Debug Like Expert
Simulates expert debugging strategies, identifying root causes and suggesting fixes from test failures with detailed explanations.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add glittercowboy-debug-like-expert npx -- -y @trustedskills/glittercowboy-debug-like-expert
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"glittercowboy-debug-like-expert": {
"command": "npx",
"args": [
"-y",
"@trustedskills/glittercowboy-debug-like-expert"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill helps AI agents debug code by simulating expert debugging strategies. It encourages a skeptical approach to your own code and utilizes a scientific method to systematically identify root causes of test failures rather than applying quick fixes. The agent will scan the codebase for clues about the project type and, if possible, load relevant domain-specific expertise to aid in the investigation.
When to use it
- When encountering unexpected test failures and needing help identifying the underlying cause.
- For debugging projects where you suspect cognitive biases might be hindering your ability to spot errors.
- When working with unfamiliar codebases and wanting a structured approach to problem-solving.
- To leverage domain-specific knowledge for common pitfalls in specific project types (e.g., Python games, macOS apps).
- When needing assistance debugging projects written in languages like Python, JavaScript, Rust, Swift, C++, Go, or Java.
Key capabilities
- Systematic Debugging: Employs a scientific method to identify root causes.
- Skeptical Code Review: Encourages questioning the assumptions behind code implementation.
- Domain Expertise Loading: Can load domain-specific debugging knowledge from
~/.claude/skills/expertise/(e.g.,macos-apps,iphone-apps,python-games). - Automatic Domain Detection: Identifies project types based on file extensions and common configuration files (like
package.json,Cargo.toml,setup.py). - Graceful Degradation: Functions effectively even without domain expertise loaded, using general debugging methodology.
Example prompts
- "I'm seeing test failures in my Python game. Can you help me debug it?"
- "My Rust project is crashing unexpectedly; can you investigate the root cause?"
- "I have a failing test in my Next.js application, what could be causing it?"
Tips & gotchas
- The skill relies on domain expertise files located in
~/.claude/skills/expertise/. Ensure these are present for optimal results when working with specific project types. - If no domain expertise is found or selected, the agent will fall back to general debugging techniques.
- Be prepared for the agent to ask clarifying questions about your project type and codebase.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.