quality-evaluation

Installation
SKILL.md

Quality Evaluation Skill

Evaluate Allied Brass generated product content using a performance-oriented rubric. This skill measures whether content would make a shopper click — not whether it followed the rules.

When to Use

  • After generating content via the pipeline, to validate quality before approval
  • When reviewing existing candidate_content in the generated_content table
  • When comparing content versions (before/after prompt changes)
  • When creating gold standard examples for the prompt_templates table
  • When the quality-evaluation skill is referenced by other skills (e.g., quality_rubric.yaml)

Why the Current Scoring Fails

The pipeline's self_score in prompts.py uses 6 criteria:

Current Criterion What It Measures The Problem
specificity Does it mention specific product details? Listing specs ≠ compelling copy. "18-inch center-to-center" scores high but reads like a database export.
Related skills
Installs
3
First Seen
Mar 5, 2026