beads-manual-qa

Automate manual UI QA tasks for Beads flows with Agent Browser CLI.

Updated Jan 26, 2026
One-click install
npx skills add https://github.com/vega113/beads-orchestration-skills --skill beads-manual-qa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: beads-manual-qa
Source: https://github.com/vega113/beads-orchestration-skills/tree/main/beads-manual-qa
Command: npx skills add https://github.com/vega113/beads-orchestration-skills --skill beads-manual-qa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Manual UI QA tasks are time-consuming and error-prone without a repeatable process.

Core Features & Use Cases

  • Standardized QA sessions with Agent Browser to verify flows and capture evidence.
  • Automatic logging of results and blockers into Beads for traceability.
  • Scope-driven testing including URL, scope, devices, and known risks with tmux integration.

Quick Start

Start a QA session for a task using agent-browser, verify the defined scope, and record findings in Beads.

Frequently Asked Questions about beads-manual-qa

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

FAQPage Schema
How do I automate manual UI QA tasks for Beads task flows?

To start a QA session, use Agent Browser alongside the Beads CLI to define the testing scope including URL, target devices, and known risks, then verify the UI changes and record your findings directly back into Beads.

What do I need to set up before running UI QA sessions with Agent Browser?

Agent Browser automates manual UI QA by applying a repeatable process to UI changes that require verification, capturing evidence during testing, and reporting blockers across Beads tasks to eliminate error-prone manual checks.

Does this UI QA process support scope definition and known risk tracking?

You can integrate tmux to manage your interactive QA sessions, allowing you to maintain persistent terminal environments while running Agent Browser to verify UI changes and capture testing evidence for Beads tasks.

Why should I use an automated approach instead of manual UI testing for Beads tasks?

If UI QA is not working, verify that both Agent Browser CLI and Beads CLI (bd) are properly installed and that you have a functional Beads environment configured, as these are required dependencies for executing the automated testing scope.