Skip to content

Comments

[DRAFT] feat: Add agent/evaluate/agent-framework as sub-skill to microsoft foundry skill#914

Draft
kuojianlu wants to merge 1 commit intomicrosoft:mainfrom
kuojianlu:kuojianlu/eval-skill
Draft

[DRAFT] feat: Add agent/evaluate/agent-framework as sub-skill to microsoft foundry skill#914
kuojianlu wants to merge 1 commit intomicrosoft:mainfrom
kuojianlu:kuojianlu/eval-skill

Conversation

@kuojianlu
Copy link

@kuojianlu kuojianlu commented Feb 13, 2026

Add agent/evaluate/agent-framework as sub-skill to microsoft foundry skill, which covers:

  • Clarify metrics, dataset
  • Configure judge model
  • Generate evaluation codes
  • Run-fix loop to resolve code issue
  • Generate evaluation.md

Important: This needs to be updated and merged after #824

…undry

Add agent/evaluate/agent-framework as sub-skill to microsoft foundry skill, which covers:
- Clarify metrics, dataset
- Configure judge model
- Generate evaluation codes
- Run-fix loop to resolve code issue
- Generate evaluation.md
@kuojianlu kuojianlu changed the title feat: Add agent/evaluate/agent-framework as sub-skill to microsoft foundry skill [DRAFT] feat: Add agent/evaluate/agent-framework as sub-skill to microsoft foundry skill Feb 13, 2026
Comment on lines +47 to +50
const agentMetadata = await run({
prompt: "Evaluate my Foundry agent built with Microsoft Agent Framework using pytest evaluators.",
shouldEarlyTerminate: terminateOnCreate,
});

Check failure

Code scanning / CodeQL

Invocation of non-function Error test

Callee is not a function: it has type undefined.
Comment on lines +75 to +78
const agentMetadata = await run({
prompt: "Add a custom evaluator to assess my agent's task completion using pytest-agent-evals.",
shouldEarlyTerminate: terminateOnCreate,
});

Check failure

Code scanning / CodeQL

Invocation of non-function Error test

Callee is not a function: it has type undefined.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant