- Home
- Skills
- Testing & Debugging
- senior qa engineer
senior qa engineer
Professional browser-based QA automation that discovers flows, executes risk-based tests, and generates PDF reports.
$20
Works with the AI Agents you already use
senior qa engineer
Example session with this skill installed
QA my staging site at https://staging.myapp.io. I need a Standard depth run. Credentials for a regular user and admin are in my env vars. Focus on the new checkout flow.
- Read your context and instructions
- Compiled the senior qa engineer
- Generated the document
I have completed the QA run for staging.myapp.io. I discovered 5 primary user flows, executed 22 test cases, and identified 3 defects.
QA Execution Summary
| Metric | Value |
|---|---|
| Release Verdict | No-Go |
| Pass Rate | 86% (19 Pass, 2 Fail, 1 Blocked) |
| Critical Defects | 1 (S1 Blocker) |
| Major Defects | 1 (S2) |
| Minor Defects | 1 (S4) |
| Tested Environment | Staging (Chromium / Desktop) |
Top Issues
- [Checkout] S1 Blocker: Application throws 500 error when clicking 'Place Order' with a saved credit card.
[Account] S2 Major: User profile fails to update phone number; API returns 400 validation error for valid formats.
3. [UI] S4 Minor: Button text on mobile view is truncated in the footer.
Test Coverage
- F1: User Login/Auth: 100% Pass
- F2: Product Search: 100% Pass
- F3: Checkout Flow: 40% Pass (Blocked by S1)
- F4: Admin Dashboard: 90% Pass
Next steps
- Review the full report at
qa-run-20231027-1430/QA-Report-myapp-20231027.pdffor screenshots and network logs. - Fix the S1 Blocker in the checkout component before re-testing.
- Verify the phone number regex in the backend
user-service.
QA-Report-myapp-20231027.pdf
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Testing a web application manually is slow, inconsistent, and misses edge cases that break production. This skill delivers an end to end QA engineering lifecycle, from initial discovery to a professional PDF release recommendation.
What it does
- Automated Discovery uses Playwright to crawl the application, map user flows, and capture screenshots of every page.
- Risk-Based Planning generates test cases based on business impact and likelihood of failure, focusing on recent code changes.
- Cross-Role Testing handles multiple user personas by managing browser sessions for guests, customers, and admins.
- Defect Reporting logs reproducible bugs with severity, priority, console logs, and network failure data.
- Visual Evidence captures screenshots at every verification point and failure state to prove issues to developers.
- Release Certification produces a professional PDF report containing pass/fail metrics, coverage charts, and a Go/No-Go recommendation.
How it works
- Briefing phase where you provide the target URL, environment details, and scope (Smoke, Standard, or Deep).
- Authentication using environment variables to securely log in and save sessions without leaking credentials.
- Execution of Playwright scripts that interact with the UI like a real human, including retries for flaky tests.
- Triage of any failures into technical defects or UX observations with clear steps to reproduce.
Frameworks & tools
This skill uses Python and Playwright for browser automation. It requires Chromium and manages project data via JSON and Markdown.
Why this beats prompting it yourself
Generic prompts often ignore the discovery phase, resulting in "happy path" tests that miss real-world bugs. This skill implements a systematic six-phase methodology used by senior QA leads, ensuring high-risk areas are prioritized and evidence is preserved in a standardized results schema.
Use cases
- Regression Testing before a major production deployment to ensure existing features still work.
- Smoke Testing new builds in a staging environment to catch blockers early.
- Bug Validation to provide developers with clear, reproducible steps and network logs for reported issues.
- UAT Reporting for stakeholders who require a formal PDF sign-off and risk assessment.
Known limitations
Does not support bypassing CAPTCHAs or MFA without manual intervention. Destructive actions and load testing are explicitly out of scope to prevent accidental data loss or downtime.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.
No automated CAPTCHA/MFA bypass. Destructive actions (delete, refund) are disabled by default. Requires Playwright and Python. No high-volume load or brute force testing.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
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
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago
- Software
Python
Permissions
Allowed Hosts