skills.rest
nebius
nebiusOFFICIAL
Explore all skills by this author →
WebsiteGitHub

sdlc-gui-test

Executes browser GUI flows and captures screenshots, accessibility snapshots, and pass/fail evidence against acceptance criteria.

7|5|Updated Jul 22, 2025
Search Tags:#browser automation#acceptance criteria#playwright#computer-use#uat#gui testing#accessibility snapshots
One-click install
npx skills add https://github.com/nebius/nebius-ps-services --skill sdlc-gui-test-nebius
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdlc-gui-test
Source: https://github.com/nebius/nebius-ps-services/tree/main/skills/sdlc-gui-test
Command: npx skills add https://github.com/nebius/nebius-ps-services --skill sdlc-gui-test-nebius

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Verifying that a web application's UI actually meets acceptance criteria requires controlled browser interaction and durable evidence, which is hard to do consistently inside an automated SDLC workflow. ## Core Features & Use Cases - Harness-aware browser control: Runs the declared harness, using human-like computer-use when the evaluation plan requires it, or Browser/Playwright MCP otherwise. - Evidence capture: Records screenshots, accessibility snapshots, and console or network notes at meaningful checkpoints, refreshing accessibility state after every action. - Failure classification: Maps failures to ENVIRONMENT_DEFECT, EVALUATION_DEFECT, TEST_DEFECT, or SPEC_GAP so the workflow can route correctly. - Use Case: During an Agentic SDLC run, a feature's UAT plan requires human-like computer-use; the coordinator invokes this skill to drive the app, capture evidence, and return a pass/fail result. ## Quick Start Ask the Agentic SDLC coordinator to run the GUI evaluation for the active feature using the declared harness and record evidence under the current run directory.

Frequently Asked Questions about sdlc-gui-test

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

FAQPage Schema
How do I run browser GUI acceptance tests in an agentic workflow?▼

Invoke the skill through the verified Agentic SDLC coordinator with the evaluation plan, app URL, and acceptance criteria. It drives the declared harness, captures screenshots and accessibility snapshots, and returns a pass/fail result with evidence.

When is computer-use required instead of Playwright for UI testing?▼

Computer-use is required when the acceptance contract explicitly demands human-like application control. Browser or Playwright MCP is only used when the evaluation plan allows it; they are not interchangeable substitutes.

Can I invoke sdlc-gui-test directly as a standalone command?▼

No. The skill is coordinator-only: it requires verified workflow context from the active Agentic SDLC coordinator, including project, run, and phase state. In Claude Code it is hidden from the public command menu.

Why should accessibility state be refreshed after every browser action?▼

Refreshing accessibility state after each navigation, click, or input prevents acting on stale coordinates or element references. It ensures the next interaction target reflects the actual current UI state.

What are the limitations of screenshot-only GUI verification?▼

Screenshots alone are insufficient when DOM or accessibility state is available, and data-backed flows cannot pass on screenshots alone when the plan requires API, database, or service correlation. Independent oracles are required for those cases.

Related Skills

Explore More Software Engineering Skills→
pratospratos
12

create-implementation-plan

Generate phased software implementation plans with success criteria from codebase analysis.

Community
Advanced
jeremy-newhousejeremy-newhouse

wa:validate-ci

Diagnose CI pipeline failures by classifying root causes from run logs.

Community
Advanced
joelklabojoelklabo

sketch-devtools-qa

Diagnose Chrome DevTools errors and UX regressions in the upload-to-convert flow.

Community
Intermediate
mistakeknotmistakeknot
3

tuivision

Spawn, interact with, and capture terminal UI screenshots for visual regression testing.

Community
Advanced