evaluation-design

Name: evaluation-design
Availability: InStock
Author: EquiStamp

Design and review AI safety evaluations against the 7-dimension rubric.

Updated Aug 27, 2026

Search Tags:#scoring #rubric #risk-assessment #design-review #ai-safety #phase-3 #evaluation-design

Ready to run

npx skills add https://github.com/EquiStamp/evaluating-evaluations --skill evaluation-design

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: evaluation-design
Source: https://github.com/EquiStamp/evaluating-evaluations/tree/main/.claude/skills/evaluation-design
Command: npx skills add https://github.com/EquiStamp/evaluating-evaluations --skill evaluation-design

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Phase 3 evaluation design for AI safety often requires structured, rubric-aligned design artifacts. This Skill helps users generate rigorous evaluation designs that align with the 7-dimension rubric and Phase 2 outputs to ensure consistent, defensible assessments.

Core Features & Use Cases

Guides users to craft an Evaluation Question, Instrument Design, Score Against Rubric, and Operational Checklist.
Supports both from-scratch design and review of existing evaluation designs for risk-grounded decisions.
Produces a complete Evaluation Design Document including tier justification, inputs, scoring, and exclusion criteria, plus a final scorecard.

Quick Start

Provide Phase 2 targets and request a Phase 3 design or review, and receive a complete Evaluation Design Document.

Frequently Asked Questions about evaluation-design

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

FAQPage Schema

How do I design an AI safety evaluation using a rubric?▼

To design an AI safety evaluation using a rubric, you align instrument inputs and scoring against a 7-dimension framework, generating a complete design document with an operational checklist and final scorecard.

What is a 7-dimension rubric for AI safety risk assessment?▼

A 7-dimension rubric for AI safety risk assessment is a structured scoring framework that evaluates evaluation designs across multiple operational criteria to ensure consistent and defensible risk-grounded decisions.

How do I review an existing AI safety evaluation design?▼

To review an existing AI safety evaluation design, score the current instrument against the 7-dimension rubric, verify exclusion criteria, and apply an operational checklist to produce a final Assessment Scorecard.

Do I need Phase 2 targets to generate an AI safety evaluation design?▼

Providing Phase 2 targets is required to generate a Phase 3 evaluation design, ensuring your evaluation question and instrument inputs align directly with established risk assessment targets.

What should be included in an evaluation design document for AI safety?▼

An evaluation design document for AI safety should include the evaluation question, instrument design with inputs and scoring, item generation, tier justification, operational checklist results, exclusion criteria, and a final scorecard.