$ loading_
Run QA checks with screenshots, Sentry errors, and fix verification.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "ai.gatetest.www/gatetest" yet — see the docs or source repo.
Using this page screenshot and this Sentry error, check whether the issue still exists and provide a verification result with next-step recommendations.
A result stating whether the issue reproduces, whether the fix works, and what follow-up checks are needed.
Analyze these screenshots together with recent Sentry exceptions as a pre-release QA gate and identify high-risk issues.
A QA gate conclusion and risk summary for release decisions.
For this supposedly fixed issue, use the available screenshots and error clues to run a regression check and say whether the ticket can be closed.
A regression result, closure recommendation, and any additional evidence still needed.
Development or QA teams can combine UI screenshots with Sentry exceptions before release to catch issues early. It is useful when fix verification and risk assessment need to happen in one flow.
When a bug is reported as fixed, teams can recheck it using screenshots and error details to confirm the issue is truly resolved. This reduces false closes and improves confidence.
If Sentry reports production errors, teams can use those exceptions as QA signals and combine them with UI evidence for regression checks. This is helpful when the impact needs to be confirmed quickly.
It is an MCP tool for QA gating. It gives Claude “eyes, ears, and hands” by using screenshots for visual checks, Sentry errors for issue signals, and workflows to verify fixes.
Based on the description, it uses screenshots and Sentry error information to support QA checks and fix verification. For exact input formats, see the source repository.
No documentation excerpt is provided, so the installation steps, runtime, and prerequisites cannot be confirmed here. Please see the source repository.
Validate specs, ADRs, task plans, and code quality before delivery.
Force factual investigation before edits or commands to improve output quality.
Add quality gates for coding agents to catch common AI mistakes.
Automate end-to-end QA planning, Playwright test generation, and review with AI agents.
Run, inspect, debug, and extend OpenClaw QA scenarios and artifacts.
Score AI-generated API tests and enforce progressive quality gates.