ai-test

Generate executable pytest tests for AI components with deterministic outputs.

1|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/selcukyucel/north-starr-genai --skill ai-test-selcukyucel
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-test
Source: https://github.com/selcukyucel/north-starr-genai/tree/main/skills/ai-test
Command: npx skills add https://github.com/selcukyucel/north-starr-genai --skill ai-test-selcukyucel

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the creation of executable pytest tests for AI components that produce deterministic outputs, enabling fast CI checks and regression protection.

Core Features & Use Cases

  • Generates hard-assertion tests for classifications, extractions, and routing decisions so failures indicate real regressions.
  • Integrates with existing eval suites, fixtures, and test conventions to maximize reuse and reduce manual writing.
  • Useful for ensuring AI components behave consistently when inputs and configurations are controlled.

Quick Start

Create an example test file that asserts deterministic outputs for a representative AI component.

Frequently Asked Questions about ai-test

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

FAQPage Schema
How do I generate deterministic pytest tests for AI components?

You generate deterministic pytest tests by automating the creation of executable assertions for AI classifications, extractions, and routing decisions. This ensures failures indicate real regressions when AI component outputs are controlled.

What is deterministic AI test generation in CI/CD pipelines?

Deterministic AI test generation in CI/CD pipelines automates executable pytest creation for AI components with controlled outputs. It applies schema validation and markers like happy_path, edge_case, and regression to protect against behavior changes.

Can I integrate generated pytest tests with existing test conventions and fixtures?

You can integrate generated pytest tests with existing eval suites, fixtures, and project-specific test conventions. This maximizes reuse and reduces manual writing by satisfying requirements for real imports and realistic inputs.

Does pytest test generation work for AI routing and extraction regression checks?

Pytest test generation works for AI routing and extraction regression checks by producing hard-assertion tests. These tests verify that classifications and routing decisions behave consistently when inputs and configurations are controlled.

What are the limitations of automating AI test generation for non-deterministic outputs?

Automating AI test generation is limited to components producing deterministic outputs. It is not suited for non-deterministic AI models where outputs vary across runs, as hard-assertion tests require controlled and predictable behavior to detect regressions.