How do I install the AI Testing skill?

Run npx skillmds@latest add tomevault-io/ai-testing in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is AI Testing safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with AI Testing?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is AI Testing free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published AI Testing?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

AI Testing by tomevault-io — Agent Skill

Name: AI Testing
Author: tomevault-io

AI Testing

Use when working with an AI tool for automated testing, focusing on output quality, reliability, user trust, regulatory compliance, and security. Use this skill to prevent injection attacks, ensure system integrity, and protect data by integrating LLM-based systems into the Deepeval Framework, running test cases, and generating structured fact-check reports.

tomevault-io 469047c 2 files · 2.8 KB Updated Sep 17, 2026

File contents

AI Testing Skill

This skill provides a structured workflow for performing AI testing, ensuring robust, reliable, and secure AI systems. It leverages the Deepeval Framework to integrate and test LLM-based systems against various quality and security metrics.

Workflow for AI Testing

Follow these steps to conduct comprehensive AI testing:

Integrate LLM System with Deepeval Framework:
- Objective: Set up the target LLM-based system for testing within the Deepeval framework.
- Action: Use the template/red_team.py file as a starting point or template to integrate the system and define evaluation metrics and test cases.
- Verification: Ensure the system is correctly initialized and accessible for testing.
Execute Test Cases:
- Objective: Run the defined test cases against the integrated LLM system.
- Action: Initiate the testing process through the Deepeval framework to evaluate the LLM's performance against criteria such as output quality, reliability, security (e.g., injection attack prevention), and compliance.
- Verification: Confirm that all test cases have been executed and raw test results are available.
Generate Structured Fact-Check Report:
- Objective: Create a clear, structured report summarizing the test findings.
- Action: Process the test results to generate a markdown-formatted report that includes detailed outcomes, identified vulnerabilities, compliance adherence, and overall system performance.
- Verification: Ensure the report is comprehensive, accurate, and saved as a .md file in an accessible location.

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: ai-testingdescription: Use when working with an AI tool for automated testing, focusing on output quality, reliability, user trust, regulatory compliance, and security. Use this skill to prevent injection attacks, ensure system integrity, and protect data by integrating LLM-based systems into the Deepeval Framework, running test cases, and generating structured fact-check reports.---# AI Testing SkillThis skill provides a structured workflow for performing AI testing, ensuring robust, reliable, and secure AI systems. It leverages the Deepeval Framework to integrate and test LLM-based systems against various quality and security metrics.## Workflow for AI TestingFollow these steps to conduct comprehensive AI testing:1. **Integrate LLM System with Deepeval Framework:** * **Objective:** Set up the target LLM-based system for testing within the Deepeval framework. * **Action:** Use the `template/red_team.py` file as a starting point or template to integrate the system and define evaluation metrics and test cases. * **Verification:** Ensure the system is correctly initialized and accessible for testing.2. **Execute Test Cases:** * **Objective:** Run the defined test cases against the integrated LLM system. * **Action:** Initiate the testing process through the Deepeval framework to evaluate the LLM's performance against criteria such as output quality, reliability, security (e.g., injection attack prevention), and compliance. * **Verification:** Confirm that all test cases have been executed and raw test results are available.3. **Generate Structured Fact-Check Report:** * **Objective:** Create a clear, structured report summarizing the test findings. * **Action:** Process the test results to generate a markdown-formatted report that includes detailed outcomes, identified vulnerabilities, compliance adherence, and overall system performance. * **Verification:** Ensure the report is comprehensive, accurate, and saved as a `.md` file in an accessible location.---> Converted and distributed by [TomeVault](https://tomevault.io/claim/dtmc-marketplace) — claim your Tome and manage your conversions.

Frequently asked questions