Debug
Debug LobeHub models directly within your AI agent using this tool for rapid iteration and troubleshooting.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add lobehub-debug npx -- -y @trustedskills/lobehub-debug
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"lobehub-debug": {
"command": "npx",
"args": [
"-y",
"@trustedskills/lobehub-debug"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
The debug skill enables AI agents to inspect, analyze, and troubleshoot issues within the LobeChat application. It provides direct access to internal diagnostics, logs, and system states to identify root causes of errors or performance bottlenecks.
When to use it
- Diagnosing unexpected crashes or unresponsive behavior in the chat interface.
- Investigating API connection failures or authentication errors during model interactions.
- Verifying data integrity when custom plugins or local file processing fails.
- Gathering detailed error logs for reporting to developers or support teams.
Key capabilities
- Access to real-time application logs and debug traces.
- Inspection of internal system states and configuration variables.
- Analysis of network requests and responses within the LobeChat environment.
- Identification of specific modules causing runtime exceptions.
Example prompts
- "Run a diagnostic check on the current session and report any detected errors."
- "Inspect the logs for the last failed message generation attempt."
- "Analyze why the local file upload feature is returning a 500 error."
Tips & gotchas
Ensure you have appropriate permissions enabled to view sensitive system logs, as some debug outputs may contain private data. This skill is primarily designed for troubleshooting within the LobeChat ecosystem and may not provide insights into external dependencies beyond immediate network reachability.
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.