invalid-bad-rubric

Test rubric validation in AI skill evaluation harnesses.

3|1|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/humanity4ai/project_human --skill invalid-bad-rubric
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: invalid-bad-rubric
Source: https://github.com/humanity4ai/project_human/tree/main/evals/fixtures/invalid-bad-rubric
Command: npx skills add https://github.com/humanity4ai/project_human --skill invalid-bad-rubric

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This is a test fixture skill used within the eval harness test suite to validate rubric processing.

Core Features & Use Cases

  • Purpose: Serves as a placeholder for testing the evaluation framework's ability to handle skills with specific configurations.
  • Boundaries: Designed for non-clinical support and includes escalation protocols for detected risk signals.
  • Workflow: Follows a standard process of context identification, skill protocol application, and structured output generation.

Quick Start

Use the invalid-bad-rubric skill to test the eval harness.

Frequently Asked Questions about invalid-bad-rubric

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

FAQPage Schema
What is a test fixture for rubric validation in an eval harness?

It serves as a placeholder skill within the test suite to validate how the evaluation framework processes and scores skills with specific rubric configurations and incomplete definitions.

How do I test my AI skill evaluation harness with incomplete rubrics?

You can use a dedicated fixture skill to test the evaluation harness by applying a standard workflow of context identification, skill protocol application, and structured output generation to validate framework robustness.

Does this test fixture support clinical use cases?

No, this test fixture is explicitly designed for non-clinical support boundaries and includes specific escalation protocols for handling detected risk signals rather than medical applications.

When do I need a fixture skill for eval harness testing?

You need a fixture skill when developing or testing an AI evaluation framework to ensure the system correctly handles specific configurations, validates rubrics properly, and processes structured outputs accurately.

What are the limitations of using an incomplete rubric fixture?

The fixture is intended solely for internal testing and development of the evaluation framework, meaning it should not be deployed in production environments or used for actual user-facing tasks.