scenario-test-designer

Community

Design and validate scenario-based agent tests.

AuthorOxilith
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps teams design and author scenario-based tests to evaluate AI agent behavior, ensuring robust evaluation coverage across skills, commands, and agents.

Core Features & Use Cases

  • Provides academic, pressure, edge-case, and integration test categories to cover diverse agent behaviors
  • Generates scenario test files and associated evaluation rubrics to standardize assessment
  • Supports interactive prompting via AskUserQuestion for persona- and context-specific testing
  • Uses template-driven initialization to accelerate test creation and maintain consistency

Quick Start

  • Initialize tests with the provided CLI: init_scenario_tests.py <target-name> <category> [--name <test-name>] [--persona <name>]
  • Review and customize test files: test-<name>.md and evaluation-rubrics.md
  • Validate and run tests using the repository tooling

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: scenario-test-designer
Download link: https://github.com/Oxilith/CopilotSkills/archive/main.zip#scenario-test-designer

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.