Browser QA — Testing skill for Claude Code
Discover YAML user-stories, fan out bowser-qa-agent subagents in parallel against a running web app, aggregate results into one Run report.
How to install Browser QA
Installs to ~/.claude/skills/hoangtmbk-skills-browser-qa/SKILL.md
mkdir -p ~/.claude/skills/hoangtmbk-skills-browser-qa && curl -fsSL https://raw.githubusercontent.com/hoangtmbk/skills/HEAD/commands/browser-qa.md -o ~/.claude/skills/hoangtmbk-skills-browser-qa/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Browser QA does
description: Discover YAML user-stories, fan out bowser-qa-agent subagents in parallel against a running web app, aggregate results into one Run report. argument-hint: [headed] [vision] [save-test] [filename-filter]
/browser-qa
Orchestrate end-to-end browser QA across every Story defined in `ai_review/user_stories/*.yaml`. Use this when you want a single command to fan out one `bowser-qa-agent` subagent per Story in parallel, then collect their PASS/FAIL verdicts into a unified Run r
Alternatives in Testing
- Deslop Reborn — One iteration of the IronClaw Reborn de-slop loop — take ONE Reborn crate, fan out parallel review sub-agents 12.6k ★
- Test Scenarios — Create comprehensive test scenarios from user stories 7.8k ★
- Factory — Dark Factory Mode - Spec-in, software-out autonomous pipeline 2.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
UI Review
Parallel user story validation — discovers YAML stories, fans out bowser-qa-agents, aggregates results
QA Explore
Autonomously click every reachable control of a running web app and report what broke
Dogfood
Exploratory web QA against a target URL — drives a real browser, captures evidence, writes a structured report
QA Integration
Run integration/E2E QA against a RUNNING app via a real browser — execute new + regression test cases, assert
ShipGuard
Claude Code skills for automated E2E testing with agent-browser (Playwright CLI). Discover routes, generate YA
Parallel Fix
Use when facing 3+ independent test failures or broken subsystems with different root causes. Dispatches one a
Related Agents
Bowser QA Agent
UI validation agent that executes user stories against web apps and reports pass/fail results with screenshots
Kimi Swarm Write
Use this agent ONLY when the user has explicitly asked Kimi to make EDITS across MANY disjoint targets IN PARA
Fan Out
Solve one slice of a decomposable task independently. Other fan-out agents may be working on other slices in p