run-tests

Run pytest suites and investigate failures with AI consultation.

4|Updated Dec 3, 2025

Search Tags:#testing #quality assurance #test automation #debugging #troubleshooting #pytest #ai-powered

Ready to run

npx skills add https://github.com/tylerburleigh/claude-foundry --skill run-tests

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: run-tests
Source: https://github.com/tylerburleigh/claude-foundry/tree/main/skills/run-tests
Command: npx skills add https://github.com/tylerburleigh/claude-foundry --skill run-tests

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Debugging failing tests is often a time-consuming, iterative process that requires deep code investigation and can be frustrating, especially in complex codebases.

Core Features & Use Cases

Systematic Test Execution: Runs pytest suites (quick, unit, integration, full) with detailed output and presets.
AI-Powered Debugging: Consults external AI tools for complex failures, offering hypotheses and recommended fixes.
5-Phase Investigation Workflow: Guides you from running tests to investigating failures, gathering context, consulting AI, and finally fixing and verifying.

Quick Start

Run the quick test suite and investigate any failures.

Frequently Asked Questions about run-tests

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

FAQPage Schema

How do I debug failing pytest tests systematically?▼

Run pytest tests through this Skill to automatically categorize failures, gather code context, and receive AI-powered hypotheses for what caused the failure and how to fix it.

Can I run different test suites like unit, integration, and full tests?▼

Yes, the Skill supports multiple pytest presets including quick, unit, integration, and full test suites with detailed output for each execution mode.

What happens after a test fails—how do I investigate?▼

The Skill guides a five-phase workflow: run tests, investigate failures, gather code context, consult external AI providers for insights, then fix and verify with targeted and regression tests.

Do I need external AI tools to use this for debugging?▼

External AI consultation is optional—the Skill performs systematic failure investigation and context gathering independently, and escalates to AI providers only when available for complex failures.

How does this differ from running pytest manually?▼

Beyond test execution, this Skill automates failure categorization, documents investigation context, formats findings for AI analysis, and validates fixes through targeted regression testing.

Can I use this in CI environments or only locally?▼

Test execution applies to both local development and CI environments, enabling consistent debugging workflows across different deployment stages.