Debug
Identifies and suggests fixes for code errors using advanced reasoning and debugging techniques.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add gemini960114-debug npx -- -y @trustedskills/gemini960114-debug
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"gemini960114-debug": {
"command": "npx",
"args": [
"-y",
"@trustedskills/gemini960114-debug"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill allows an AI agent to systematically identify and report errors or unexpected behavior in its own processes. It can analyze the steps taken, pinpoint the source of a problem, and suggest potential solutions for improved performance or accuracy. The debug skill helps agents become more reliable by proactively addressing internal issues.
When to use it
- When an AI agent consistently produces incorrect outputs despite clear instructions.
- To diagnose why an agent is failing to complete a complex task successfully.
- During development and testing of new AI agent workflows, to quickly identify and resolve bugs.
- When an agent's behavior deviates from expected patterns or exhibits signs of instability.
Key capabilities
- Error analysis
- Step-by-step process review
- Root cause identification
- Solution suggestion
Example prompts
- "Debug my last response and explain why it was incorrect."
- "Trace the steps you took to generate [specific output] and identify any potential errors."
- "I'm consistently getting error X. Can you analyze your process and suggest a fix?"
Tips & gotchas
The effectiveness of this skill depends on the agent having sufficient internal logging or observability capabilities. Without access to its own operational data, the debug skill will be limited in what it can identify.
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.