Author eval suite for skill `azure-policy-advisor`

[arnaudlh]

Skill

azure-policy-advisor — source: .github/skills/azure-policy-advisor/SKILL.md

Scope

Author the eval suite at .github/evals/azure-policy-advisor/:

• eval.yaml — suite config (executor, model, graders)
• At least 2 positive tasks under tasks/positive-*.yaml
• At least 1 negative task under tasks/negative-*.yaml
• Entry added to .github/evals/manifest.yaml at tier: expanded

Procedure

1. /skill-bench azure-policy-advisor drafts the suite from the live SKILL.md.
2. waza run .github/evals/azure-policy-advisor/eval.yaml -v locally.
3. /skill-improve azure-policy-advisor to iterate on graders.
4. Open PR.
5. Mock CI runs automatically. A maintainer will dispatch a real-model run before merge.

Acceptance

• Suite runs cleanly in mock executor.
• At least one positive task passes in a real-model run.
• All negative tasks produce a refusal or out-of-scope acknowledgement.
• manifest.yaml entry added; PR description includes the real-model run summary.

Conventions to follow

• Persona lock: refusal graders should accept the agent's own scope language.
• Don't add required_skills to a skill_invocation grader unless the skill genuinely invokes those sub-skills.
• Prompt graders need continue_session: true in their grader config.

Related

• Umbrella: [meta] Eval suite coverage for agents and skills #93
• Harness: Agent/Skill eval framework #61