Debug
Cerico-debug automatically identifies and suggests fixes for code errors during automated testing cycles.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add cerico-debug npx -- -y @trustedskills/cerico-debug
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"cerico-debug": {
"command": "npx",
"args": [
"-y",
"@trustedskills/cerico-debug"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill, authored by cerico, provides debugging capabilities to AI agents. It allows users to inspect the agent's internal state and reasoning process. The tool facilitates identifying errors in logic or unexpected behavior within an AI agent’s workflow.
When to use it
- When an AI agent produces incorrect or unexpected results.
- To understand why an agent made a particular decision.
- During development and testing of AI agents, to pinpoint the source of issues.
- For troubleshooting complex workflows involving multiple steps or tools.
Key capabilities
- Inspect internal state
- Reasoning process analysis
- Error identification
Example prompts
- "Debug my agent's last action."
- "Show me why you chose that particular option."
- "What was your reasoning when deciding to [specific task]?"
Tips & gotchas
This skill is most effective when used during the development and testing phases of an AI agent. It requires a level of understanding of the agent's internal workings to effectively interpret the debugging information provided.
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.