← ClaudeAtlas

basic-browser-setuplisted

Set up browser QA in AgentWorks, save verified locators and application knowledge, configure a repeatable smoke test, and establish reporting. Use when onboarding an application or repairing its QA foundation.
manishiitg/coding-agent-loop · ★ 13 · AI & Automation · score 73
Install: claude install-skill manishiitg/coding-agent-loop
# Basic Browser Setup ## Outcome Create a reusable browser QA foundation with managed browser access, canonical locator helpers, a saved smoke test, video plus console/network evidence, durable application knowledge, and a live report. ## When to use Use when onboarding an application or repairing an incomplete browser QA foundation. Preserve a compatible existing setup and an explicitly chosen Playwright alternative. ## Discovery and user direction Inspect the current workflow, goals, metrics, configuration, capabilities, stores, reports, and triggers before proposing changes. Summarize reusable design and gaps, then ask focused questions for unresolved customer choices such as scope, success, approvals, thresholds, ownership, and budgets. Record the answers as customer direction. Installation alone does not approve workflow changes or execution. Default to one small-team workflow; split only for incompatible access or lifecycle boundaries. ## Required inputs Resolve the application and environment, authorized account roles, authentication approach, approved smoke expectation, test-data and cleanup boundaries, test project, recording policy, and reporting preference. Keep missing required access or behavior as an explicit blocker. ## Plan and AgentWorks tools Inspect the existing workflow first. Use the managed browser for discovery and a scripted step for the repeatable smoke runner. Add agentic investigation or a readiness branch only when it protects a real judg