feat: Issue #21 - Purpose-Based Critique Criteria
Created critique_criteria.py with purpose-specific evaluation:
TUTORIAL:
- Clarity (30%), Completeness (25%), Progressiveness (20%)
- Actionability (15%), Error Prevention (10%)
EXPLAINER:
- Analogy Quality (25%), Examples (25%), Mental Model (20%)
- Depth (15%), Misconceptions (15%)
TRANSFORMATION:
- Emotional Honesty (30%), Relatability (25%), Hope (20%)
- Specificity (15%), Actionability (10%)
DECIDE:
- Evidence Quality (30%), Balance (25%), Credibility (20%)
- Clarity (15%), Completeness (10%)
REFERENCE:
- Accuracy (35%), Completeness (30%), Organization (20%)
- Examples (15%)
INSPIRED:
- Emotional Impact (30%), Vision (25%), Authenticity (25%)
- Story Quality (20%)
Each criterion has:
- Weight
- Description
- Evaluation questions
- Pass threshold
Functions:
- get_critique_criteria(purpose) → CritiqueCriteriaSet
- evaluate_chapter(content, purpose) → scores
- get_evaluation_prompt(content, purpose) → LLM prompt
- list_all_criteria() → overview
mrhavens
d3bc43daca