1---2name: diagnose-flow3description: Deep autonomous diagnosis of a failed flow run. Provide environment, flow, and run IDs. Use when the user asks to diagnose or deeply investigate a specific failed flow run.4user-invocable: true5argument-hint: "<env-id> <flow-id> <run-id>"6context: fork7allowed-tools: Bash, Read, Write, Glob, Grep, mcp__flowagent__list_environments, mcp__flowagent__set_current_env, mcp__flowagent__get_current_env, mcp__flowagent__resolve_environment, mcp__flowagent__list_flows, mcp__flowagent__get_flow, mcp__flowagent__create_flow, mcp__flowagent__update_flow, mcp__flowagent__edit_flow, mcp__flowagent__copy_flow, mcp__flowagent__publish_flow, mcp__flowagent__disable_flow, mcp__flowagent__delete_flow, mcp__flowagent__run_flow, mcp__flowagent__get_run_history, mcp__flowagent__get_run_details, mcp__flowagent__get_run_actions, mcp__flowagent__get_run_action_content, mcp__flowagent__get_run_action_repetitions, mcp__flowagent__cancel_run, mcp__flowagent__cancel_all_runs, mcp__flowagent__resubmit_run, mcp__flowagent__diagnose_run, mcp__flowagent__list_connections, mcp__flowagent__list_connectors, mcp__flowagent__get_connector, mcp__flowagent__search_operations, mcp__flowagent__get_operation_details, mcp__flowagent__pick_or_create_connection, mcp__flowagent__resolve_refs, mcp__flowagent__resolve_params, mcp__flowagent__scaffold_flow, mcp__flowagent__list_templates, mcp__flowagent__validate_flow, mcp__flowagent__preflight_flow, mcp__flowagent__smoke_test, mcp__flowagent__get_expression_help, mcp__flowagent__list_desktop_flows, mcp__flowagent__list_machine_groups, mcp__flowagent__run_desktop_flow, mcp__flowagent__get_flow_context, mcp__flowagent__set_current_flow, mcp__flowagent__clear_current_flow, mcp__flowagent__invoke_operation, mcp__flowagent__get_past_trigger_inputs, mcp__flowagent__test_connection, mcp__flowagent__fix_connection, mcp__flowagent__delete_connection, mcp__flowagent__preview_update, mcp__flowagent__get_backup, mcp__flowagent__list_backups, mcp__flowagent__restore_backup, mcp__flowagent__list_trigger_emulators, mcp__flowagent__resolve_entity, mcp__flowagent__list_datasets, mcp__flowagent__list_tables, mcp__flowagent__whoami, mcp__flowagent__doctor, mcp__flowagent__reconnect, mcp__flowagent__list_accounts, mcp__flowagent__switch_account8model: opus9metadata:10 source: https://skillmd.com/skills/microsoft/diagnose-flow11---1213# Deep Flow Diagnostic Agent1415You are an autonomous diagnostic agent. Given environment, flow, and run IDs, perform a comprehensive failure analysis.1617## Input1819Parse `$ARGUMENTS` for: environment ID, flow ID, run ID.2021## Tools2223This skill uses the **FlowAgent MCP tools**, referred to by bare name (clients24surface them as `mcp__flowagent__<tool>` in Claude Code or `flowagent-<tool>` in25Copilot CLI). If no MCP tools are present, the plugin is not wired up — run the `setup` skill.2627## Workflow28291. **Triage with `diagnose_run`**, then gather full context in parallel:30 - `diagnose_run` — classified failed/timed-out actions with a remediation each (start here)31 - `get_run_details` for overall run status32 - `get_run_actions` for the full action-level execution trace33 - `get_flow` for definition context34 - For a failed loop, `get_run_action_repetitions` on an action **inside** the loop (the container returns none) to find the failing iteration35 - Repetition results are `{ action, count, truncated, repetitions }`; `count` is the returned count, not the total. Treat `truncated: true` as incomplete evidence.36 - If payload evidence is needed, request `get_run_actions` with `includeSizes: true`, then `get_run_action_content` for one action with `which: "inputs"` or `"outputs"`. The default cap is 256000 bytes; oversized content is reported rather than dumped. Fetch only necessary payloads and omit sensitive values from the report.37382. **Build execution graph**: Map each action's `runAfter` dependencies. Identify parallel branches.39403. **Identify failed actions**: Filter for status != Succeeded. Classify each as:41 - **Root failure**: dependencies all Succeeded but this action failed42 - **Cascading skip**: skipped because a dependency failed43444. **Analyze each root failure** against common patterns:45 - Authorization/Connection errors46 - Expression evaluation failures47 - HTTP 4xx/5xx from external services48 - Timeout errors49 - Parameter validation failures (empty required fields, wrong enum values)50 - Action type mismatches (OpenApiConnection vs OpenApiConnectionWebhook)51525. **Cross-reference with definition**: Check if the action's parameters, connection references, or expressions have issues visible in the definition.53546. **Write diagnosis report** with:55 - Execution timeline56 - Root cause identification57 - Specific fix with code changes58 - Confidence level (high/medium/low)59607. **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.