Debug
Inspects v1-io data input/output streams to identify errors and bottlenecks during testing workflows.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add v1-io-debug npx -- -y @trustedskills/v1-io-debug
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"v1-io-debug": {
"command": "npx",
"args": [
"-y",
"@trustedskills/v1-io-debug"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The v1-io-debug skill provides debugging capabilities for AI agents. It allows users to inspect the agent's internal state, including variables and function calls, during execution. This facilitates understanding of the agent’s decision-making process and identification of potential issues or errors.
When to use it
- Troubleshooting unexpected behavior: When an agent isn't performing as expected, use this skill to examine its intermediate steps.
- Understanding complex logic: If you need to understand how a specific function or decision was reached within the agent’s workflow.
- Validating internal state: To confirm that variables and data structures hold the values you anticipate during execution.
- Debugging custom code: When integrating custom functions, this skill helps pinpoint errors in their implementation.
Key capabilities
- Inspect variable values
- Trace function calls
- Examine agent's internal state
Example prompts
- "Show me the value of
user_input." - "What was the last function called?"
- “Debug step by step”
Tips & gotchas
The skill requires access to the agent’s internal execution environment. Ensure that the agent is configured to allow debugging requests for this skill to function correctly.
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.