fix-e2e

Categorize failing E2E CI failures by root cause and plan fixes.

4|3|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/steilerDev/cornerstone --skill fix-e2e
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fix-e2e
Source: https://github.com/steilerDev/cornerstone/tree/main/.claude/skills/fix-e2e
Command: npx skills add https://github.com/steilerDev/cornerstone --skill fix-e2e

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Iteratively fix failing E2E tests from a CI run. Analyzes failures, plans fixes, implements them, pushes, and repeats until all E2E tests pass.

Core Features & Use Cases

  • Automates failure analysis and categorization of CI errors.
  • Plans fixes and assigns responsibilities to the appropriate agents.
  • Orchestrates fix-push-verify cycles and CI re-runs until success.

Quick Start

Provide a GitHub Actions run URL or run ID to begin analyzing failures and starting the fix cycle.

Frequently Asked Questions about fix-e2e

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

FAQPage Schema
How do I automate fixing failing E2E tests in CI?

You can automate fixing failing E2E tests by providing a GitHub Actions run URL to orchestrate an iterative repair cycle. The system analyzes CI failures, categorizes root causes, plans concrete fixes, pushes changes, and verifies until all E2E tests pass.

How does automated E2E failure categorization work for CI runs?

Automated E2E failure categorization works by analyzing failing CI runs and grouping errors by root cause. It identifies whether failures stem from test bugs, production bugs, or spec mismatches to determine the correct repair approach.

What's the best way to orchestrate pull request creation for E2E test fixes?

The best way to orchestrate pull request creation for E2E test fixes is to use an automated repair cycle. It plans tasks across agents, implements fixes, verifies changes pass all E2E tests in CI, and prepares a pull request with the fix plan and implementation details.

Can I use automated E2E repair with GitHub Actions run IDs?

Yes, you can use automated E2E repair with GitHub Actions by providing a specific run ID or URL. This initiates the failure analysis and starts the fix-push-verify orchestration cycle to resolve failing tests.

Why do my E2E tests keep failing after automated CI fixes?

If E2E tests keep failing after automated CI fixes, the orchestration loop continues iterating. It categorizes remaining failures by root cause, proposes new concrete fixes, and re-verifies changes in CI until all E2E tests successfully pass.

Do I need to manually assign CI failure fixes to different agents?

No, you do not need to manually assign CI failure fixes to different agents. The orchestration automatically plans fix tasks and assigns responsibilities to the appropriate agents for analysis, implementation, push, and verification.