agentleFS
MicrosoftKnown publishermicrosoft/copilot-agentic-business-process/.github/skills/deploy-business-process-core/SKILL.md

deploy-business-process-core

Skill1 starsChanged 52 days agoMITView on GitHub

Deploy BusinessProcessCore or check and validate an existing installation, including the Core prerequisite for OrderProcessing.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Before executing any PowerShell, resolve the folder containing this SKILL.md to $skillFolder.

    line 8
  2. Very specific:

    Use Installation Check for check/verify/validate requests and OrderProcessing prerequisite checks.

    line 10
  3. Distinctive:

    Ask whether a Dataverse environment exists.

    line 14
  4. Distinctive:

    Read roles/licensing; run Core readiness.

    line 16
  5. Distinctive:

    Follow the deployment guide.

    line 18
  6. Distinctive:

    Run Installation Check after the final import.

    line 19
  7. Distinctive:

    Follow installation verification.

    line 27

≈ “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 Business Process Core

Before executing any PowerShell, resolve the folder containing this SKILL.md to $skillFolder; do not hardcode its location.

Use Installation Check for check/verify/validate requests and OrderProcessing prerequisite checks. Otherwise use Deploy. Ask which workflow when unclear.

Deploy

  1. Ask whether a Dataverse environment exists. If yes, request its environment ID, not its name or organization ID. Wait for the answer.
  2. Complete technical prerequisites from the repository root.
  3. Read roles/licensing; run Core readiness. Resolve failures and document unverified requirements.
  4. Summarize applicable requirements; require explicit user confirmation of understanding and availability of access, licenses, Copilot Credits, and delegated support.
  5. Follow the deployment guide. For new environments, verify active tenant-wide Power Platform Administrator and obtain provisioning approval; confirm the new ID and rerun readiness.
  6. Run Installation Check after the final import. Require every check to pass
  7. Provide the deployment summary. Hand over the environment/organization IDs, solution and package versions, application-user/connection IDs, role verification, Workflow Console URL, and credential expiry/secure storage reference. Do not include secrets.

Installation Check

  1. Require an existing environment ID, tenant ID, organization ID/URL, and approved package/version and managed/unmanaged state. Do not provision an environment.
  2. Complete technical prerequisites from the repository root.
  3. Follow installation verification; run the bundled script and evaluate every criterion, including runtime privileges and all 13 tool associations.
  4. Report Pass, Fail, or Not verified per criterion with brief evidence. Overall Pass requires all criteria to pass. Stop on failures/unknowns; obtain separate approval for repairs and rerun after repair. Do not import, publish, activate, or run business actions in this workflow.

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.