run

Execute browser QA plans and update run evidence incrementally.

1|Updated May 19, 2026
One-click install
npx skills add https://github.com/edonghyun/donghyuns-agent-tools --skill run-edonghyun
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: run
Source: https://github.com/edonghyun/donghyuns-agent-tools/tree/main/plugins/qa-operator/skills/run
Command: npx skills add https://github.com/edonghyun/donghyuns-agent-tools --skill run-edonghyun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns a prepared QA plan into a real browser execution flow, so you can validate login, server behavior, feature paths, screenshots, logs, and UX risks without manually stitching evidence together.

Core Features & Use Cases

  • Incremental QA execution: Loads an existing plan and updates results as each item is tested in the browser.
  • Evidence capture: Collects screenshots, traces, console logs, and network error logs while preserving a clear run history.
  • Validation and risk checks: Verifies functional behavior, retries failed items, and scans for usability issues like discoverability, feedback, accessibility, and recovery.
  • Use case: Run a browser QA pass for a login or feature release, then keep the evidence folder and summary current until every item is PASS, PARTIAL, FAIL, or BLOCKED.

Quick Start

Ask the skill to run the existing QA plan in a browser, keep the evidence updated, and summarize the results as the run progresses.

Frequently Asked Questions about run

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

FAQPage Schema
How do I capture screenshots and console logs during browser QA?

Browser QA execution captures screenshots, console logs, network traces, and network error logs incrementally as each test item runs, preserving a clear run history without manual stitching.

How do I run a Playwright QA plan and update test evidence in real time?

Load an existing qa-plan.json file and execute it in the browser to validate login flows and features, updating run-scoped result files and evidence summaries incrementally as the run progresses.

Do I need a qa-plan.json file to start browser evidence capture?

Yes, browser evidence capture and incremental QA execution require an existing qa-plan.json file and run-scoped result files, while browser evidence management strictly avoids any code changes.

How does UX risk scanning work during browser feature validation?

UX risk scanning during feature validation verifies functional behavior and checks for usability issues like discoverability, feedback, accessibility, and recovery, retrying failed items until they reach a final PASS or FAIL status.

Can I run network tracing and server checks without modifying application code?

Yes, network tracing and server checks execute against real applications while avoiding code changes, focusing entirely on browser evidence management and updating the summary until every item reaches a final status.