auto-test-execution

Automatically execute relevant software tests after AI agents modify source files.

Updated Mar 11, 2026
One-click install
npx skills add https://github.com/robit-man/transcribe-cli --skill auto-test-execution
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: auto-test-execution
Source: https://github.com/robit-man/transcribe-cli/tree/main/.claude/skills/auto-test-execution
Command: npx skills add https://github.com/robit-man/transcribe-cli --skill auto-test-execution

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill ensures that code-generating agents automatically run tests before returning code, preventing the delivery of untested or broken code.

Core Features & Use Cases

  • Automated Test Execution: Triggers tests automatically when source files are modified by an agent.
  • Test Discovery: Locates relevant tests based on file naming conventions.
  • Feedback Loop: Manages test failures by initiating a debug-and-retry cycle.
  • Use Case: When an agent writes new TypeScript code for a feature, this skill will automatically run the corresponding unit tests to verify the changes before the agent's output is finalized.

Quick Start

Use the auto-test-execution skill to automatically run tests whenever source code files are modified.

Frequently Asked Questions about auto-test-execution

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

FAQPage Schema
How do I automatically run tests when an AI agent modifies my source code?

Automated test execution enforces an execute-before-return workflow by detecting modified source files, locating associated test files, and running the project's configured test runner to verify agent-generated code changes.

What is the execute-before-return pattern for code-generating agents?

The execute-before-return pattern prevents AI agents from delivering untested code by automatically triggering software tests before finalizing output, ensuring modified source files pass validation through an automated feedback loop.

How does automated test discovery work for multi-language codebases?

Automated test discovery identifies modified source files across multiple programming languages and locates associated test files by analyzing project naming conventions and integrating with project awareness to detect configured test frameworks.

Can I use this to manage a debug-and-retry cycle for failing unit tests?

Yes, the automated feedback loop manages test failures by initiating a debug-and-retry cycle, utilizing debug memory to learn from persistent failures and ensuring the code-generating agent fixes broken code before returning.

Does automated test execution work with my existing CI/CD pipeline and test runner?

Automated test execution integrates with your project's configured test runner to execute relevant tests, functioning within your existing developer tools and CI/CD feedback loop without requiring specific external dependencies.

What happens when persistent test failures occur during automated test execution?

When persistent test failures occur, the feedback loop utilizes debug memory to learn from the errors, allowing the agent to analyze recurring issues across multiple programming languages and apply targeted code modifications.