Skills for Copilot Studio is a plugin for authoring, testing, and troubleshooting standard Microsoft Copilot Studio agents as YAML files from a terminal or editor. It is intended for users of Claude Code, GitHub Copilot CLI, and VS Code who work with Copilot Studio agents. The catalogue add-ons are the plugin's skills, agents, hook, and plugin definition.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/skills-for-copilot-studio --skill create-eval-setgit clone --depth 1 https://github.com/microsoft/skills-for-copilot-studioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/skills-for-copilot-studio/create-eval-set)<a href="https://agentmods.dev/skills/microsoft/skills-for-copilot-studio/create-eval-set"><img src="https://agentmods.dev/badge/skills/microsoft/skills-for-copilot-studio/create-eval-set.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.01292 |
| Opus 5 | $0.00034 | $0.00646 |
| Sonnet 5 | $0.00014 | $0.00258 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
create-eval-set scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Evaluation Test Set
Create a test set CSV file that can be imported into Copilot Studio's Evaluate tab for in-product agent evaluation.
Phase 1: Understand the Agent
Read the agent's YAML files to understand what it does:
Glob: **/agent.mcs.yml— find the agent- Read
agent.mcs.yml— get the agent's instructions, description, and capabilities - Read
settings.mcs.yml— check orchestration mode (generative vs classic) Glob: **/topics/*.mcs.yml— list all topics- Read key topics (especially non-system ones) — understand trigger phrases, conversation flows, expected behaviors
- Check for knowledge sources, actions, and connected tools
Phase 2: Design Test Cases
Create test cases that cover:
| Category | What to test | Example |
|---|---|---|
| Core functionality | Main topics and capabilities | Questions matching trigger phrases |
| Knowledge/generative | Knowledge source responses | Questions the agent should answer from its knowledge |
| System topics | Greeting, Escalation, Goodbye, Thank You, Fallback | "Hi", "I want to speak to a person", "Goodbye" |
| Edge cases | Out-of-scope, ambiguous, off-topic | "Tell me a joke", "Book a flight for me" |
| Boundary testing | Things the agent should NOT do | Actions beyond its capabilities |
Aim for 10–25 test cases with good coverage across categories.
Phase 3: Write the Expected Responses
The CSV import only supports two columns: question and expectedResponse. Test methods cannot be set via CSV import — they are configured in the UI after import. The default test method (General quality) is applied to all imported test cases.
Write expected responses with this in mind:
- For questions where you want General quality grading: write behavioral descriptions ("The response should recommend hotels in Paris with relevant details")
- For questions where you'll later switch to Compare meaning or Exact match in the UI: write realistic agent replies that the grader can compare against
- Leave
expectedResponseempty for questions that only need General quality (it works without expected responses)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 125 lines · 68 tokens per session scan A af5d744065ec
create-eval-set is a skill published in the GitHub repository microsoft/skills-for-copilot-studio (430 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 1,292 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
trailblaze
Use when working with Trailblaze — natural-language device control for coding agents across iOS, Android, and web, with replayable .trail.yaml files as the artifact. Trigger on mentions of Trailblaze, the trailblaze CLI, .trail.yaml files, trailmaps, waypoints, or requests to drive / author / debug / run UI tests on…
Detox Mobile Testing
Gray-box end-to-end testing for React Native apps with Detox. Covers .detoxrc.js configuration, build and test commands, matchers, device.launchApp control, automatic synchronization, and macOS CI pipelines.