e2e-test

Simulate personas to evaluate AI skills and generate scoring reports.

1|Updated Mar 30, 2026

Search Tags:#testing #e2e #evaluation #simulation #persona #skill

Ready to run

npx skills add https://github.com/Driving-Teacher/driving-teacher-ai-native --skill e2e-test-driving-teacher

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: e2e-test
Source: https://github.com/Driving-Teacher/driving-teacher-ai-native/tree/main/.claude/skills/e2e-test
Command: npx skills add https://github.com/Driving-Teacher/driving-teacher-ai-native --skill e2e-test-driving-teacher

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables automated end-to-end evaluation of other skills by simulating personas and orchestrating evaluation sequences, reducing manual QA effort and ensuring consistent testing across scenarios.

Core Features & Use Cases

Persona-based E2E testing: simulate user roles and workflows to exercise a skill in realistic contexts.
Automated evaluation: compare outputs against defined criteria and generate scoring and insights.
Reproducible QA: run repeatable test sessions and store results for regression checks.

Quick Start

Invoke the e2e-test skill with a target skill name to initiate an automated persona-based evaluation workflow.

Frequently Asked Questions about e2e-test

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

FAQPage Schema

How do I automate end-to-end evaluation for AI skills?▼

Automated end-to-end evaluation of AI skills is done by simulating personas and orchestrating test sequences to measure performance. This approach applies persona-based E2E testing to exercise a skill in realistic contexts and generate automated scoring.

What is persona-based testing for AI skill QA?▼

Persona-based testing for AI skill QA is the process of simulating user roles and workflows to evaluate a skill in realistic contexts. It compares outputs against defined criteria to generate scoring and insights, reducing manual QA effort and ensuring consistent testing across scenarios.

How do I run reproducible regression checks on AI skills?▼

Run reproducible regression checks on AI skills by executing repeatable test sessions that simulate personas and orchestrate evaluation sequences. The process stores simulation results and scoring data, enabling consistent regression checks across multiple persona profiles.

What do I need to set up before triggering an AI skill simulation?▼

Before triggering an AI skill simulation, you need access to personas/ directories, criteria/ evaluation rules, and the target skill's SKILL.md file. These elements provide the user roles, scoring benchmarks, and target definitions required to perform simulation and reporting.

Can I use automated persona simulation to test multiple AI skill profiles?▼

Automated persona simulation supports testing multiple AI skill profiles by applying QA across various user roles and workflows. It exercises the target skill in multiple contexts and generates performance scoring and insights for each profile.

Why does my AI skill evaluation require access to personas and criteria rules?▼

AI skill evaluation requires access to personas and criteria rules because the simulation needs defined user roles to exercise the skill and evaluation rules to compare outputs against benchmarks. Without these, the system cannot perform persona-based scoring or generate actionable insights.