skills.rest
jmagly
jmaglyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

auto-test-execution

Automate test execution for modified TypeScript, JavaScript, Python, Go, and Rust files.

175|26|Updated Aug 14, 2025
Search Tags:#automation#testing#developer tools#ci/cd#debugging#code generation
One-click install
npx skills add https://github.com/jmagly/aiwg --skill auto-test-execution-jmagly
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-test-execution
Source: https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/ralph/skills/auto-test-execution
Command: npx skills add https://github.com/jmagly/aiwg --skill auto-test-execution-jmagly

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill ensures that code-generating AI agents execute tests on their output before returning it, preventing the delivery of broken code and enforcing a critical development best practice.

Core Features & Use Cases

  • Automated Test Execution: Triggers tests automatically when source code files are modified.
  • Failure Handling: Manages test failures by initiating a debug-and-retry loop.
  • Use Case: When a 'software-implementer' agent generates new TypeScript code, this skill will automatically run the relevant unit tests. If they pass, the code is returned; if they fail, the agent attempts to fix the issue up to three times before escalating.

Quick Start

Use the auto-test-execution skill to verify changes made to the src/utils/helpers.ts file.

Frequently Asked Questions about auto-test-execution

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

FAQPage Schema
How do I automate test execution for code generated by AI agents?▼

Automated test execution triggers when an AI agent modifies source code, enforcing an execute-before-return pattern. It runs the relevant test suite on TypeScript, JavaScript, Python, Go, or Rust files before returning the final code.

What happens when automated tests fail during AI code generation?▼

When tests fail, a debug-and-retry loop handles the failure by attempting to fix the code. The agent retries the test execution up to three times before escalating the persistent failure.

Does this automated test execution work with Python and Go projects?▼

Yes, automated test execution supports projects with defined test suites for TypeScript, JavaScript, Python, Go, and Rust files.

How does the debug-and-retry loop handle persistent test failures?▼

The debug-and-retry loop handles persistent test failures by using debug memory for analysis. It attempts to fix issues up to three times before escalating the failure.

What do I need to detect test frameworks for automated test execution?▼

Detecting test frameworks requires integration with project-awareness. This detects the project's test frameworks to run the appropriate tests on modified files.

When should I use an execute-before-return pattern for AI agents?▼

Use the execute-before-return pattern when generating code with AI agents to prevent delivering broken code. It enforces the development best practice of verifying code modifications with tests before returning them.

Related Skills

Explore More Software Engineering Skills→
Marshall-HallenbeckMarshall-Hallenbeck
5

run-unit-tests

Detects the test runner from project configuration files and executes unit test suites.

Community
Intermediate
robit-manrobit-man

auto-test-execution

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

Community
Advanced
gkganesh12gkganesh12
1

gk-review

Audit source code against documentation and test suites for architectural drift.

Community
Advanced
Marshall-HallenbeckMarshall-Hallenbeck
5

fix-tests

Diagnose and repair failing test suites across multiple language ecosystems.

Community
Advanced