priority-weight

Score reconciled clusters across five dimensions with 0–10 calibration anchors.

Updated Apr 21, 2026

Search Tags:#scoring #priority #decision-making #reconciled_verdict #cluster-context #auditable-design

Ready to run

npx skills add https://github.com/speplinski/hackathon-opus-47 --skill priority-weight

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: priority-weight
Source: https://github.com/speplinski/hackathon-opus-47/tree/main/skills/priority-weight
Command: npx skills add https://github.com/speplinski/hackathon-opus-47 --skill priority-weight

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This scoring skill provides a deterministic, per-dimension priority vector for reconciled clusters, enabling product teams to rank work by impact and effort and to align L6 decisions with business goals.

Core Features & Use Cases

Score five dimensions (severity, reach, persistence, business_impact, cognitive_cost) for a reconciled cluster using input from L5.
Output raw per-dimension scores (0–10) and allow meta-weights to be applied externally to compute a final priority.
Works across design audits to help triage clusters for L7 decisions.
Use Case: When an L5 cluster has multiple tensions, the L6 skill yields a comparable vector to compare clusters.

Quick Start

Score a reconciled cluster by providing its ReconciledVerdict and cluster context to the L6 priority-weight skill.

Frequently Asked Questions about priority-weight

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

FAQPage Schema

How do I rank design audit clusters by priority and impact?▼

Rank design audit clusters by scoring five priority dimensions: severity, reach, persistence, business impact, and cognitive cost. This generates a comparable per-dimension vector to guide downstream decision-making.

What is multi-dimension priority scoring for reconciled clusters?▼

Multi-dimension priority scoring evaluates a reconciled cluster across five distinct dimensions using a 0–10 scale with calibration anchors. It yields a robust vector for comparing clusters without applying final weighting.

How do I apply priority weights to a ReconciledVerdict?▼

Apply priority weights by passing the ReconciledVerdict and cluster context into the scoring skill. It outputs raw per-dimension scores from 0–10, leaving final meta-weight calculations to external systems.

Can I use custom meta-weights to calculate final priority scores?▼

You can use custom meta-weights by applying them externally to the raw per-dimension scores. The skill intentionally leaves final weighting out, providing a robust score vector for your downstream scoring logic.

Does priority scoring require L5 reconciliation outputs?▼

Priority scoring requires L5 reconciliation outputs, specifically the cluster context, quotes, and the ReconciledVerdict. These inputs provide the necessary tension data to score the five priority dimensions accurately.

When should I not use automated priority scoring for design clusters?▼

You should not use automated priority scoring when final meta-weight alignment is needed within the tool itself, or when an L5 cluster lacks a reconciled verdict and sufficient context for the five-dimension evaluation.