Debug
Analyzes test execution logs from rsmdt tests to pinpoint root causes of failures and suggest remediation steps.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add rsmdt-debug npx -- -y @trustedskills/rsmdt-debug
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"rsmdt-debug": {
"command": "npx",
"args": [
"-y",
"@trustedskills/rsmdt-debug"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill, rsmdt-debug, provides debugging capabilities for AI agents. It allows users to inspect the agent's internal state and reasoning process. Specifically, it can be used to examine variables, trace execution flow, and identify potential errors within an agent’s workflow.
When to use it
- Troubleshooting unexpected behavior: If your AI agent isn't producing the desired results, this skill helps pinpoint the source of the problem.
- Understanding complex workflows: When dealing with intricate sequences of actions or decisions made by the agent,
rsmdt-debugcan illuminate how it arrives at its conclusions. - Validating assumptions about agent logic: Verify that your agent is behaving as intended and following the correct decision paths.
- Debugging custom code integrations: When integrating custom functions or tools into an AI agent's workflow, use this skill to debug any issues arising from those integrations.
Key capabilities
- Inspect internal variables
- Trace execution flow
- Identify errors in reasoning
Example prompts
- "Debug the last step and show me all variable values."
- "Step through the process of deciding whether to send this email."
- "Show me the logic path that led to this decision."
Tips & gotchas
This skill requires a good understanding of the AI agent's underlying code or workflow. The level of detail available during debugging will depend on how the agent was designed and instrumented.
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.