power-automate-mcp: Skill for Claude Code

.claude/skills/build-flow/SKILL.md

build-flow is a skill for Claude Code from OwnOptic/power-automate-mcp. It costs 68 tokens per session (798 once invoked), scanned A, original, MIT.

A skill for creating or changing Microsoft Power Automate flows through its tools. Power Automate is Microsoft’s service for connecting triggers, actions, and external services into automated workflows.

In plain words
What is it for?
Use it to create flows, add or change actions, connect services, and start flows that need connector setup. It covers both simple flows and flows that use services such as databases or other Microsoft connectors.
Why use it?
It prevents common definition and connection mistakes that can make a flow appear to save successfully but fail when it runs. It also keeps secrets out of the workflow definition.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is OwnOptic/power-automate-mcp's own configuration. It tells Claude Code how to work on power-automate-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything power-automate-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to OwnOptic/power-automate-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/OwnOptic/power-automate-mcp/main/.claude/skills/build-flow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/OwnOptic/power-automate-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for build-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/ownoptic/power-automate-mcp/build-flow/github.svg)](https://agentmods.dev/skills/ownoptic/power-automate-mcp/build-flow)
Your own site
<a href="https://agentmods.dev/skills/ownoptic/power-automate-mcp/build-flow"><img src="https://agentmods.dev/badge/skills/ownoptic/power-automate-mcp/build-flow/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for build-flow

Your own site · 80×15
<a href="https://agentmods.dev/skills/ownoptic/power-automate-mcp/build-flow"><img src="https://agentmods.dev/badge/skills/ownoptic/power-automate-mcp/build-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.00798
Opus 5 $0.00034 $0.00399
Sonnet 5 $0.00014 $0.00160
Haiku 4.5 $0.00007 $0.00080

Measured today against content hash 274f41b26591, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

build-flow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/build-flow/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build or modify a Power Automate flow

Definition rules (violating any of these produces a misleading failure)

  1. Always declare the magic parameters at top level next to triggers and actions:
    "parameters": {
      "$connections":    {"defaultValue": {}, "type": "Object"},
      "$authentication": {"defaultValue": {}, "type": "SecureObject"}
    }
    
    Without them, connector flows 400 with an error blaming the trigger, which sends you hunting in the wrong place. Harmless on connector-free flows, so always include them.
  2. Look up connector operationIds and parameter keys on Microsoft Learn. Never guess them - a guessed operationId saves fine and fails at runtime. Use the Microsoft Learn MCP server (microsoft_docs_search, microsoft_docs_fetch):
    • Fetch https://learn.microsoft.com/connectors/<connector>/ once you know the connector (shared_teams -> teams). Searching the bare operationId tends to land on SDK pages instead.
    • Connector pages are large (Teams is ~157k characters). Search first; fetch only when the excerpt is not enough.
    • Skip anything marked [DEPRECATED] and use the replacement it names.
    • A parameter typed dynamic (e.g. Teams body) stops at the top-level key. Take the nested shape from get_flow on a working flow - rule 4. If the Learn server is not connected, say so rather than guessing.
  3. Never inline a secret in a definition. It is stored in plaintext on the flow artifact. Use a Power Platform environment variable or a Key Vault reference.
  4. Start from a working example. get_flow on an existing similar flow and adapt its definition rather than writing one from scratch.

Create

  • Connector-free (Recurrence, Request, Compose, HTTP actions): create_flow(display_name, definition) - it starts immediately.
  • Connector flow: create_flow(..., start=False), then bind_connection(flow_id, connector). Creating never binds connections; a 201 still leaves the flow unstartable ("CannotStartUnpublishedSolutionFlow"). bind_connection resolves the connectionName, PATCHes definition + reference, and starts the flow in one call.
    • status: "ambiguous" - re-call with one of the listed connection_names.
    • status: "not_found" - the connection must first be created and authenticated in the maker portal. No API reachable here can do that.

Read the full file on GitHub · 67 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · +10 lines 274f41b26591
  2. 11d ago First seen · 57 lines · 68 tokens per session scan A decb62b3662b

Subscribe to this mod's changes

build-flow is a skill published in the GitHub repository OwnOptic/power-automate-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 798 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

library-cleanup

Organizes files in a document library so people and AI can find them easily. Scans all files, summarizes issues (duplicates, empty folders, bad names), recommends a clean structure with a visual before/after comparison, reads file content to propose meaningful rename suggestions, then executes with a TODO checklist…

pnp/sharepoint-skills · 81 tokens

organize-library

End-to-end orchestrator that fully organizes a SharePoint document library — classifies files by content type (via the file-classifier skill), creates and extracts metadata columns, applies brand-consistent column and view formatting, builds per-content-type views, colors folders, and creates notification rules for…

pnp/sharepoint-skills · 0 tokens

callback

A callback workflow through Mango Office, a business phone service. It can call a customer, find the resulting recording, and send an SMS if the customer does not answer.

theYahia/WWmcp · 24 tokens

notion

Read and write Notion pages, databases, and blocks via the public REST API — query a database with filters, create/update pages, append block content, search the workspace. Use when the user wants an agent to interact with their Notion workspace (e.g., a tasks or docs database) without the MCP server installed.

mnlt/teleport · 68 tokens

n8n

Manage n8n workflow automation via its public REST API — list/get/create/update workflows, activate/deactivate, inspect execution history, retry/stop executions, manage credentials, tags, variables, users, and projects. Works with self-hosted n8n and n8n Cloud. Use when the user wants programmatic access to their n8n…

mnlt/teleport · 83 tokens

slack

Send messages, read channels, search Slack via its Web API. Use when the user wants to post to a channel, read recent messages, list users/channels, or search a workspace programmatically — no MCP server required.

mnlt/teleport · 48 tokens