AI Output Eval Scorecard

Score AI-generated marketing outputs across accuracy, clarity, brand fit, policy compliance, and actionability.

evaluation, governance, qa, llm-judge, risk-control

Install this skill

./bin/skills-hub install marketing/[email protected] --runtime codex

./bin/skills-hub install marketing/[email protected] --runtime claude

./bin/skills-hub install marketing/[email protected] --runtime generic --target ./my-agent/skills

Operational Summary

Use when: Use when AI-generated marketing outputs need repeatable scoring across quality, compliance, and actionability.

Execution mode: analysis-only

Approval boundary: Safe for evaluation and recommendation; require human approval before approving externally visible copy.

Readiness: Experimental

Security reviewed: no

Lifecycle: Active

ID: marketing/ai-output-eval-scorecard

Runtimes: codex, claude, generic

Tool dependencies: 1

API dependencies: 0

Tools: python3

APIs: Not documented