copilot-studio-agent-test
Test Microsoft Copilot Studio agents programmatically against a set of question/answer pairs, without driving a browser. Use when the user wants to evaluate, test, validate, benchmark or regression-test a Copilot Studio agent; run an eval set or test set against an agent; check whether an agent answers correctly from its knowledge bases; verify agent grounding or citations; or ask a Copilot Studio agent a question from the command line. Triggers include 'test my Copilot Studio agent', 'run an eval against the agent', 'validate agent answers', 'check the agent knowledge base', 'ask the agent', 'regression test the agent'. Do NOT use for building or authoring agents, for Copilot Studio topic design, or for testing declarative agents in Microsoft 365 Copilot.
Agent Skill from microsoft/cat-agent-skills
Copilot Studio
Passes documented load rulesNo documented load rule failed.
Microsoft 365 Copilot Preview, Frontier tenants only
Needs changes- Fails: Every file has a supported file type (M365-FILE-TYPES)
1 unsupported: scripts/cs-agent-test.cmd
rule · Microsoft 365 Copilot: Supported file and script types
An agent can have at most 8 skills. Custom skills aren't available in tenants that use Microsoft Purview Information Barriers.
Standards signals
Meets the agentskills.io required fields.
| Frontmatter | Present and parsed Spec: frontmatter |
| name | Meets the spec (1-64 chars, a-z 0-9 hyphens) Spec: name |
| description | Present, 1-1,024 characters Spec: description |
| compatibility | Absent or under 500 characters Spec: compatibility |
| Name matches folder | Yes (copilot-studio-agent-test)Spec: name |
Observed from the public SKILL.md at the commit above on 2026-10-24. Not a certification: AAIF and the Agent Skills project don't certify skills. Validate your own skill with skills-ref validate.
| Source repo | microsoft/cat-agent-skills |
| Path | submissions/copilot-studio-agent-test/SKILL.md |
| Commit checked | 5c8cad25a6f1 |
| Repo license | MIT |
| Files | 8 |
| Scripts | 2 (1 scanned for the sandbox heuristic) |
| Instructions | 16,330 characters |
| Deepest folder | 1 below the skill folder |
| Rules version | 2026-10-22 |
Re-check the latest version How skill checks work
Rule-based checks of public files against Microsoft's documented load rules, not tested in Copilot Studio or Microsoft 365 Copilot. Independent project, not affiliated with Microsoft.