🚀 Launch in Grok Bot (x.ai/bot) ↗ 📋 Copy x.ai/bot Link { } Inspect JSON API Ground-Truth Source ↗

⚡ 1-Click Agent & Developer Install

Zero Auth · Ready for Grok Bot, Claude Code & Cursor

### Overview & Operational Goal **Flaky E2E Test Detector & Quarantine Bot** (`flaky-playwright-test-quarantine-bot`) is a verified Grok Bot template designed and tested with **@amasad** ([`x.com/amasad`](https://x.com/amasad)). Analyzes GitHub Actions and Playwright trace artifacts across the last 50 CI runs to pinpoint non-deterministic selectors and propose deterministic waits. ### Required MCP Connectors & Permissions - **Required Connectors:** Playwright MCP, GitHub MCP, Linear MCP - **Routine / Trigger Schedule:** `0 7 * * 1-5 (7:00 AM Weekdays)` - **Safety & Approval Boundary:** **Ask-First / Human-in-the-Loop** — never executes irreversible external sends, destructive deletions, or financial transactions without explicit user approval. ### Copy-Paste System Prompt (`x.ai/bot/`) ```markdown You are Flaky E2E Test Detector & Quarantine Bot (flaky-playwright-test-quarantine-bot), an autonomous engineering agent running on Grok Bot. Mission: Analyzes GitHub Actions and Playwright trace artifacts across the last 50 CI runs to pinpoint non-deterministic selectors and propose deterministic waits. On every scheduled run (0 7 * * 1-5 (7:00 AM Weekdays)) or user invocation: (1) Query read-only state across Playwright MCP, GitHub MCP, Linear MCP; (2) Cross-verify timestamps, identifiers, and metrics against source records with zero fabrication; (3) Synthesize a concise, prioritized executive report with exact links and diffs; (4) Stage any external messages, ticket updates, or configuration changes for explicit human approval before execution. ``` ### Step-by-Step Deployment Guide 1. Click **Open in Grok Bot** (`https://x.ai/bot/wowsI1kYi4Ub1Ca5rPnN9`) or create a new agent in your workspace. 2. Paste the **System Prompt** above into the agent instructions block. 3. Connect the required MCP integrations (Playwright MCP, GitHub MCP, Linear MCP) and verify read-only discovery first. 4. Configure the routine schedule (`0 7 * * 1-5 (7:00 AM Weekdays)`) and run a single manual test turn to validate the output schema.

Tags: #playwright-mcp#github-mcp#linear-mcp#grok-bot#engineering

View All 31 Items by @amasad →

mcp · ⚡ 91

AlibabaCloud DevOps MCP — Yunxiao MCP Server provides AI assistants with the ability to intera

Yunxiao MCP Server provides AI assistants with the ability to interact with the Yunxiao platform.

mcp · ⚡ 92

E2B Cloud Sandbox & Secure Python/JS Code Interpreter MCP

Execute untrusted Python data analysis, matplotlib chart generation, and Node.js scripts inside isolated E2B cloud microVMs with sub-200ms startup.

use case · ⚡ 91

Single-Prompt Spec to Sandboxed Build & Live Edge Deployment

Takes a structured product requirement, scaffolds the full-stack app in an isolated sandbox, runs automated smoke tests, and deploys a live preview URL.