Public skill
m365-agent-evaluator
Use this skill when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @microsoft/m365-copilot-eval CLI. Trigger on intents such as "evaluate my agent", "test my agent", "run my evals", "create eval prompts", "add multi-turn tests", "tune evaluator thresholds", "why is my agent failing", or "set up eval environment variables".
Package contents
Manifest
Use this skill when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @microsoft/m365-copilot-eval CLI. Trigger on intents such as "evaluate my agent", "test my agent", "run my evals", "create eval prompts", "add multi-turn tests", "tune evaluator thresholds", "why is my agent failing", or "set up eval environment variables".
803d6ba86678f9c732649941662712f624f4f5eca0499bab452cc58df7416663- SKILL.md8,124 bytes
- examples/analyze-failures.md1,507 bytes
- examples/basic-generation.md1,822 bytes
- examples/iterate-on-changes.md1,302 bytes
- examples/missing-instructions.md1,581 bytes
- examples/not-atk-project.md1,452 bytes
- examples/run-and-analyze.md1,660 bytes
- references/azure-setup.md5,927 bytes
- references/eval-templates.md5,176 bytes
- references/guardrails.md4,221 bytes
- references/output-schema.json4,051 bytes
- references/output-schema.md2,711 bytes
- references/pra-framework.md3,319 bytes
- references/prompts-schema.json15,760 bytes
- references/remediation-patterns.md3,675 bytes
- references/result-analysis.md4,514 bytes
- references/workflow.md6,623 bytes
Release history