Monte Carlo Troubleshoot Agent Traces Skill

This skill investigates Monte Carlo AI agent alerts and traces — evaluation score drops, latency and token spikes, trajectory violations, and validation breaches — by classifying the alert, routing to the right playbook for the agent's backend, and guiding a systematic investigation with Monte Carlo's MCP tools. It runs Monte Carlo's trace troubleshooting agent (TTSA) in parallel with the manual investigation and merges both sets of findings.

Monte Carlo tool routing (required): Always call Monte Carlo MCP tools through this plugin's bundled server, whose fully-qualified tool names are mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__<tool> (e.g. mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__get_alerts). Bare tool names used in this skill (get_alerts, search, get_table, …) refer to that bundled server. If the session also has a separately-configured monte-carlo-mcp server, do not route to it — it may point at a different endpoint or credentials.

Reference files live next to this skill file. Use the Read tool (not MCP resources) to access them:

• Alert-shape playbooks (WHAT to investigate): references/agent-alert-evaluation.md, references/agent-alert-metric.md, references/agent-alert-trajectory.md, references/agent-alert-validation.md
• Backend guides (HOW to investigate there / what signal exists): references/agent-backend-clickhouse.md, references/agent-backend-cortex.md, references/agent-backend-genie.md, references/agent-backend-customer-otel.md, references/agent-backend-mlflow-sdk.md, references/agent-backend-mlflow-ka.md
• Intake without an alert: references/agent-direct-trace.md

When to activate this skill