agency-evidence-collector

Captures and analyzes Playwright-generated screenshots across desktop, tablet and mobile breakpoints for QA reporting.

Updated Jul 24, 2026
One-click install
npx skills add https://github.com/imMamdouhaboammar/kaku-chatgpt-harness --skill agency-evidence-collector-immamdouhaboammar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agency-evidence-collector
Source: https://github.com/imMamdouhaboammar/kaku-chatgpt-harness/tree/main/.agents/skills/testing-evidence-collector
Command: npx skills add https://github.com/imMamdouhaboammar/kaku-chatgpt-harness --skill agency-evidence-collector-immamdouhaboammar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, and includes scripts (resource) components.

What problem does it solve?

This skill eliminates fantasy-based reporting and subjective quality assessments by mandating objective, screenshot-based evidence for every claim made during the QA process.

Core Features & Use Cases

  • Automated Visual Capture: Uses Playwright to generate consistent screenshots across desktop, tablet, and mobile breakpoints.
  • Evidence-Based Reporting: Forces a structured analysis comparing actual visual output against original project specifications.
  • Use Case: When a developer claims a feature is complete, this skill automatically captures the UI state and highlights discrepancies between the requested design and the actual implementation.

Quick Start

Run the agency-evidence-collector to perform a full visual audit of the current project and generate a comprehensive QA report.

Frequently Asked Questions about agency-evidence-collector

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

FAQPage Schema
How do I automate visual regression testing with Playwright to capture UI evidence?

Automated visual regression testing captures consistent Playwright screenshots across desktop, tablet, and mobile breakpoints to generate structured validation evidence. It compares actual visual output against project specifications to highlight UI discrepancies objectively.

Can I validate responsive layouts across multiple device profiles using automated screenshots?

Yes, responsive layouts are validated across multiple device profiles using automated screenshot generation. Playwright captures the application state at different breakpoints, enabling structured analysis of interactive elements and specification compliance.

What is the best way to enforce objective QA standards and eliminate subjective quality assessments?

Objective QA standards are enforced by mandating screenshot-based evidence for every claim during the testing process. This approach eliminates fantasy-based reporting by comparing actual visual output directly against original project requirements.

Do I need Playwright installed to run automated visual audits for web applications?

Yes, Playwright is required to run automated visual audits. The Skill depends on Playwright to automate screenshot generation and perform structured validation of UI components against defined requirements.

How does evidence-based reporting compare actual UI implementation against design specifications?

Evidence-based reporting forces a structured analysis comparing actual visual output against original project specifications. When a developer claims completion, it automatically captures the UI state and highlights discrepancies between requested designs and implementations.

When should I avoid using automated screenshot validation for QA?

Automated screenshot validation is not suited for testing non-visual application logic or backend functionality. It focuses strictly on capturing visual evidence of web application states and validating UI components against defined requirements.