agents-debug

What problem does it solve?

Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisites when the CLI itself isn't working. Triggers on: "agent not working", "wrong answer", "agent error", "tool call failing", "debug agent", "check logs", "read traces", "broken", "500 error", "424 error", "model access denied", "command not found", "stuck in DELETING", "maxVms exceeded", "cold start diagnosis", "cold start slow", "agentcore create error", "create failed", "exit code 7", "connection refused local dev". Not for deploy failures — use agents-deploy. Not for performance tuning without errors — use agents-optimize.

Core Features & Use Cases

• The skill provides diagnostic steps to identify CLI/prerequisite issues and agent behavioral problems by inspecting traces, logs, and runtime configuration.
• It guides users through verifying CLI version, reading traces/logs, and diagnosing common problems with targeted actions and references.
• Use Case: When an agent returns incorrect results or tool calls fail, load traces and logs to determine root causes and reference doctor.md for prerequisites.

Quick Start

Describe the issue you're facing to start diagnostics and get step-by-step guidance.