skills.rest
glowingkitty
glowingkittyCOMMUNITY
Explore all skills by this author →
GitHub

openmates:fix-next-test

Fix the next priority failing Playwright test after triaging failure reports.

43|2|Updated Jan 25, 2024
Search Tags:#test automation#debugging#root cause analysis#playwright#code fixing#regression verification#CI triage
One-click install
npx skills add https://github.com/glowingkitty/OpenMates --skill openmates-fix-next-test
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openmates:fix-next-test
Source: https://github.com/glowingkitty/OpenMates/tree/main/.claude/skills/fix-next-test
Command: npx skills add https://github.com/glowingkitty/OpenMates --skill openmates-fix-next-test

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you quickly diagnose and repair the next failing Playwright test in a priority-ordered workflow, so CI stays green without random guesswork.

Core Features & Use Cases

  • Automated failure triage: Delegates to a test-failure-triager agent to group failures by root-cause tier and provide a ranked recommendation.
  • Root-cause-driven fixing: Selects the highest-priority failing group (or a specified spec) and enforces one root cause per run, minimizing churn.
  • Sessioned verification & deployment: Starts a bug-fix session, runs the targeted spec, and deploys when the fix passes.

Quick Start

Run openmates:fix-next-test without arguments to triage, pick the next highest-priority failing spec, fix the root cause, and verify it in Playwright.

Frequently Asked Questions about openmates:fix-next-test

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

FAQPage Schema
How do I fix failing Playwright tests in CI without random guesswork?▼

Triage failing Playwright tests by grouping the latest CI failure reports by root-cause tier, selecting the highest-priority failing spec group, and verifying the targeted code fix with a controlled run.

Why do multiple Playwright specs fail at once in my CI pipeline?▼

Multiple Playwright specs often fail simultaneously due to shared runtime or infrastructure root causes, requiring failure triage to group specs by root-cause tier rather than fixing them randomly.

What is the best way to automate root cause analysis for browser test regressions?▼

Automate root cause analysis for browser test regressions by delegating failure reports to a triager agent that ranks failures by root-cause tier and enforces one root cause per run to minimize churn.

Can I run a targeted Playwright spec fix without starting a full bug-fix session?▼

You can target a specified Playwright spec for fixing, but the workflow requires session start unless explicitly skipped, and verification runs via run_tests.py with a controlled two-attempt limit.

How do I verify a Playwright code fix passes before deploying to CI?▼

Verify a Playwright code fix by starting a bug-fix session, running the targeted spec through run_tests.py with a two-attempt limit, and deploying the change only when the fix passes regression verification.

Related Skills

Explore More Software Engineering Skills→
mvillmowmvillmow
18

extract-test-failures

Parse test logs to extract and categorize failures by type.

Community
Basic
withzombieswithzombies
80

fixing-bugs

Automate bug fixing from issue creation through regression testing and closure.

Community
Advanced
jr2804jr2804

systematic-debugging

Guide four-phase root-cause investigation before implementing fixes.

Community
Basic
glowingkittyglowingkitty
43

openmates:fix-tests

Triage failing test runs into root-cause groups and apply targeted fixes.

Community
Intermediate