Browser automation
Skill aizech/bernhard-zechmann-skills/skills/engineering/browser-automation
Modular AI agent skills used across engineering, writing, and research workflows. Model‑agnostic, composable, and production‑tested. Includes engineering, productivity, personal, and experimental skill packs.
npx -y skills add aizech/bernhard-zechmann-skills --skill browser-automationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Automate browser interactions for scraping, testing, and workflows. Use when the user wants to navigate pages, fill forms, extract data, or take screenshots with Puppeteer or Playwright.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.5 KB, as published. Nobody here has run it
Browser Automation
Automate browser tasks for scraping, testing, and workflows.
Core capabilities
- Navigation: load URLs, wait for selectors, scroll, handle navigation.
- Interaction: click, type, select, upload files.
- Extraction: read text, attributes, tables, or lists.
- Capture: screenshots, PDFs, and traces.
Workflow
- Open the page.
- Wait for the right selector.
- Interact with elements.
- Extract or capture the result.
- Handle pagination or repeated steps with clear bounds.
Best practices
- Use stable selectors like
data-testidinstead of CSS paths. - Wait for elements before interacting.
- Add human-like delays when mimicking real users.
- Respect rate limits and robots.txt.
- Capture screenshots on failure.
- Use headless mode for production.
Example
await page.goto('https://example.com/login');
await page.fill('#email', '[email protected]');
await page.fill('#password', 'securepass');
await page.click('button[type="submit"]');
await page.waitForNavigation();
Guardrails
- Do not scrape behind authentication unless explicitly asked.
- Do not run aggressive crawlers without rate limiting.
- Keep personal data out of logs and screenshots.