flowstudio-power-automate-debug
Debug failing Power Automate cloud flows using the FlowStudio MCP server. The Graph API only shows top-level status codes. This skill gives your agent action-level inputs and outputs to find the actual root cause. Load this skill when asked to: debug a flow, investigate a failed run, why is this flow failing, inspect action outputs, find the root cause of a flow error, fix a broken Power Automate flow, diagnose a timeout, trace a DynamicOperationRequestFailure, check connector auth errors, read
Security Assessment
Detected risks:
About flowstudio-power-automate-debug
The flowstudio-power-automate-debug skill provides a step-by-step process for diagnosing failing Power Automate cloud flows through the FlowStudio MCP server. It exists because the Graph API only exposes top-level status codes, whereas this skill retrieves action-level inputs and outputs to find the actual root cause. It requires a FlowStudio MCP subscription and a valid token.
Its diagnostic workflow locates the flow, finds the failing run, gets the top-level error to learn which action failed, and then, critically, inspects that action's runtime inputs and outputs to learn why, since generic error codes like ActionFailed, NotSpecified, and InternalServerError hide the real detail (HTTP status and body, expression failures, null values, and stack traces). It provides a Python helper for calling MCP tools, notes that the failedActions list is ordered outer-to-inner so the root cause is the last entry, and explains how to inspect foreach iterations. It advises confirming current tool names and schemas via tool_search, since the live API is authoritative.
It is most useful for makers and engineers troubleshooting broken Power Automate flows who need to trace beyond generic error codes to the action-level root cause.
FAQ
When should I use this skill?
When debugging a failing Power Automate cloud flow, investigating a failed run, or tracing the root cause of a flow error beyond top-level status codes.
Why not just use the Graph API error?
Top-level codes like ActionFailed, NotSpecified, and InternalServerError are generic wrappers; the real cause lives in the failing action's inputs and outputs.
What is the diagnostic sequence?
Locate the flow, find the failing run, get the top-level error to see which action failed, then inspect that action's inputs and outputs to see why.
How do I find the root failing action?
The failedActions list is ordered outer-to-inner, so the root cause is the last entry; for actions inside a foreach, inspect specific iterations.
What does it require?
A reachable FlowStudio MCP server with a valid token, and confirming current tool names and parameters via tool_search since the API is authoritative.
Install flowstudio-power-automate-debug
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
github/awesome-copilot