Agent skill · DevOps & Cloud

flowstudio-power-automate-build

Build, scaffold, and deploy Power Automate cloud flows using the FlowStudio MCP server. Your agent constructs flow definitions, wires connections, deploys, and tests — all via MCP without opening the portal. Load this skill when asked to: create a flow, build a new flow, deploy a flow definition, scaffold a Power Automate workflow, construct a flow JSON, update an existing flow's actions, patch a flow definition, add actions to a flow, wire up connections, or generate a workflow definition from scratch. Requires a FlowStudio MCP subscription — see https://mcp.flowstudio.app

GitHub68,948★ · +463/wk · 2 repos on radarProfile →
copilotMIT
Install
npx skills add github/awesome-copilot --skill flowstudio-power-automate-build --agent copilot

Same command for any agent — swap --agent for claude-code, codex, cursor.

Facts
Files in the skill folder: 7
SKILL.md size: 19 KB
Bundled scripts: none
Path: skills/flowstudio-power-automate-build/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 37,432 · +281 this week
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Guides an agent to construct, wire, deploy, verify, and test Power Automate cloud flows through the FlowStudio MCP server. It supports creating new flows or updating existing ones, building a flow definition, resolving connection references, deploying via update_live_flow, and performing post-deploy verification and testing steps. The workflow emphasizes using MCP calls like list_live_flows, get_live_flow, update_live_flow, get_live_flow, resubmit_live_flow_run, trigger_live_flow, get_live_flow_runs, and related describe-assisted steps to define connectors and actions, all without opening the portal.

How it works

  • Load the current build tools by calling tool_search with query "skill:create-flow" for new flows or using the build-flow bundle for edits.
  • Check if the flow already exists with list_live_flows and derive FLOW_ID if found; otherwise proceed with a blank new flow.
  • Obtain active connections via list_live_connections, confirm required connectors exist, and build connection_references and host_templates blocks for the flow.
  • Build the flow definition object with the required schema, including triggers and actions, informed by live connector descriptors when possible.
  • Deploy the flow with update_live_flow; omit flowName for creation, or include flowName for updates; set a displayName and description accordingly.
  • Verify deployment by calling get_live_flow and inspecting properties.state and the actions present in the definition.
  • Test the flow using resubmit_live_flow_run for existing flows or trigger_live_flow for new, non-HTTP scenarios, ensuring user confirmation before triggering tests.

When to use it

Use when asked to create a flow, build a new flow, deploy a flow definition, scaffold a Power Automate workflow, construct a flow JSON, update an existing flow's actions, patch a flow definition, add actions to a flow, wire up connections, or generate a workflow definition from scratch. Requires a FlowStudio MCP subscription.

What it can touch

  • Tools: copilot (as declared)
  • MCP API via Python helper code blocks in the skill for calling: tool_search, list_live_flows, get_live_flow, list_live_connections, describe_live_connector, get_live_dynamic_options, update_live_flow, get_live_flow_runs, resubmit_live_flow_run, trigger_live_flow, set_live_flow_state, get_live_flow_runs, get_live_flow_run_error, and related auxiliary tools described in the instructions.

Caveats

  • Requires a FlowStudio MCP subscription.
  • The skill emphasizes calling list_skills / tool_search first to confirm available tool names and parameter schemas and notes that tool schemas may change between server versions.
  • The update_live_flow tool returns an error key on failure; a missing key value indicates success. Do not treat the presence of the error key as failure when its value is null.
  • Flow description is in definition["description"], and the server may append "#flowstudio-mcp" for usage tracking; do not pass a top-level description argument unless the active schema shows one.
  • Testing requires explicit user confirmation before triggering actions that have real side effects (emails, Teams messages, etc.).
From the SKILL.md

# Build & Deploy Power Automate Flows with FlowStudio MCP Step-by-step guide for constructing and deploying Power Automate cloud flows programmatically through the FlowStudio MCP server. **Prerequisite**: A FlowStudio MCP server must be reachable with a valid JWT. See the `flowstudio-power-automate-mcp` skill for connection setup. Subscribe at https://mcp.flowstudio.app Workflow: 1. Load current build tools. 2. Check for an existing flow. 3. Resolve connection references. 4. Build the definition. 5. Deploy. 6. Verify. 7. Test. --- ## Source of Truth > **Always call `list_skills` / `tool_search` first** to confirm available tool > names and parameter schemas. Tool names and parameters may change between > server versions. > This skill covers response shapes, behavioral notes, and build patterns — > things tool schemas cannot tell you. If this document disagrees with > `tool_search` or a real API response, the API wins. --- ## Python Helper ```python import json, urllib.request MCP_URL = "https://mcp.flowstudio.app/mcp" MCP_TOKEN = "<YOUR_JWT_TOKEN>" def mcp(tool, **kwargs): payload = json.dumps({"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": tool, "arguments":

What's inside
Steps it walks through
  1. Source of Truth
  2. Python Helper
  3. 0. Load the Current Build Tools
  4. 1. Safety Check: Does the Flow Already Exist?
  5. 2. Obtain Connection References
  6. 2a — Find active connections
  7. 2b — Determine which connectors the flow needs
  8. 2c — If connections are missing, guide the user
  9. 2d — Build the connectionReferences block
  10. 3. Build the Flow Definition
  11. Discover connector operations before guessing JSON
  12. 4. Deploy (Create or Update)
  13. Create a new flow (no existing flow)
  14. Update an existing flow
Ships with 6 files
  • references/action-patterns-connectors.md
  • references/action-patterns-core.md
  • references/action-patterns-data.md
  • references/build-patterns.md
  • references/flow-schema.md
  • references/trigger-types.md
More from awesome-copilot
All skills →
About this skill
What does the flowstudio-power-automate-build skill do?

Build, scaffold, and deploy Power Automate cloud flows using the FlowStudio MCP server. Your agent constructs flow definitions, wires connections, deploys, and tests — all via MCP without opening the portal. Load this skill when asked to: create a flow, build a new flow, deploy a flow definition, scaffold a Power Automate workflow, construct a flow JSON, update an existing flow's actions, patch a flow definition, add actions to a flow, wire up connections, or generate a workflow definition from scratch. Requires a FlowStudio MCP subscription — see https://mcp.flowstudio.app

How do I install it?

Run `npx skills add github/awesome-copilot --skill flowstudio-power-automate-build --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From github/awesome-copilot, a repository with 37,432 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going