Debug
Automatically identifies and suggests fixes for common coding errors in Python and JavaScript projects.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add zhiruifeng-debug npx -- -y @trustedskills/zhiruifeng-debug
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"zhiruifeng-debug": {
"command": "npx",
"args": [
"-y",
"@trustedskills/zhiruifeng-debug"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill, zhiruifeng-debug, provides debugging capabilities for AI agents. It allows users to inspect and modify the agent's internal state during execution. This is useful for understanding why an agent is behaving in a certain way and correcting errors or improving performance.
When to use it
- Troubleshooting unexpected behavior: If your agent isn’t performing as expected, use this skill to examine its thought process.
- Understanding complex workflows: Debug the execution flow of multi-step tasks to identify bottlenecks or inefficiencies.
- Validating assumptions: Verify that the agent is reasoning correctly and using information as intended.
- Improving agent performance: Analyze internal states to optimize decision making and resource utilization.
Key capabilities
- Inspect agent state during execution
- Modify agent state for testing purposes
- Provides insights into agent’s thought process
Example prompts
- "Debug the last step of my workflow."
- "Show me the current value of 'temperature'."
- "What was the reasoning behind your last decision?"
Tips & gotchas
This skill requires a good understanding of the agent's internal workings. Incorrectly modifying state can lead to unpredictable behavior, so use with caution and in controlled testing environments.
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.