skills.rest
clfigueiredo
clfigueiredoCOMMUNITY
Explore all skills by this author →
GitHub

browser-qa

Automates visual testing and UI interaction verification on deployed web pages using browser automation.

5|15|Updated Jul 8, 2026
Search Tags:#accessibility#qa#browser automation#wcag#regression testing#playwright#visual testing
One-click install
npx skills add https://github.com/clfigueiredo/hermes-infra-skills --skill browser-qa-clfigueiredo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-qa
Source: https://github.com/clfigueiredo/hermes-infra-skills/tree/main/.hermes/skills/curso-hermes/browser-qa
Command: npx skills add https://github.com/clfigueiredo/hermes-infra-skills --skill browser-qa-clfigueiredo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually verifying that a deployed feature actually works across pages, viewports, and user journeys is slow and error-prone. This Skill drives a real browser through smoke tests, interaction checks, visual regression, and accessibility audits so broken layouts, dead links, and console errors are caught before shipping. ## Core Features & Use Cases - Four-phase QA workflow: smoke test (console errors, network failures, Core Web Vitals), interaction test (nav links, forms, auth flows), visual regression (screenshots at 375px/768px/1440px against baselines), and accessibility audit (axe-core, WCAG 2.2 AA, keyboard navigation). - Safety-first defaults: read-only by default, mutating journeys (checkout, payment, delete) require explicit opt-in and a staging URL, with test credentials only and PII redaction in screenshots. - Structured verdict report: outputs a Markdown QA report ending in SHIP, SHIP WITH FIXES, DO NOT SHIP, or INCONCLUSIVE when no visual baseline exists. - Use Case: After deploying a PR to a preview URL, ask the agent to run browser QA and receive a report flagging a hero section overflow on mobile and two WCAG contrast violations before merge. ## Quick Start Run browser QA on the staging deployment at https://staging.example.com and give me the full report with screenshots at mobile and desktop widths.

Frequently Asked Questions about browser-qa

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run automated visual testing on a deployed website?▼

Point the browser automation at the target URL and run the four phases: smoke test for console and network errors, interaction test for links and forms, visual regression with screenshots at 375px, 768px, and 1440px, and an accessibility audit. The result is a Markdown report with a SHIP or DO NOT SHIP verdict.

What browser automation tools work with this QA workflow?▼

The workflow works with any browser MCP: claude-in-chrome tools are preferred since they use your actual Chrome, but Playwright via browserbase MCP or direct Puppeteer scripts also work. The phases and report format stay the same regardless of driver.

Can I run interaction tests against a production site?▼

Read-only checks like navigation and screenshots are fine on production, but mutating journeys such as checkout, payment, or delete require explicit opt-in and a staging or preview URL. Always use seeded test credentials, never real production logins.

Does axe-core accessibility testing cover all WCAG issues?▼

No. axe-core automatically covers roughly 30-40% of WCAG criteria, so a clean run is necessary but not sufficient. Keyboard navigation, focus order, and a screen reader pass still require manual verification before claiming a page is accessible.

What happens if there is no baseline for visual regression?▼

Without committed baseline screenshots, visual comparison cannot produce a reliable pass. The report is marked INCONCLUSIVE rather than silently passing, so you know a baseline must be captured first.

Related Skills

Explore More Software Engineering Skills→
pulsemcppulsemcp

test-in-staging

Deploy the current branch to staging and run end-to-end verification checks.

Official
Advanced
TumeloRamaphosaTumeloRamaphosa

canary

Monitors live applications after deployment for console errors, performance regressions, and page failures.

Community
Intermediate
VibeStackCodesVibeStackCodes

playwright-testing

Automate cross-browser end-to-end testing with Playwright.

Official
Intermediate
Prompt-or-Die-LabsPrompt-or-Die-Labs
7

testing-framework-helper

Generates unit, integration, and E2E tests for JavaScript, TypeScript, and Python.

Official
Advanced