← Back to Skills
Product & StrategyBusinessPlatinum

Designing scoring systems, quality rubrics, or evaluation frameworks for content, code, legal, marketing, or AI output.

Scoring System Architect

Criteria Design, Weighting (AHP), Calibration, Radar Charts, IRR Metrics

1 activationsadvanced

Best for

  • Design a multi-dimensional scoring rubric for any artifact type
  • Choose optimal criteria count, scales, and weighting methods
  • Set up inter-rater calibration with anchor examples and kappa checks
  • Build domain-specific scoring for content, code, legal, marketing, or LLM output

What you'll get

  • Multi-dimensional scoring rubric with criteria definitions, AHP-weighted dimensions, 5-level descriptors, and aggregation formula
  • Inter-rater calibration protocol with anchor examples, scoring exercises, IRR measurement, and disagreement resolution procedures
  • Radar chart visualization spec with dimension axes, normalization method, overlay comparison, and threshold indicators for quality tiers
  • Evaluation framework comparing scoring approaches (weighted sum, geometric mean, TOPSIS) with sensitivity analysis and bias detection
Expects

The domain or artifact to score, the purpose of scoring, and who will use the scores.

Returns

Complete scoring system architecture with criteria, weights, descriptors, aggregation method, calibration plan, and visualization recommendation.

What's inside

You are the Scoring System Architect. You design structured, reproducible scoring systems for any domain. You combine psychometric rigor with practical usability, drawing on MCDA research, rubric design literature, and LLM evaluation frameworks. You help teams build scoring systems that transform su...

Covers

Your RoleCore KnowledgeMethodologyScoring System: [Name]
Not designed for ↓
  • ×Implementing scoring algorithms in code
  • ×Statistical analysis or data science tasks

SupaScore

90.5
Research Quality (15%)
9.5
Prompt Engineering (25%)
9.1
Practical Utility (15%)
9
Completeness (10%)
8.8
User Satisfaction (20%)
8.7
Decision Usefulness (15%)
9.2

Evidence Policy

Standard: no explicit evidence policy.

scoringrubricqualityevaluationmetricskpiradar-chartcalibrationinter-ratermcdaweightingassessment

Research Foundation: 8 sources (5 academic, 2 industry frameworks, 1 web)

This skill was developed through independent research and synthesis. SupaSkills is not affiliated with or endorsed by any cited author or organisation.

Version History

v1.0.03/12/2026

Initial release: scoring system design with MCDA, IRR, calibration, radar charts

Works well with

© 2026 Kill The Dragon GmbH. This skill and its system prompt are protected by copyright. Unauthorised redistribution is prohibited. Terms of Service · Legal Notice