skills.rest
ZTE-AICloud
ZTE-AICloudOFFICIAL
Explore all skills by this author →
GitHub

evaluation-rubric

Assess specification outputs with a four-dimension rubric and YAML reports.

52|3|Updated Feb 14, 2026
Search Tags:#checklist#specification#quality#traceability#rubric#evaluate
One-click install
npx skills add https://github.com/ZTE-AICloud/Co-OmniSpec --skill evaluation-rubric
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: evaluation-rubric
Source: https://github.com/ZTE-AICloud/Co-OmniSpec/tree/main/skills/evaluation-rubric
Command: npx skills add https://github.com/ZTE-AICloud/Co-OmniSpec --skill evaluation-rubric

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Spec content quality assessment rubric for outputs produced in spec_eval mode. Defines four dimensions scoring (business value, technical completeness, clarity & testability, traceability) with check items, scoring criteria, and YAML report format. Used by evaluation-analyst (Eva) in evaluation workflows.

Core Features & Use Cases

  • Four-dimension scoring system: 25 points per dimension, total 100 points, with explicit criteria for each dimension.
  • Clear checklists and objective criteria to ensure consistency across evaluations.
  • YAML-based evaluation reports for easy integration with tooling and audits.

Quick Start

Run a rubric-based evaluation on a spec artifact to generate a YAML evaluation report.

Frequently Asked Questions about evaluation-rubric

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

FAQPage Schema
How do I evaluate specification quality using a scoring rubric?▼

Assess specification content quality using a four-dimension rubric covering business value, technical completeness, clarity and testability, and traceability, scoring 25 points per dimension to total 100 points and outputting a YAML evaluation report.

What does traceability evaluation involve for requirement specifications?▼

Traceability evaluation checks traceable mappings from user stories to features, designs, and acceptance criteria within specification outputs, ensuring complete requirements coverage and alignment across the spec_eval workflow.

Can I generate YAML reports for spec quality assessments?▼

Yes, you can generate YAML-based evaluation reports that include explicit checklists, objective scoring criteria, and dimension scores, ensuring easy integration with tooling and audit processes for specification outputs.

What are the best criteria for assessing technical completeness in a spec?▼

Assessing technical completeness uses explicit checklists to verify required specification elements, ensuring objective scoring and consistency across evaluations within the rubric's 25-point framework.

How do you measure business value in a specification evaluation?▼

Business value is measured as one of the four rubric dimensions, scoring specification outputs against explicit criteria to determine alignment with intended business outcomes for up to 25 points.

Related Skills

Explore More Content & Communication Skills→
aaronbassettaaronbassett

dapp-sdd:specify

Generate a structured specification document from a dApp README.

Community
Advanced
duc01226duc01226
7

plan-analysis

Parse implementation plans to extract requirements and assess architecture impact.

Community
Advanced
FVossebeldFVossebeld

evaluation

Evaluate agent outputs with weighted rubric criteria and per-dimension scores.

Community
Advanced
multiplex-aimultiplex-ai
2

geo-content

Score E-E-A-T signals and AI citability for web content pages.

Official
Advanced