Test Auth logo

Test Auth

Organization
microsoft
test-auth

Authenticate for Copilot Studio evaluation API and SDK chat. Caches a token that is shared across run-eval and chat-sdk skills. Run this before any eval or SDK chat workflow. Requires an App Registration with MakerOperations and Copilots.Invoke permissions.

Overview

Publishermicrosoft
Repositoryskills-for-copilot-studio
Skill nametest-auth
Stars
478
Forks
101
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Test Auth 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/microsoft/skills-for-copilot-studio/tree/main/skills/test-auth
  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/microsoft/skills-for-copilot-studio.git /tmp/skills-for-copilot-studio
mkdir -p .claude/skills
cp -r /tmp/skills-for-copilot-studio/skills/test-auth .claude/skills/test-auth
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Test Auth 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 Test Auth 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 Test Auth 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.

Test Agent Authentication

Authenticate with the Power Platform API for evaluation and SDK chat workflows. This caches a token in the "test-agent" slot that is shared by run-eval and chat-sdk.

Step 1: Find the workspace

Locate the agent workspace (directory containing .mcs/conn.json):

bash
Glob: **/agent.mcs.yml

The conn.json provides the tenant ID automatically — no need to ask the user for it.

Step 2: Get the client ID

CRITICAL: You MUST present the FULL configuration checklist below when asking for the client ID. Do NOT omit any items — users frequently miss the redirect URI and public client settings, which causes auth failures.

Ask the user for their App Registration Client ID and show them all of the following requirements in your message:

What is your App Registration Client ID for the Evaluation API?

Before sharing it, please verify your App Registration has all of these settings:

  1. Redirect URI: Under Authentication > Mobile and desktop applications > redirect URI set to http://localhost
  2. Public client: Under Authentication > Advanced settings > Allow public client flows set to Yes
  3. API permissions: Under API permissions, these delegated permissions on the Power Platform API:
    • CopilotStudio.MakerOperations.Read (list test sets, get results)
    • CopilotStudio.MakerOperations.ReadWrite (start evaluation runs)
    • CopilotStudio.Copilots.Invoke (SDK chat — send utterances to the agent)
  4. Admin consent: Granted for the tenant (green checkmarks in the API permissions list)

Missing any of these will cause authentication to fail.

If the user doesn't have one, guide them:

How to create an App Registration:

  1. Go to Azure Portal > App Registrations
  2. Click New registration, name it (e.g., "Copilot Studio Eval")
  3. Under API permissions > Add a permission > APIs my organization uses > search Power Platform API
  4. Select Delegated permissions and add:
    • CopilotStudio.MakerOperations.Read
    • CopilotStudio.MakerOperations.ReadWrite
    • CopilotStudio.Copilots.Invoke
  5. Click Grant admin consent for the tenant
  6. Under Authentication > Add a platform > Mobile and desktop applications > set redirect URI to http://localhost
  7. Still in Authentication, scroll to Advanced settings and set Allow public client flows to Yes (required — without this the interactive browser login will fail with an AADSTS error)
  8. Copy the Application (client) ID from the Overview page

Step 3: Authenticate

Run the auth command (opens a browser — no device code needed):

bash
node ${CLAUDE_SKILL_DIR}/../../scripts/eval-api.bundle.js auth --workspace <path> --client-id <id>

If successful, you'll see:

json
{"status": "ok", "message": "Authentication successful. Token cached for subsequent commands."}

Return the client ID and workspace path to the caller — they need these for subsequent run-eval and chat-sdk calls.

Troubleshooting

  • HTTP 403 / InsufficientDelegatedPermissions: The app registration is missing required permissions. Guide the user through adding them (Step 2).
  • AADSTS700016 / app not found in directory: The client ID doesn't exist in the agent's tenant. The app must be registered in the same tenant as the Copilot Studio environment (check conn.json > AccountInfo.TenantId).
  • AADSTS7000218 / request body must contain client_secret or client_assertion: The app registration is not configured as a public client. Go to Authentication > Advanced settings > set Allow public client flows to Yes.
  • SDK chat hangs after auth: The cached token may have stale permissions. Clear the cache and re-authenticate:
    • Delete ~/.copilot-studio-cli/test-agent.cache.json
    • Run security delete-generic-password -s "copilot-studio-cli" -a "test-agent" to clear the macOS Keychain entry
    • Re-run the auth command

Frequently asked questions

What does the Test Auth AI skill do?

Authenticate for Copilot Studio evaluation API and SDK chat. Caches a token that is shared across run-eval and chat-sdk skills. Run this before any eval or SDK chat workflow. Requires an App Registration with MakerOperations and Copilots.Invoke permissions.

Why use Test Auth on TypingMind?

Because you install it once and use it with any model. Test Auth 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 Test Auth in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/microsoft/skills-for-copilot-studio/tree/main/skills/test-auth. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Test Auth?

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 Test Auth?

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

Is the Test Auth AI skill free?

Yes. It is published on GitHub by microsoft 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 👇