Convex Agents Debugging
Automates debugging convex-agent configurations by identifying common errors and suggesting fixes for improved performance.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add convex-agents-debugging npx -- -y @trustedskills/convex-agents-debugging
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"convex-agents-debugging": {
"command": "npx",
"args": [
"-y",
"@trustedskills/convex-agents-debugging"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill provides debugging capabilities for Convex agents. It allows you to inspect agent state, step through execution, and identify errors within your agent workflows. Specifically, it facilitates understanding why an agent made a particular decision or encountered a failure during its operation.
When to use it
- Troubleshooting Agent Failures: When an agent consistently fails to achieve its goals, this skill can help pinpoint the root cause of the problem.
- Understanding Complex Decisions: If you're unsure why an agent took a specific action, debugging tools allow for inspection of intermediate states and reasoning processes.
- Validating Agent Logic: During development, use this skill to verify that your agents are behaving as expected and following the intended logic flow.
- Performance Optimization: Identify bottlenecks or inefficient steps within an agent's execution path.
Key capabilities
- State inspection of agent variables
- Step-by-step execution tracing
- Error identification and reporting
Example prompts
- "Debug the last run of my 'order_processing' agent."
- "Show me the state of the 'inventory' variable when the agent decided to reorder."
- "Step through the execution of the 'search_for_product' function in my agent."
Tips & gotchas
This skill requires a running Convex agent environment. Debugging can be computationally intensive, so use it judiciously during development and testing phases.
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.