test-runner

Execute multi-framework tests and route failures to subagents with retries.

Updated Feb 9, 2026
One-click install
npx skills add https://github.com/msanssouci/opencode --skill test-runner-msanssouci
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test-runner
Source: https://github.com/msanssouci/opencode/tree/main/skills/test-runner
Command: npx skills add https://github.com/msanssouci/opencode --skill test-runner-msanssouci

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires beads-workflow.

What problem does it solve?

This Skill automates test execution across multi-framework projects (backend, frontend, and end-to-end) and manages failures by creating actionable beads tasks and routing issues to the right subagents.

Core Features & Use Cases

  • Detects test framework and selects the correct command (backend: Gradle/JUnit/Kotest, frontend: Jest, E2E: Playwright)
  • Executes tests, captures output, and determines pass/fail status
  • Parses failures to generate beads fix tasks and assigns them to appropriate subagents
  • Supports a retry loop with a maximum of 3 attempts and escalates when needed
  • Keeps task context and links original task details for traceability

Quick Start

Load the skill and run tests for a project task to automatically execute, parse results, and create fix tasks for any failures.

Frequently Asked Questions about test-runner

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

FAQPage Schema
How do I automate test execution across multiple frameworks like Jest and Playwright?

Automating multi-framework test execution is handled by detecting the test framework and selecting the correct command for backend, frontend, and end-to-end suites. The process captures output, determines pass/fail status, and routes failures to subagents.

How do I manage test failures and automatically create fix tasks for broken Jest or Playwright tests?

Managing test failures involves parsing failed test outputs to generate actionable fix tasks and assigning them to appropriate subagents. It keeps task context and links original details for traceability throughout the test execution workflow.

Does this test execution workflow support Kotlin backend tests and frontend unit tests simultaneously?

Yes, this test execution workflow supports Kotlin backend tests using Gradle, JUnit, or Kotest, alongside frontend Jest unit tests and Playwright end-to-end tests. It automatically detects the framework to select the correct test command.

What happens when automated tests keep failing after multiple retries in CI/CD pipelines?

When automated tests keep failing in CI/CD pipelines, a retry loop runs up to a maximum of 3 attempts. If failures persist after these retries, the system escalates the issue to ensure it receives proper attention.

Do I need beads-workflow to route test failures to subagents?

Yes, you need beads-workflow to route test failures to subagents. The test execution and failure management process uses this dependency to create beads fix tasks and maintain traceability with original task details.