The request "Gr Test" is ambiguous: it could mean grading tests, running Playwright end-to-end tests, or running Python/pytest unit tests. The closest matches are Grafana Labs' k6 test investigation and grading actions 5, GitHub's Playwright test-generation skill 2, and the Playwright test runner 7. Which kind of test you mean would narrow this down.
A question back: Do you mean grading existing test quality, generating or running end-to-end browser tests, or running Python unit tests with pytest?
- 1
Grafana Cloud k6grafana.comverified and signed
Investigates and grades Grafana Cloud k6 test runs, listing run history, pass/fail status and metric trends 5.
official:MCP server · io.github.grafana/mcp-grafanaCLI · grafanarepository · business-linksskill · dashboardingCLI · logcli+35 community tools built for it
for agents: k6-cloud-investigate-test · testing · k6-trend-analysis
- 2
GitHub Copilot playwright-generate-test skillgithub.comverified and signed
Generates a Playwright test from a scenario using Playwright MCP 2.
official:MCP server · @github/mcp-registrySDK · @github/copilot-sdklibrary · CodeQL: StubCLI · specifyrepository · copilot-engine-sdk+2,577 community tools built for it
for agents: breakdown-test · scoutqa-test · playwright-generate-test
- 3
Playwright Testplaywright.devwebsite read, tools not yet checked
A full-featured test runner with auto-waiting, assertions and tracing across Chromium, Firefox and WebKit 7.
official:SDK · playwright+232 community tools built for it
Sources
- 2GitHub · Change is constant. GitHub keeps you ahead. · GitHub · GitHubgithub.com · read 2026-10-29
- 5Full-stack observability for the agentic era | Grafana Labsgrafana.com · read 2026-10-29
- 7Fast and reliable end-to-end testing for modern web apps | Playwrightplaywright.dev · read 2026-10-29
For agents: the 10 actions behind this answer
grade-tests · grade-tests verified and signed
Grade curated individual tests for readiness, A-F quality and improvements. ALWAYS USE FOR: grade tests, review only a named test, per-test readiness or quality bands for supplied methods, bodies, file spans or bounded PR diffs, including existing tests. Return Pass/Failed/Uncertain/Not applicable;
breakdown-test · breakdown-test verified and signed
Test Planning and Quality Assurance prompt that generates comprehensive test strategies, task breakdowns, and quality validation plans for GitHub projects.
run_test · Firebase MCP Server found in code, not yet checked
Run a remote test.
test · pytest verified and signed
k6-cloud-investigate-test · k6-cloud-investigate-test verified and signed
Investigate a Grafana Cloud k6 test — describe the script, list run history, identify pass/fail status, pull raw metric time-series and log lines for one or more runs, and (if asked) safely edit the test script. Use when the user asks about a specific k6 cloud test or run, gives a `/a/k6-app/tests/<
PostTestHelpersTreasuryOutboundTransfersOutboundTransferReturn · Stripe API verified and signed
Test mode: Return an OutboundTransfer
· Playwright website read, tools not yet checked
Web automation and testing for apps, scripts, and AI agents
gRPC · Grpc.Tools verified and signed
checker · typing verified and signed
Grid · Azure.Messaging.EventGrid verified and signed
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.