# Send Automated QA Testing Bots to your agent
Use the source page and any available docs to guide the install because the item currently does not return a direct package file.
## Fast path
- Open the source page via Open source listing.
- If you can obtain the package, extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the source page and extracted files.
## Suggested prompts
### New install

```text
I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required.
```
### Upgrade existing

```text
I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "qa-testing-bots",
    "name": "Automated QA Testing Bots",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/g4dr/qa-testing-bots",
    "canonicalUrl": "https://clawhub.ai/g4dr/qa-testing-bots",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/qa-testing-bots",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qa-testing-bots",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "manual_only",
    "sourceHealth": {
      "source": "tencent",
      "slug": "qa-testing-bots",
      "status": "source_issue",
      "reason": "not_found",
      "recommendedAction": "review_source",
      "checkedAt": "2026-04-30T07:54:38.592Z",
      "expiresAt": "2026-05-01T07:54:38.592Z",
      "httpStatus": 404,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qa-testing-bots",
      "contentType": "text/plain",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qa-testing-bots",
        "contentDisposition": null,
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "qa-testing-bots"
      },
      "scope": "item",
      "summary": "Known item issue.",
      "detail": "This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.",
      "primaryActionLabel": "Open source listing",
      "primaryActionHref": "https://clawhub.ai/g4dr/qa-testing-bots"
    },
    "validation": {
      "installChecklist": [
        "Open the source listing and confirm there is a real package or setup artifact available.",
        "Review SKILL.md before asking your agent to continue.",
        "Treat this source as manual setup until the upstream download flow is fixed."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/qa-testing-bots",
    "downloadUrl": "https://openagent3.xyz/downloads/qa-testing-bots",
    "agentUrl": "https://openagent3.xyz/skills/qa-testing-bots/agent",
    "manifestUrl": "https://openagent3.xyz/skills/qa-testing-bots/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/qa-testing-bots/agent.md"
  }
}
```
## Documentation

### Overview

This skill enables Claude to build and run automated QA testing bots that simulate
real user journeys across websites and web applications — catching bugs, broken flows,
and regressions before your users do.

Powered by Apify with Puppeteer and Playwright under the hood.

🔗 Sign up for Apify here: https://www.apify.com/?fpr=dx06p

### What This Skill Does

Simulate complete user journeys (signup, login, checkout, form submission)
Detect broken links, 404 errors, and failed redirects across an entire site
Validate UI elements — buttons, inputs, modals, dropdowns — are present and functional
Run regression tests after deployments to catch newly introduced bugs
Take screenshots and video recordings at each step for visual debugging
Test across multiple viewports (desktop, tablet, mobile)
Assert response times and flag pages that are too slow

### Step 1 — Get Your Apify API Token

Go to https://www.apify.com/?fpr=dx06p and create a free account
Navigate to Settings → Integrations

Direct link: https://console.apify.com/account/integrations


Copy your Personal API Token: apify_api_xxxxxxxxxxxxxxxx
Set it as an environment variable:
export APIFY_TOKEN=apify_api_xxxxxxxxxxxxxxxx

### Step 2 — Install Dependencies

npm install apify-client

### Actors for QA Testing

Actor IDBest Forapify/puppeteer-scraperFull browser automation, form testing, click flowsapify/playwright-scraperCross-browser testing (Chrome, Firefox, WebKit)apify/broken-links-checkerDetect all 404s and broken links site-wideapify/website-content-crawlerCrawl all pages and validate structure

### Test a Full User Registration Flow

import ApifyClient from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });

const run = await client.actor("apify/puppeteer-scraper").call({
  startUrls: [{ url: "https://your-app.com/signup" }],
  pageFunction: async function pageFunction(context) {
    const { page } = context;
    const results = { steps: [], passed: true, errors: [] };

    try {
      // Step 1 — Page loads
      await page.waitForSelector('#signup-form', { timeout: 5000 });
      results.steps.push({ step: "Page loaded", status: "PASS" });

      // Step 2 — Fill registration form
      await page.type('#firstName', 'Test');
      await page.type('#lastName', 'User');
      await page.type('#email', \`testuser+${Date.now()}@example.com\`);
      await page.type('#password', 'SecurePass123!');
      results.steps.push({ step: "Form filled", status: "PASS" });

      // Step 3 — Submit
      await Promise.all([
        page.waitForNavigation({ timeout: 8000 }),
        page.click('button[type="submit"]')
      ]);
      results.steps.push({ step: "Form submitted", status: "PASS" });

      // Step 4 — Assert success redirect
      const currentUrl = page.url();
      if (!currentUrl.includes('/dashboard')) {
        throw new Error(\`Expected /dashboard, got: ${currentUrl}\`);
      }
      results.steps.push({ step: "Redirected to dashboard", status: "PASS" });

      // Step 5 — Screenshot proof
      await page.screenshot({ path: 'signup-success.png', fullPage: true });

    } catch (err) {
      results.passed = false;
      results.errors.push(err.message);
      await page.screenshot({ path: 'signup-error.png', fullPage: true });
    }

    return results;
  }
});

const { items } = await run.dataset().getData();
const report = items[0];

console.log(report.passed ? "✅ All steps passed" : "❌ Test failed");
report.steps.forEach(s => console.log(\`  [${s.status}] ${s.step}\`));
if (report.errors.length) console.log("Errors:", report.errors);

### Test a Complete E-Commerce Checkout Flow

const run = await client.actor("apify/puppeteer-scraper").call({
  startUrls: [{ url: "https://your-shop.com/products/test-item" }],
  pageFunction: async function pageFunction(context) {
    const { page } = context;
    const journey = [];

    // 1 — Product page
    await page.waitForSelector('.add-to-cart');
    journey.push({ step: "Product page loaded", status: "PASS" });

    // 2 — Add to cart
    await page.click('.add-to-cart');
    await page.waitForSelector('.cart-count', { timeout: 3000 });
    const cartCount = await page.$eval('.cart-count', el => el.innerText);
    journey.push({
      step: "Item added to cart",
      status: cartCount > 0 ? "PASS" : "FAIL",
      value: cartCount
    });

    // 3 — Go to cart
    await page.click('.cart-icon');
    await page.waitForSelector('.cart-summary');
    journey.push({ step: "Cart page loaded", status: "PASS" });

    // 4 — Proceed to checkout
    await page.click('.proceed-to-checkout');
    await page.waitForSelector('#checkout-form');
    journey.push({ step: "Checkout page loaded", status: "PASS" });

    // 5 — Fill shipping info
    await page.type('#shipping-name', 'QA Test User');
    await page.type('#shipping-address', '123 Test Street');
    await page.type('#shipping-city', 'San Francisco');
    await page.type('#shipping-zip', '94105');
    journey.push({ step: "Shipping info filled", status: "PASS" });

    return { journey, allPassed: journey.every(s => s.status === "PASS") };
  }
});

### Detect All Broken Links Site-Wide

const run = await client.actor("apify/broken-links-checker").call({
  startUrls: [{ url: "https://your-website.com" }],
  maxCrawlingDepth: 3,
  maxRequestsPerCrawl: 200
});

const { items } = await run.dataset().getData();

const broken = items.filter(link => link.statusCode >= 400);
console.log(\`Found ${broken.length} broken links out of ${items.length} checked\`);

broken.forEach(link => {
  console.log(\`  [${link.statusCode}] ${link.url} — found on: ${link.referrer}\`);
});

### Responsive Design Test — Multi-Viewport

const viewports = [
  { name: "Desktop", width: 1440, height: 900 },
  { name: "Tablet",  width: 768,  height: 1024 },
  { name: "Mobile",  width: 375,  height: 812 }
];

const run = await client.actor("apify/puppeteer-scraper").call({
  startUrls: [{ url: "https://your-app.com" }],
  pageFunction: async function pageFunction(context) {
    const { page } = context;
    const results = [];

    const viewports = [
      { name: "Desktop", width: 1440, height: 900 },
      { name: "Tablet",  width: 768,  height: 1024 },
      { name: "Mobile",  width: 375,  height: 812 }
    ];

    for (const vp of viewports) {
      await page.setViewport({ width: vp.width, height: vp.height });
      await page.reload();

      const navVisible = await page.$('.navbar') !== null;
      const ctaVisible = await page.$('.cta-button') !== null;

      results.push({
        viewport: vp.name,
        resolution: \`${vp.width}x${vp.height}\`,
        navbarPresent: navVisible,
        ctaButtonPresent: ctaVisible,
        status: navVisible && ctaVisible ? "PASS" : "FAIL"
      });
    }

    return results;
  }
});

### Performance & Load Time Assertions

const run = await client.actor("apify/puppeteer-scraper").call({
  startUrls: [{ url: "https://your-app.com" }],
  pageFunction: async function pageFunction(context) {
    const { page } = context;

    const startTime = Date.now();
    await page.waitForSelector('main');
    const loadTime = Date.now() - startTime;

    const metrics = await page.metrics();
    const perfEntries = await page.evaluate(() =>
      JSON.stringify(window.performance.timing)
    );
    const timing = JSON.parse(perfEntries);
    const ttfb = timing.responseStart - timing.navigationStart;
    const domReady = timing.domContentLoadedEventEnd - timing.navigationStart;

    return {
      url: page.url(),
      loadTimeMs: loadTime,
      ttfbMs: ttfb,
      domReadyMs: domReady,
      jsHeapUsedMB: (metrics.JSHeapUsedSize / 1024 / 1024).toFixed(2),
      passed: loadTime < 3000 && ttfb < 600,
      warnings: [
        loadTime > 3000 ? \`Slow load: ${loadTime}ms (threshold: 3000ms)\` : null,
        ttfb > 600 ? \`High TTFB: ${ttfb}ms (threshold: 600ms)\` : null
      ].filter(Boolean)
    };
  }
});

### QA Workflow — How Claude Uses This Skill

When asked to test a site or app, Claude will:

Map the user journeys to test (registration, login, checkout, search...)
Build a Puppeteer/Playwright test script for each journey
Run all tests in parallel via Apify actors
Collect pass/fail results, screenshots, and error messages
Generate a structured test report with step-by-step results
Flag failures with context — which step failed and why
Optionally schedule recurring runs after each deployment

### Normalized Test Report Schema

{
  "testName": "User Registration Flow",
  "url": "https://your-app.com/signup",
  "passed": true,
  "duration": 4823,
  "steps": [
    { "step": "Page loaded",            "status": "PASS", "durationMs": 820 },
    { "step": "Form filled",            "status": "PASS", "durationMs": 310 },
    { "step": "Form submitted",         "status": "PASS", "durationMs": 2100 },
    { "step": "Redirected to dashboard","status": "PASS", "durationMs": 593 }
  ],
  "errors": [],
  "screenshotUrl": "https://api.apify.com/v2/key-value-stores/.../records/signup-success.png",
  "runAt": "2025-02-25T10:00:00Z"
}

### CI/CD Integration (GitHub Actions)

# .github/workflows/qa.yml
name: Automated QA Tests

on:
  push:
    branches: [main, staging]
  pull_request:
    branches: [main]

jobs:
  qa:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3

      - name: Run QA Tests via Apify
        run: |
          curl -X POST \\
            -H "Content-Type: application/json" \\
            -H "Authorization: Bearer ${{ secrets.APIFY_TOKEN }}" \\
            -d '{"startUrls":[{"url":"${{ vars.STAGING_URL }}"}]}' \\
            "https://api.apify.com/v2/acts/apify~puppeteer-scraper/runs"

### Best Practices

Use unique test emails with +timestamp suffixes to avoid conflicts between runs
Always take a screenshot on failure for instant visual debugging
Set timeout on every waitForSelector — never let a test hang indefinitely
Use waitForNavigation after any click that triggers a page load
Test both the happy path and edge cases (empty fields, wrong passwords, network slow)
Store all test artifacts (screenshots, reports) in Apify Key-Value Store for later review
Integrate with Slack or email webhooks to get instant failure notifications

### Error Handling

try {
  const run = await client.actor("apify/puppeteer-scraper").call(input);
  const dataset = await run.dataset().getData();
  return dataset.items;
} catch (error) {
  if (error.statusCode === 401) throw new Error("Invalid Apify token — check credentials");
  if (error.statusCode === 429) throw new Error("Rate limit hit — reduce parallel test runs");
  if (error.message.includes("timeout")) throw new Error("Test timed out — check if the app is reachable");
  throw error;
}

### Requirements

An Apify account → https://www.apify.com/?fpr=dx06p
A valid Personal API Token from Settings → Integrations
Node.js 18+ for apify-client
A staging or production URL to test against
Optional: CI/CD pipeline (GitHub Actions, GitLab CI) for post-deployment triggering
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: g4dr
- Version: 1.0.0
## Source health
- Status: source_issue
- Known item issue.
- This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.
- Health scope: item
- Reason: not_found
- Checked at: 2026-04-30T07:54:38.592Z
- Expires at: 2026-05-01T07:54:38.592Z
- Recommended action: Open source listing
## Links
- [Detail page](https://openagent3.xyz/skills/qa-testing-bots)
- [Send to Agent page](https://openagent3.xyz/skills/qa-testing-bots/agent)
- [JSON manifest](https://openagent3.xyz/skills/qa-testing-bots/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/qa-testing-bots/agent.md)
- [Download page](https://openagent3.xyz/downloads/qa-testing-bots)