Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
GitHub Copilot
Gemini CLI+20 moreClaude CodeCursorCodex CLIGitHub CopilotGemini CLI
OpenClaw
Manus
Grok+17 agentsPlaywright Test Failure Debugger
Diagnose flaky, timed-out, or CI-only Playwright test failures using traces and logs.
$9.99
Playwright Test Failure Debugger
Example session with this skill installed
My test times out on CI but passes locally. Here is the Playwright trace and the test file. Why is the 'Submit' button not becoming actionable in WebKit?
- Read your context and instructions
- Compiled the playwright test failure
Verdict: Material browser-test failure.
Root Cause: A race condition in hydration causes the 'Submit' button to rerender after Playwright's actionability check but before the click event.
Remediation: Use a web-first assertion to ensure the button is attached and stable.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Playwright test failures are often misleading. A timeout at the end of a script is usually just a symptom of a race condition, network failure, or state pollution that happened minutes earlier.
What it does
- Analyzes Playwright traces, HAR files, and CI logs to reconstruct the exact failure timeline.
- Identifies the root cause of flaky tests that pass locally but fail in CI.
- Diagnoses locator fragility, strict-mode violations, and actionability blockers.
- Evaluates authentication, storage-state issues, and fixture isolation problems.
- Provides a prioritized remediation plan and a 100-point diagnostic quality score.
Frameworks & tools
Playwright, Chromium, Firefox, WebKit, CI environments (GitHub Actions, GitLab CI, Jenkins), and HAR/JSON network logs.
Why this beats prompting it yourself
Generic LLMs often suggest "increasing the timeout" or "adding a sleep." This skill follows a 27-step specialized audit workflow to find the earliest point of divergence, preventing you from masking bugs with blind retries.
Use cases
- Debugging "passed on retry" flakiness in CI pipelines.
- Fixing complex navigation races and hydration-related timeouts.
- Resolving cross-browser inconsistencies between Chromium and WebKit.
- Audit of storage-state and authentication setup for multi-tenant testing.
Known limitations
This tool does not execute tests, open live websites, or modify your source code directly. It requires exported artifacts like traces or logs to perform a high-confidence analysis.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 1 month ago
- Passed all security checks, Safe to install