Power Automate logo

Power Automate

Community
korchard333
power-automate

Power Automate Cloud Flows. Use when: designing flows, error handling (scope try/catch), triggers, Dataverse actions, Apply to Each performance, child flows, HTTP connector, expressions, approval flows, Teams Adaptive Cards, desktop flows (RPA).

Overview

Publisherkorchard333
Repositoryclaude-power-platform-community
Skill namepower-automate
Stars
50
Forks
6
Bundled files
9
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by korchard333 on GitHub. Read the source before you install it.

Installation

Install the Power Automate AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/korchard333/claude-power-platform-community/tree/main/.claude/skills/power-automate
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/korchard333/claude-power-platform-community.git /tmp/claude-power-platform-community
mkdir -p .claude/skills
cp -r /tmp/claude-power-platform-community/.claude/skills/power-automate .claude/skills/power-automate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Power Automate in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Power Automate on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Power Automate is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill: Power Automate Cloud Flows

When to Use

Trigger when designing, building, reviewing, or debugging Power Automate cloud flows.


Flow Design Principles

  1. Idempotent flows: Re-running the same trigger should produce the same result
  2. Error handling first: Add try/catch scope before writing the happy path
  3. Minimal permissions: Use service principal connections for production
  4. No hardcoded IDs: Use environment variables or dynamic lookups
  5. Name every action: Descriptive action names are your documentation
  6. Solution-aware: Every production flow must be inside a solution

When to Use Power Automate vs Alternatives

ScenarioRecommendedWhy
React to Dataverse record changesPower AutomateNative trigger with filtering columns
Complex business logic on savePlugin (C#)Runs synchronously in transaction pipeline
Reusable API callable from multiple appsCustom APIRegistered in Dataverse, callable via Web API
Scheduled batch processingPower AutomateRecurrence trigger + pagination
Real-time validation before savePlugin (C#)Pre-operation stage, can throw to block save
External system integration (async)Power AutomateHTTP connector with retry policies
External system integration (sync)Custom ConnectorWhen response needed immediately
UI automation (no API available)Desktop FlowPower Automate Desktop with cloud orchestration

Solution-Aware Flow Checklist

  • Flow is inside a solution (not "My Flows")
  • All connections use Connection References
  • All hardcoded URLs/IDs use Environment Variables
  • Flow has error handling scope (try/catch)
  • Flow name follows convention: [Solution] - [Trigger] - [Action]
  • Run-only permissions configured if shared
  • Trigger conditions set to avoid unnecessary runs
  • Concurrency controls set on Apply to Each loops
  • Action retry policies configured for external calls

⚠️ Verify Flow Patterns Against MS Learn

Before writing flow definitions programmatically, verify patterns using the MS Learn MCP tools:

  1. microsoft_docs_search("power automate [your pattern]") — quick overview
  2. microsoft_docs_fetch(url) — full page detail
  3. microsoft_code_sample_search("power automate [pattern]") — working examples

Skill files are battle-tested but can contain errors. If MS docs contradict what's in the skill file, trust MS docs and flag the discrepancy.


⚠️ REQUIRED: Load Sub-Files Before Implementation

SKILL.md is a summary only — it is NOT sufficient for implementation.

The detailed content (complete payloads, XML templates, working examples, edge-case handling) lives in sub-files in the same directory as this SKILL.md. Before writing any code, you MUST use read_file on the sub-files relevant to your task:

  • Error Handling — Scope-based try/catch/finally pattern, error notification, cleanup actions
  • Triggers — Trigger selection, Dataverse filtering columns, trigger conditions (OData expressions)
  • Dataverse Actions & Performance — Native connector actions, OData filters, Apply to Each concurrency, child flows, pagination pattern, performance profiles
  • Expressions & HTTP Connector — Null-safe access, date formatting, JSON parsing, HTTP resilient pattern with retry policies
  • Approvals & Teams Adaptive Cards — Approval flow pattern, Teams card posting, email notification sync, approval types
  • Desktop Flows (RPA) — When to use RPA, execution modes, cloud-to-desktop integration, best practices
  • Agent Flows — Agent Flows (AI-native automation), generative actions, Automation Center governance, autonomous agent patterns
  • Flow Creation via Web API — Programmatic flow creation, activation, and monitoring via Dataverse Web API: clientdata structure, trigger types, connection reference wiring, activation latency, run monitoring via flowruns entity

Anti-Patterns

  • Flows outside of solutions ("My Flows") — can't be promoted via ALM
  • Dataverse calls inside unbounded Apply to Each (no concurrency limit)
  • Personal connections instead of connection references
  • Missing error handling (no try/catch scope)
  • No retry policy on HTTP actions
  • Hardcoded GUIDs, URLs, or environment-specific values
  • Using "Send an HTTP request to Dataverse" when a native action exists
  • Apply to Each with >1000 items and no pagination strategy
  • Approval flows with Teams cards AND email notifications enabled simultaneously (card won't sync)
  • Using desktop flows when a cloud connector exists for the same system

Related Skills

  • dataverse — Schema design for tables that flows operate on
  • code-apps — Triggering flows from Code Apps via Custom API or Dataverse record triggers
  • custom-connectors — Building connectors for external APIs used in flows
  • alm — Solution packaging, connection references, environment variables for flow deployment
  • plugins — Alternative to flows for synchronous, transactional Dataverse logic

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Power Automate AI skill do?

Power Automate Cloud Flows. Use when: designing flows, error handling (scope try/catch), triggers, Dataverse actions, Apply to Each performance, child flows, HTTP connector, expressions, approval flows, Teams Adaptive Cards, desktop flows (RPA).

Why use Power Automate on TypingMind?

Because you install it once and use it with any model. Power Automate is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Power Automate in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/korchard333/claude-power-platform-community/tree/main/.claude/skills/power-automate. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Power Automate?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Power Automate?

As many as you like. As long as a model supports skills, you can use Power Automate with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Power Automate AI skill free?

Yes. It is published on GitHub by korchard333 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇