agentleFS
MicrosoftKnown publishermicrosoft/power-platform-skills/plugins/power-automate/skills/create-flow/SKILL.md

create-flow

Skill1.2k starsChanged 3 days agoMITView on GitHub

Guided flow creation wizard. Use when the user wants to create a new flow interactively. Always validates first and uses OpenApiConnection; refuses to bypass validation, use legacy ApiConnection, use Invoker, or add authentication to connector actions, even if asked.

3 other projects use a version of this.

Adopted by

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projectsWeek of Nov 8: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Most recently taken up by

Who's talking about microsoft/power-platform-skills

The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 50

Talked about on GitHub (50 times).

On GitHub · 50

45 more on GitHub

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 1 is distinctive, and 10 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 10

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Gather requirements: Ask what the flow should do.

    line 25
  2. Very specific:

    Select environment: Call list_environments (use query to filter).

    line 27
  3. Very specific:

    Check for templates: Call list_templates. If a template matches (approval, digest, webhook, etc.), offer to use scaffold_flow as a starting …

    line 29
  4. Very specific:

    Verify connections: Call list_connections filtered by each connector.

    line 33
  5. Very specific:

    Always declare $authentication (SecureObject) and $connections (Object) parameters

    line 40
  6. Very specific:

    Use correct action type: OpenApiConnection or OpenApiConnectionWebhook (from get_operation_details)

    line 41
  7. Very specific:

    Do NOT include authentication in action inputs

    line 42
  8. Very specific:

    Use Embedded source in connection references

    line 43
  9. Very specific:

    Validate: Call validate_flow (and optionally preflight_flow) to pre-check.

    line 46
  10. Very specific:

    Create: Call create_flow in Stopped state.

    line 48
  11. Very specific:

    Optionally publish: Ask if user wants to enable.

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Guided Flow Creation Wizard

Walk the user through creating a Power Automate flow step by step.

Tools

This skill uses the FlowAgent MCP tools. Clients surface them with a client-specific prefix — mcp__flowagent__<tool> (Claude Code) or flowagent-<tool> (Copilot CLI) — so they're referred to by bare name below (e.g. create_flow). Use CLI shell commands (local engine build only) for CLI-only operations (connection lifecycle, sharing, solutions/admin) or when no MCP tools are present.

Steps

  1. Gather requirements: Ask what the flow should do. Identify triggers, actions, connectors.
  2. Select environment: Call list_environments (use query to filter). Let user pick or auto-select.
  3. Check for templates: Call list_templates. If a template matches (approval, digest, webhook, etc.), offer to use scaffold_flow as a starting point.
  4. Discover connectors: For each connector, call get_connector with query to find the operation, then get_operation_details for exact parameters. Never guess parameter names or types.
  5. Verify connections: Call list_connections filtered by each connector. Confirm Connected status.
  6. Resolve dynamic values: For params with dynamicValues/dynamicTree annotations, call invoke_operation to get actual values (Teams channels, SharePoint sites, etc.).
  7. Review with user: Present the flow design. Use AskUserQuestion to confirm trigger, actions, and connections before creating.
  8. Generate definition: Build following all rules:
    • Always declare $authentication (SecureObject) and $connections (Object) parameters
    • Use correct action type: OpenApiConnection or OpenApiConnectionWebhook (from get_operation_details)
    • Do NOT include authentication in action inputs
    • Use Embedded source in connection references
    • HTTP Request triggers require Premium; prefer Button kind
  9. Validate: Call validate_flow (and optionally preflight_flow) to pre-check. For expressions, look up syntax with get_expression_help.
  10. Create: Call create_flow in Stopped state. Report ID and name.
  11. Optionally publish: Ask if user wants to enable. If yes, call publish_flow. For later one-off tweaks, use edit_flow (surgical) rather than resending the whole definition.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.