agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/aibast-agents-library/skills/deploy-to-copilot-studio/SKILL.md

deploy-to-copilot-studio

Skill8 starsChanged 3 months agoMITView on GitHub

Deploy an AIBAST Agents Library solution (for example Tiered Huddle Board) into the user's own Copilot Studio environment with their own sign-in. Use when someone asks to deploy, install or try a library solution in Copilot Studio, or to remove one.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Sign in: Run python3 copilot_studio_deploy_agent.py check.

    line 24
  2. Very specific:

    If it says they are not signed in, have them run pac auth create --deviceCode themselves and finish the sign-in in their browser.

    line 25
  3. Very specific:

    Pick an environment: Run python3 copilot_studio_deploy_agent.py envs and ask which one to use.

    line 28
  4. Very specific:

    Deploy only after the user says yes: Run the same command with deploy ...

    line 34
  5. Very specific:

    Never pass --yes until the user has seen the plan and agreed.

    line 44
  6. Distinctive:

    Never store or print tokens or passwords.

    line 45
  7. Distinctive:

    If a step fails, read the summary to the user and stop.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Deploy a library solution to Copilot Studio

You help the user put one library solution into their own Copilot Studio environment. Everything runs through one script with the user's own Power Platform sign-in. Show each command before you run it.

Get the script (once)

curl -fsSLo copilot_studio_deploy_agent.py https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/agents/@aibast-agents-library/templates/copilot_studio_deploy_agent.py

It needs Python 3 and the Power Platform CLI (pac). If pac is missing, tell the user how to install it (dotnet tool install --global Microsoft.PowerApps.CLI.Tool, or the Windows installer) and stop.

Steps

  1. Sign in. Run python3 copilot_studio_deploy_agent.py check. If it says they are not signed in, have them run pac auth create --deviceCode themselves and finish the sign-in in their browser. Never ask for or type a password.
  2. Pick an environment. Run python3 copilot_studio_deploy_agent.py envs and ask which one to use. Suggest a test environment, not production.
  3. Check first. Run python3 copilot_studio_deploy_agent.py plan <solution> --env "<environment>". Tell the user, in plain words, what will happen and every note (already installed, missing connections). Nothing changes in this step.
  4. Deploy only after the user says yes. Run the same command with deploy ... --yes. Add --replace only if they asked to overwrite an existing install.
  5. Report. Give the summary, then the test_question for them to ask in Copilot Studio's test pane.
  6. Undo, if asked. python3 copilot_studio_deploy_agent.py undo <solution> --env "<environment>" --yes after the user confirms.

Rules

  • Never pass --yes until the user has seen the plan and agreed.
  • Never store or print tokens or passwords.
  • If a step fails, read the summary to the user and stop. Do not retry with different flags on your own.
  • Solution names are the library's folder names, such as tiered-huddle-board.

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.

Check your setup, free