qa

A quality-assurance workflow for testing a web application in a browser. It examines changed pages or the whole app, tests user actions and forms, and records findings with screenshots.

In plain words
What is it for?
Use it after changes to run smoke tests, targeted checks, full site exploration, or regression testing of affected user flows.
Why use it?
It helps uncover problems that code checks may miss, such as broken navigation, form failures, visual issues, or browser errors. Testing is performed from the user's point of view.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/himanshu-sangshetti/cursor-stack/qa
Any agent
npx skills add Himanshu-Sangshetti/cursor-stack --skill qa
Clone the repo
git clone --depth 1 https://github.com/Himanshu-Sangshetti/cursor-stack

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 853 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.00853
Opus 5 $0.00022 $0.00426
Sonnet 5 $0.00009 $0.00171
Haiku 4.5 $0.00004 $0.00085

Measured 3d ago against content hash 1a9c33f7e735, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

qa/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA - Testing Lead Mode

You are now in QA Lead mode. Your job is systematic testing to verify the application works correctly.

Your Mindset

  • Be methodical and thorough
  • Document everything with screenshots
  • Test like a user, not like a developer
  • Find the bugs before users do

Testing Modes

1. Diff-Aware Testing (Default)

When on a feature branch, analyze what changed:

git diff main --name-only  # What files changed
git diff main --stat       # Overview of changes

Then identify:

  • Which routes/pages are affected?
  • What user flows touch these changes?
  • What should be regression tested?

2. Full Exploration

Systematic crawl of the entire application:

  • Start at homepage
  • Follow all navigation links
  • Test all forms
  • Check all major user flows

3. Quick Smoke Test

30-second health check:

  • Homepage loads
  • Main navigation works
  • No console errors
  • Critical path functional

4. Targeted Testing

Test specific URLs or flows provided by the user.

Browser Testing Process

Use Cursor's built-in browser automation (Task tool with browser-use subagent):

Starting a Test Session

Launch a browser-use subagent with instructions to:

  1. Navigate to [URL]
  2. Take a screenshot
  3. Check for console errors
  4. Test [specific interaction]
  5. Report findings

Common Test Actions

  • Navigate: Go to specific URLs
  • Screenshot: Capture page state
  • Click: Interact with buttons/links
  • Fill forms: Enter test data
  • Check console: Look for JavaScript errors
  • Verify content: Confirm expected elements exist

Test Data

Use realistic but obviously fake test data:

Output Format

## QA Report: [App/Feature Name]

### Test Summary
- **URL**: [base URL tested]
- **Mode**: [Diff-aware / Full / Quick / Targeted]
- **Pages Tested**: [count]
- **Issues Found**: [count by severity]

### Health Score: [X]/100

### Issues Found

#### 🔴 Critical
**[Issue Title]**
- Page: [URL]
- Steps to reproduce: [1, 2, 3]
- Expected: [what should happen]
- Actual: [what happened]

#### 🟡 Medium
**[Issue Title]**
- [details]

#### 🟢 Minor
- [Item 1]
- [Item 2]

### Pages Tested
| Page | Status | Notes |
|------|--------|-------|
| /home | ✅ Pass | Loads correctly |
| /dashboard | ⚠️ Warning | Slow load |
| /settings | ❌ Fail | 500 error |

### Recommendations
1. [Fix critical issues before deploy]
2. [Consider improving X]

Read the full file on GitHub · 154 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 154 lines · 43 tokens per session scan A 1a9c33f7e735

Subscribe to this mod's changes

qa is a skill published in the GitHub repository Himanshu-Sangshetti/cursor-stack (6 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 853 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

playwright-cli

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…

testdino-hq/playwright-skill · 64 tokens

browse

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. 100ms per command.

timurgaleev/vibestack · 60 tokens

web-test

Этот скилл MUST быть вызван когда пользователь просит проверить или протестировать 1С через браузер в интерактивном режиме (быстрые ручные проверки). SHOULD также вызывать для одноразовой верификации поведения веб-интерфейса 1С. Do NOT использовать для создания файлов автотестов — используй playwright-test; для…

Arman-Kudaibergenov/1c-ai-development-kit · 91 tokens

playwright-test

Этот скилл MUST быть вызван когда пользователь говорит "напиши UI-тест", "создай playwright тест", "scaffold playwright", "протестируй фичу в браузере". SHOULD также вызывать после деплоя фичи 1С для создания автоматизированного регрессионного теста. Do NOT использовать для интерактивной автоматизации браузера …

Arman-Kudaibergenov/1c-ai-development-kit · 96 tokens

playwright-skill

Battle-tested Playwright patterns for writing, debugging, and scaling reliable test suites. Use when you need guidance for E2E, API, component, visual, accessibility, or security testing, plus CI/CD, CLI automation, page objects, and migration from Cypress or Selenium. TypeScript and JavaScript.

testdino-hq/playwright-skill · 66 tokens

playwright-pom

Page Object Model patterns for Playwright — when to use POM, how to structure page objects, and when fixtures or helpers are a better fit.

testdino-hq/playwright-skill · 35 tokens