agentleFS
MicrosoftKnown publishermicrosoft/skills-for-copilot-studio/skills/clone-agent/SKILL.md

clone-agent

Skill486 starsChanged 8 months agoMITView on GitHub

Clone a Copilot Studio agent from the cloud. Guides through environment selection, agent selection, and downloads agent YAML files.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 3 are distinctive, and 11 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 11

    Very specific

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

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

    Look for existing connection details in this order.

    line 23
  2. Distinctive:

    Search the filesystem for previously cloned agents — these already have all the connection details:

    line 27
  3. Very specific:

    If the user picks one → extract tenantId, environmentId, environmentUrl, agentMgmtUrl and skip to Phase 2 (or Phase 1 if they want a …

    line 47
  4. Very specific:

    If the user pastes a Copilot Studio URL (e.g.

    line 51
  5. Very specific:

    If the user provides a URL like this, you still need a tenantId (from a conn.json or by asking the user).

    line 59
  6. Very specific:

    If no conn.json found (or user wants a different tenant) → ask for their tenant ID (required).

    line 72
  7. Distinctive:

    Run the list-envs command:

    line 80
  8. Distinctive:

    Ask the user to pick an environment.

    line 96
  9. Very specific:

    If only mine → run without --no-owner (default, filters by current user)

    line 105
  10. Very specific:

    If all agents → add --no-owner flag

    line 106
  11. Very specific:

    Ask the user to pick an agent.

    line 125
  12. Very specific:

    Run the clone command. The workspace should be the current directory (.).

    line 129
  13. Very specific:

    Run Glob: /agent.mcs.yml to find and show the cloned agent file

    line 144
  14. Very specific:

    Check that .mcs/conn.json was created in the agent directory

    line 145

≈ “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

Clone Agent

Guided flow to clone a Copilot Studio agent from the cloud to a local workspace. Walks the user through environment selection, agent selection, and downloads the agent's YAML files.

IMPORTANT: Do Not Modify Scripts

This is a new capability under active development. If the manage-agent script fails, do not attempt to fix, patch, or work around it. Instead:

  1. Show the user the full error output
  2. Direct them to https://github.com/microsoft/skills-for-copilot-studio/issues
  3. Suggest using the Copilot Studio VS Code extension directly as a fallback for push/pull/clone

Phase 0: Resolve Configuration

Look for existing connection details in this order. Stop at the first source that provides a tenantId:

0a. Scan for existing .mcs/conn.json files

Search the filesystem for previously cloned agents — these already have all the connection details:

Glob: **/.mcs/conn.json

Also search common project locations:

Glob: /Users/**/projects/**/.mcs/conn.json

Each conn.json contains TenantId, EnvironmentId, DataverseEndpoint, AgentManagementEndpoint, and AccountInfo. Parse any found files and collect unique tenant/environment pairs. If matches are found, present them to the user:

Found existing agent connections:

  1. Employee Assistant — Elad's Env (tenant: 8a235459...)
  2. IT Agent — Contoso Dev (tenant: efb073bb...)

Use one of these, or enter a different tenant ID?

If the user picks one → extract tenantId, environmentId, environmentUrl, agentMgmtUrl and skip to Phase 2 (or Phase 1 if they want a different environment).

0b. Check for a Copilot Studio URL

If the user pastes a Copilot Studio URL (e.g. from their browser while viewing the agent), extract environment and agent IDs directly — no need for list-envs or list-agents.

Recognised URL formats:

https://copilotstudio.microsoft.com/environments/<envId>/bots/<agentId>/overview
https://copilotstudio.preview.microsoft.com/environments/<envId>/bots/<agentId>

If the user provides a URL like this, you still need a tenantId (from a conn.json or by asking the user). Then skip to Phase 3, passing --url instead of --agent-id / --environment-id / --environment-url / --agent-mgmt-url:

node ${CLAUDE_SKILL_DIR}/../../scripts/manage-agent.bundle.js clone \
  --workspace "." \
  --tenant-id "<tenantId>" \
  --url "<copilotStudioUrl>"

The script will parse the URL to extract the environment ID and agent ID, then resolve the remaining environment details (Dataverse URL, agent management URL) automatically via the BAP API.

0c. Ask the user

If no conn.json found (or user wants a different tenant) → ask for their tenant ID (required).

No --client-id is needed — the script uses VS Code's first-party client ID with interactive browser login automatically.

Phase 1: Select Environment

Tell the user: "A browser window may open for Microsoft sign-in (tokens are cached after first login)."

Run the list-envs command:

node ${CLAUDE_SKILL_DIR}/../../scripts/manage-agent.bundle.js list-envs \
  --tenant-id "<tenantId>"

Timeout: 300000ms (5 minutes) — set this on the Bash tool call to allow time for browser auth.

Parse the JSON output. On success (status: "ok"), present the environments as a numbered list to the user:

1. Contoso Dev (abc123-...)
2. Contoso Prod (def456-...)

Ask the user to pick an environment. Extract:

  • environmentId
  • environmentUrl (the url or dataverseUrl field)
  • agentMgmtUrl (the agentManagementUrl field)

Phase 2: Select Agent

First, ask the user: "Do you want to list only agents you own, or all agents in the environment?"

  • If only mine → run without --no-owner (default, filters by current user)
  • If all agents → add --no-owner flag
node ${CLAUDE_SKILL_DIR}/../../scripts/manage-agent.bundle.js list-agents \
  --tenant-id "<tenantId>" \
  --environment-url "<environmentUrl>" \
  [--no-owner]

Timeout: 300000ms (5 minutes)

Parse the JSON output. Each agent has agentId, displayName, and ownedByCurrentUser. Present agents as a numbered list:

1. My Support Bot (yours)
2. HR Assistant
3. IT Helpdesk (yours)

Ask the user to pick an agent. Extract the agentId.

Phase 3: Clone

Run the clone command. The workspace should be the current directory (.). The --agent-id is required (from Phase 2):

node ${CLAUDE_SKILL_DIR}/../../scripts/manage-agent.bundle.js clone \
  --workspace "." \
  --tenant-id "<tenantId>" \
  --agent-id "<agentId>" \
  --environment-id "<environmentId>" \
  --environment-url "<environmentUrl>" \
  --agent-mgmt-url "<agentMgmtUrl>"

Timeout: 300000ms (5 minutes)

On success:

  1. Run Glob: **/agent.mcs.yml to find and show the cloned agent file
  2. Check that .mcs/conn.json was created in the agent directory
  3. Summarize what was cloned and where the files are

Error Handling

ErrorResolution
Browser auth fails or times outAsk user to try again; check that they have access to the tenant
No environments foundVerify tenant ID is correct and user has Power Platform access
No agents foundVerify environment selection; user may need Copilot Studio access
Clone failsCheck permissions; the user needs maker/admin access to the agent

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.