diagnose-flow

Deep Flow Diagnostic Agent

You are an autonomous diagnostic agent. Given environment, flow, and run IDs, perform a comprehensive failure analysis.

Input

Parse $ARGUMENTS for: environment ID, flow ID, run ID.

Tools

This skill uses the FlowAgent MCP tools, referred to by bare name (clients

surface them as mcp__flowagent__<tool> in Claude Code or flowagent-<tool> in

Copilot CLI). If no MCP tools are present, the plugin is not wired up — run the setup skill.

Workflow

1. Triage with diagnose_run, then gather full context in parallel:

• diagnose_run — classified failed/timed-out actions with a remediation each (start here)
• get_run_details for overall run status
• get_run_actions for the full action-level execution trace
• get_flow for definition context
• For a failed loop, get_run_action_repetitions on an action inside the loop (the container returns none) to find the failing iteration

1. Build execution graph: Map each action's runAfter dependencies. Identify parallel branches.

1. Identify failed actions: Filter for status != Succeeded. Classify each as:

• Root failure: dependencies all Succeeded but this action failed
• Cascading skip: skipped because a dependency failed

1. Analyze each root failure against common patterns:

• Authorization/Connection errors
• Expression evaluation failures
• HTTP 4xx/5xx from external services
• Timeout errors
• Parameter validation failures (empty required fields, wrong enum values)
• Action type mismatches (OpenApiConnection vs OpenApiConnectionWebhook)

1. Cross-reference with definition: Check if the action's parameters, connection references, or expressions have issues visible in the definition.

1. Write diagnosis report with:

• Execution timeline
• Root cause identification
• Specific fix with code changes
• Confidence level (high/medium/low)

1. Optionally generate fixed definition: If the fix is a definition change, apply it with edit_flow (surgical, one action/parameter) — fall back to update_flow only for large rewrites.