Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    quickcast qa assistant

    1

    Convert screen recordings into Playwright E2E tests, timestamped bug reports, and step-by-step SOP documentation.

    Free

    1 useSecurity scanned
    quickcast qa assistant

    quickcast qa assistant

    Example session with this skill installed

    I just recorded a bug where the checkout button fails. Can you generate a Playwright test to reproduce it and a GitHub bug report from the latest session?

    • Read your context and instructions
    • Compiled the quickcast qa assistant

    I have retrieved the session data from your latest recording (Session ID: qc_88291_x) and generated both the reproduction test and the formatted bug report.

    Playwright Reproduction Test

    import { test, expect } from '@playwright/test';
    
    test('reproduce checkout button failure', async ({ page }) => {
      // Environment: Chrome / macOS
      await page.goto('https://shop.example.com/cart');
    
      // Step 1: User navigates to cart
      await expect(page).toHaveURL(/.*cart/);
    
      // Step 2: Attempt to click checkout
      const checkoutBtn = page.getByRole('button', { name: /proceed to checkout/i });
      await expect(checkoutBtn).toBeVisible();
      
      // Capturing potential runtime crashes
      page.on('pageerror', exception => {
        console.log(`Uncaught exception: "${exception.message}"`);
      });
    
      await checkoutBtn.click();
    
      // Assertion: Check for success state or error message
      // Based on recording, the URL did not change to /checkout
      await expect(page).toHaveURL('https://shop.example.com/checkout');
    });
    

    GitHub Bug Report

    Title: Bug: Checkout button unresponsive on /cart
    Environment: Chrome 124.0.5, macOS 14.4
    Video Evidence: Watch Recording

    Reproduction Steps

    1. Navigate to https://shop.example.com/cart 00:02
    2. Add item to cart and proceed to summary 00:08
    3. Click 'Proceed to Checkout' button 00:15

    Observed Behavior

    The button displays a click animation but does not initiate a redirect or show a loading state at 00:16. Console shows a 403 error for /api/v1/checkout/validate.

    Expected Behavior

    The user should be redirected to the secure checkout page.

    Next steps

    1. Save the reproduction code to tests/repro_issue_checkout.spec.ts.
    2. Run npx playwright test to verify the failure locally.
    3. Submit the Markdown report to the repository issue tracker.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Manual test writing is a bottleneck. Converting screen recordings into actionable code usually requires hours of manual mapping, locator identification, and report writing. This skill bridges the gap between a visual demo and a production-ready codebase.

    What it does

    • Playwright generation creates executable TypeScript or JavaScript E2E tests by mapping user actions from recordings to resilient locators.
    • Deep-linked bug reporting formats GitHub and Jira issues with timestamped video links that jump to the exact moment of failure.
    • SOP documentation generates step-by-step operational guides with timecode references for onboarding and team handovers.
    • Session inspection retrieves telemetry, network diagnostics, and environment data from the latest recording sessions.

    How it works

    1. Fetch session data using get_latest_session to pull video URLs, duration, and telemetry from the QuickCast MCP server.
    2. Generate assets by calling specific tools like scaffold_playwright_test or format_github_bug_report.
    3. Refine and harden the output by adding auto-waiting assertions, resilient role-based locators, or environment matrices.

    Frameworks & tools

    This skill requires the quickcast-mcp server. It produces code and documentation for Playwright, GitHub, Jira, and standard Markdown environments.

    Why this beats prompting it yourself

    Writing reliable Playwright tests from memory is error-prone. This skill uses direct session telemetry to ensure locators match the actual DOM state and injects precise video timestamps that general-purpose prompts cannot access without specialized MCP tool integration.

    Use cases

    • Convert a quick UI bug reproduction video into a functional Playwright regression test.
    • Generate high-fidelity GitHub issues that link directly to specific seconds in a demo video.
    • Create technical SOPs for complex internal workflows based on a recorded screen walkthrough.

    Known limitations

    Requires the quickcast-mcp server to be configured in your environment. Test generation is optimized for Playwright and may require manual tweaks for non-standard web components.

    Requires quickcast-mcp server setup. Optimized specifically for Playwright (TS/JS). Telemetry must be stored in ~/.quickcast/sessions.json to be accessible.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    • Free with an Agensi account

    Requires

    Quickcast MCP
    playwright
    Node.js

    Permissions

    Terminal / Shell
    Browser
    Listed1 month ago
    Updated24 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the transition from visual screen recordings to technical QA assets, including Playwright E2E test scripts, deep-linked Jira/GitHub bug reports, and timestamped SOP documentation.

    The skill requires the `quickcast-mcp` server to be installed and configured in your environment to fetch session telemetry and video data. Once the server is active, you can invoke the skill within any MCP-compatible AI agent.

    Unlike general prompts, this skill uses direct session telemetry to identify precise DOM locators and inject exact video timestamps into reports, ensuring the generated code is resilient and the bug reports are actionable.

    While optimized for Playwright (TypeScript/JavaScript), the skill generates standard Markdown for SOPs and bug reports, making it compatible with GitHub, Jira, and most documentation platforms.

    You receive the full skill logic for generating Playwright tests, bug reports, and SOPs, along with documentation on connecting it to your QuickCast MCP server. Updates are provided through the marketplace as new locator strategies or framework versions are released.

    New in Testing & Debugging