evaluation-framework

Evaluate artifacts using weighted criteria and threshold-based decision rules.

326|35|Updated Nov 23, 2025

Search Tags:#evaluation #quality #framework #scoring #thresholds

Ready to run

npx skills add https://github.com/athola/claude-night-market --skill evaluation-framework

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: evaluation-framework
Source: https://github.com/athola/claude-night-market/tree/main/plugins/leyline/skills/evaluation-framework
Command: npx skills add https://github.com/athola/claude-night-market --skill evaluation-framework

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generic weighted scoring and threshold-based decision framework for evaluating artifacts against configurable criteria.

Core Features & Use Cases

Define criteria with weights
Score, combine, and map to decisions
Reusable across domains (docs, code, specs)

Quick Start

Define criteria and thresholds in YAML to drive automated decisions.

Frequently Asked Questions about evaluation-framework

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

FAQPage Schema

How do I set up a weighted scoring system for evaluating quality?▼

Weighted scoring combines multiple criteria with assigned weights to produce a total score. Define your criteria, assign weights to each, score artifacts against them, calculate the weighted total, and apply thresholds to map results to decisions. This framework works across code review, documentation, and risk assessment domains.

Can I use threshold-based decision rules to automate quality gates?▼

Yes. Threshold-based decision rules automatically map scores to pass/fail or accept/reject outcomes. Configure score ranges and assign decisions to each range, enabling automated quality gates without manual review at each step.

What's the best way to define evaluation criteria with different importance levels?▼

Assign weights to each criterion to reflect its importance. Higher weights increase a criterion's contribution to the final score. Define criteria and weights in YAML configuration, then apply them consistently across evaluations to ensure criteria with greater priority drive decisions.

How can I reuse the same scoring framework across different domains?▼

The framework is domain-agnostic. Configure different criteria sets and thresholds for each domain—code review, documentation quality, knowledge intake, or risk assessment—then apply the same weighted scoring and threshold logic to all. Separate configuration from logic for portability.

Does this framework integrate with existing evaluation rubrics and tooling?▼

The framework maps scores to decisions and supports integration with domain-specific rubrics and tooling. Export scores and decisions to downstream systems for reporting, automation, or further analysis in your existing workflow.