e2e-loop

Automate end-to-end testing loops to detect and fix flaky tests.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/exerias21/brainstorm-toolkit --skill e2e-loop-exerias21
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: e2e-loop
Source: https://github.com/exerias21/brainstorm-toolkit/tree/main/copilot/skills/e2e-loop
Command: npx skills add https://github.com/exerias21/brainstorm-toolkit --skill e2e-loop-exerias21

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the end-to-end testing cycle by automatically detecting flaky tests, applying targeted fixes, and re-running until the test suite passes or a configured max_fix_loops is reached.

Core Features & Use Cases

  • Automated end-to-end loop that identifies flaky and failing tests, isolates root causes, and applies minimal fixes.
  • Inline orchestration in Copilot flows without external subagents, with configuration read from .claude/project.json.
  • Re-run control that converges on green results, with optional patterns file guiding selective re-runs.

Quick Start

Run the E2E loop on your project to automatically detect flaky tests, apply fixes, and re-run until the suite passes.

Frequently Asked Questions about e2e-loop

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

FAQPage Schema
How do I automate fixing flaky Playwright tests in CI?

Automating flaky test remediation requires running an end-to-end loop that detects failing browser-driven tests, applies targeted fixes, and re-runs the suite until it passes or reaches a configured iteration limit.

What is an e2e loop for automatic test fixes?

An e2e loop is an automated testing cycle that identifies flaky tests, isolates their root causes, applies minimal code fixes inline, and converges on green results across iterations without external subagents.

How do I configure selective re-runs for flaky end-to-end tests?

Selective re-runs are configured by supplying an optional patterns file alongside the project configuration, allowing the end-to-end loop to target specific test suites during the automated detection and remediation cycle.

Do I need a project configuration file to automate end-to-end testing loops?

Yes, automating the end-to-end testing loop requires a project configuration file located at .claude/project.json to define parameters like max_fix_loops and orchestrate the inline remediation workflow.

How does inline orchestration handle end-to-end test remediation without subagents?

Inline orchestration handles end-to-end test remediation by reading configuration from the project file, detecting flaky tests, and applying fixes directly within the Copilot flow without relying on external subagents.

What happens when the end-to-end loop reaches the max_fix_loops limit?

When the end-to-end loop reaches the configured max_fix_loops limit, the automated testing cycle terminates, stopping further remediation attempts even if the test suite has not yet passed.