needing advanced root cause analysis and code debugging capabilities. Debug是一种AI智能调试工具,帮助开发者快速解决代码问题。它支持多种编程语言,包括Python、Node.js和React

johnlindquist johnlindquist
[0]
[0]
Updated: 2/24/2026

Agent Capability Analysis

The debug skill by johnlindquist is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for AI Agents needing advanced root cause analysis and code debugging capabilities.

Core Value

Empowers agents to perform comprehensive codebase investigations, leveraging GitHub issues search and multi-framework reasoning to generate specific fix recommendations with code, utilizing systematic thinking and code analysis techniques.

Capabilities Granted for debug

Debugging complex code issues
Investigating and resolving GitHub issues
Applying multi-framework reasoning for root cause analysis

! Prerequisites & Limits

  • Requires Gemini CLI for AI analysis
  • Limited to codebase and GitHub issues search
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

debug

Install debug, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Debug - Root Cause Debugging Workflow

Complete debugging workflow that enforces root cause analysis: Investigate → Understand → Reason → Fix.

Overview

Debug combines multiple debugging approaches:

  • Codebase investigation - Search for relevant code
  • GitHub issues search - Find known issues and workarounds
  • Multi-framework reasoning - Apply systematic thinking
  • Fix generation - Specific recommendations with code

Prerequisites

bash
1# Gemini CLI for AI analysis 2pip install google-generativeai 3export GEMINI_API_KEY=your_api_key 4 5# gh CLI for GitHub issue search 6brew install gh 7gh auth login

Debugging Workflows

bash
1# Phase 1: Investigate codebase 2rg -l "error pattern" --type ts 3rg "relevant_function" -A 10 -B 5 4 5# Phase 2: Search GitHub for known issues 6gh search issues "error message" --repo owner/repo --limit 10 7gh issue view 123 --repo owner/repo 8 9# Phase 3: Reason about root cause 10gemini -m pro -o text -e "" "Given this error and code context, what is the root cause? 11 12Error: [error message] 13 14Code: 15\$(cat src/file.ts) 16 17Investigation findings: 18- [finding 1] 19- [finding 2] 20 21Apply first principles, systematic, and critical thinking frameworks." 22 23# Phase 4: Generate fix 24gemini -m pro -o text -e "" "Based on root cause: [cause] 25 26Provide: 271. Specific code fix 282. Before/after code 293. How to verify 304. How to prevent"

Quick Debug (Simple Issues)

bash
1# Skip deep reasoning, focus on investigation + fix 2rg "error pattern" --type ts -A 5 -B 5 3 4gemini -m pro -o text -e "" "Debug this quickly: 5 6Problem: [description] 7Error: [message] 8 9Code: 10\$(cat src/problematic-file.ts) 11 12Give me the root cause and fix in 3 sentences."

Debug with Context (Known Files)

bash
1# When you already know which files are involved 2gemini -m pro -o text -e "" "Debug using these files: 3 4Problem: [description] 5 6File 1: 7\$(cat src/file1.ts) 8 9File 2: 10\$(cat src/file2.ts) 11 12Provide: 131. Root cause 142. Specific fix with line numbers 153. Verification steps"

Comprehensive Diagnosis (Complex Issues)

bash
1# Parallel investigation of multiple sources 2 3# Terminal 1: Codebase search 4rg "error" --type ts --stats > /tmp/codebase.txt & 5 6# Terminal 2: GitHub issues 7gh search issues "error" --limit 20 > /tmp/github.txt & 8 9# Terminal 3: Git history 10git log --oneline --all -S "problematic_function" > /tmp/history.txt & 11 12wait 13 14# Synthesize findings 15gemini -m pro -o text -e "" "Synthesize these diagnostic findings: 16 17Codebase: 18\$(cat /tmp/codebase.txt) 19 20GitHub Issues: 21\$(cat /tmp/github.txt) 22 23Git History: 24\$(cat /tmp/history.txt) 25 26Provide unified diagnosis with: 271. Most likely root cause 282. Confidence level 293. Key evidence 304. Differential diagnosis 315. Recommended action"

Root Cause Protocol

Always follow this hierarchy:

  1. INVESTIGATE - Search for evidence first
  2. UNDERSTAND - Read relevant code
  3. REASON - Apply systematic thinking
  4. FIX - Only then propose changes

Forbidden Shortcuts

SymptomBANNED FixREQUIRED Fix
Null errorif (x) { x.y }Find why x is null
TimeoutIncrease timeoutFind what's slow
Flaky testSkip testFind race condition
Type erroras anyFix type hierarchy

Investigation Commands

bash
1# Find error patterns 2rg "throw.*Error" --type ts -A 3 3 4# Find function definitions 5rg "function functionName|const functionName" --type ts 6 7# Find usages 8rg "functionName\(" --type ts 9 10# Find recent changes 11git log --oneline -20 --all -- src/problematic/ 12git diff HEAD~5 -- src/problematic/
bash
1# Search issues 2gh search issues "error message" --repo owner/repo --state all 3 4# View issue details 5gh issue view 123 --repo owner/repo --comments 6 7# Search across multiple repos 8for repo in repo1 repo2 repo3; do 9 gh search issues "error" --repo owner/$repo --limit 5 10done

Log Analysis

bash
1# Find logs first 2find . -name "*.log" -type f 3 4# Tail recent logs 5tail -100 logs/app.log | grep -i error 6 7# Search logs for patterns 8grep -n "ERROR\|WARN" logs/*.log | tail -50

Framework-Based Reasoning

First Principles

bash
1gemini -m pro -o text -e "" "Apply first principles to this bug: 2 3Problem: [description] 4 5Questions: 61. What is this code supposed to do? 72. What is it actually doing? 83. What assumptions are being made? 94. Which assumption is wrong?"

Systematic Analysis

bash
1gemini -m pro -o text -e "" "Systematically analyze: 2 3Problem: [description] 4 5Walk through: 61. Input → What data enters? 72. Processing → What transformations? 83. State → What state changes? 94. Output → What comes out? 105. Where does expected diverge from actual?"

Critical Thinking

bash
1gemini -m pro -o text -e "" "Challenge assumptions: 2 3Problem: [description] 4 5For each potential cause: 6- What evidence supports it? 7- What evidence contradicts it? 8- What would we expect to see if true? 9- Can we rule it out?"

Output Format

A debug session should produce:

markdown
1## ROOT CAUSE 2Single sentence identifying the actual cause. 3 4## CONFIDENCE 5high | medium | low 6 7## FIX 8Specific code changes: 9- File: src/file.ts 10- Line: 42 11- Before: `oldCode()` 12- After: `newCode()` 13 14## VERIFICATION 15How to verify the fix works: 161. Run test: `npm test -- specific.test.ts` 172. Manual check: [steps] 18 19## PREVENTION 20How to prevent this in the future: 21- Add validation at boundary 22- Add regression test

Best Practices

  1. Logs first - Read logs before reading code
  2. Evidence required - No fix without citing specific evidence
  3. One cause - Find THE root cause, not symptoms
  4. Verify hypothesis - Test your theory before fixing
  5. Prevent recurrence - Add tests for the failure mode
  6. Document findings - Capture what you learned

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is debug?

Perfect for AI Agents needing advanced root cause analysis and code debugging capabilities. Debug是一种AI智能调试工具,帮助开发者快速解决代码问题。它支持多种编程语言,包括Python、Node.js和React

How do I install debug?

Run the command: npx killer-skills add johnlindquist/claude/debug. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for debug?

Key use cases include: Debugging complex code issues, Investigating and resolving GitHub issues, Applying multi-framework reasoning for root cause analysis.

Which IDEs are compatible with debug?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for debug?

Requires Gemini CLI for AI analysis. Limited to codebase and GitHub issues search.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add johnlindquist/claude/debug. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use debug immediately in the current project.

Related Skills

Looking for an alternative to debug or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI