← ClaudeAtlas

critical-journey-validationlisted

Build AgentWorks browser regression validation using existing application knowledge, test setup, and verified locators. Run approved journeys, investigate failures, and publish durable evidence-backed results.
manishiitg/coding-agent-loop · ★ 13 · AI & Automation · score 73
Install: claude install-skill manishiitg/coding-agent-loop
# Critical Journey Validation ## Outcome Create repeatable regression coverage for agreed critical journeys using the application's existing browser foundation, canonical locators, recording policy, durable results, and live report. ## When to use Use after Basic Browser Setup or with an equivalent verified configuration. Use it to add, execute, and investigate approved journeys while preserving the customer's runner, process, and approval rules. ## 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 profile, canonical suite and locator helpers, journeys and expected outcomes, account/test-data boundaries, execution and diagnostic limits, recording retention, and reporting preferences. ## Plan and AgentWorks tools Use scripted steps for saved Playwright execution and deterministic persistence. Keep investigation and evidence-based classification in a coherent message sequence. Add branches only when failure classifications lead to different actions. Foll