composite-scorer

Apply weighted composite scoring to evaluate artifacts and generate scores, grades, readiness flags, and prioritized actions.

4|1|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/AreteDriver/ai-skills --skill composite-scorer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: composite-scorer
Source: https://github.com/AreteDriver/ai-skills/tree/main/personas/engineering/composite-scorer
Command: npx skills add https://github.com/AreteDriver/ai-skills --skill composite-scorer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a standardized, reproducible method for evaluating any artifact (code, content, infrastructure) using weighted category sub-scores, resulting in a clear composite score, grade, and prioritized action list.

Core Features & Use Cases

  • Weighted Scoring: Assign importance to different evaluation criteria.
  • Categorization: Break down complex assessments into measurable sub-scores.
  • Grading & Readiness: Assign letter grades (A-F) and determine readiness for deployment or release.
  • Prioritized Actions: Generate a list of actionable steps, ranked by impact.
  • Use Case: Evaluate a new software feature against criteria like correctness, security, and performance, receiving a score, grade, and a list of critical fixes needed before release.

Quick Start

Use the composite-scorer skill to evaluate the attached code against correctness, security, and maintainability criteria, with weights 0.4, 0.3, and 0.3 respectively.

Frequently Asked Questions about composite-scorer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I calculate a weighted composite score for software readiness assessment?

Weighted composite scoring evaluates artifacts by assigning importance weights to defined categories, calculating sub-scores, and aggregating them into a 0-100 score with a letter grade, readiness flag, and prioritized action list.

Can I use a decision matrix to generate a letter grade for code quality assessment?

Defining a decision matrix with weighted categories like maintainability and performance allows the assessment to produce a standardized 0-100 score, an A-F letter grade, a readiness flag, and a prioritized action list.

How do I evaluate infrastructure readiness using performance metrics and categorization?

Evaluating infrastructure readiness involves breaking down performance metrics into measurable weighted sub-scores across defined categories, yielding a standardized JSON output contract with a 0-100 score, readiness flag, and prioritized actions.

Does composite scoring support reproducible quality assessment across different artifact types?

Composite scoring ensures reproducible quality assessment across code, content, and infrastructure artifacts by utilizing a standardized JSON output contract that consistently generates 0-100 scores, letter grades, and prioritized action lists.

What is the best way to prioritize action lists for deployment readiness flags?

Prioritizing action lists for deployment readiness flags involves ranking actionable steps by their impact on weighted category sub-scores, ensuring critical fixes are resolved before release based on the generated 0-100 composite score.