← ClaudeAtlas

release-pr-quality-gatelisted

Build an AgentWorks release or pull-request browser quality gate over saved suites and exact build identity. Use when a merge, deployment, or promotion needs an auditable QA decision.
manishiitg/coding-agent-loop · ★ 13 · AI & Automation · score 73
Install: claude install-skill manishiitg/coding-agent-loop
# Release and PR Quality Gate ## Outcome Create an auditable decision workflow that binds an exact change/build to required Browser QA suites, evaluates completeness and policy, and publishes `pass`, `fail`, or `needs_review` with evidence. ## When to use Use after the required suites have passed independently and can run unattended against a uniquely identified preview or release candidate. Use scheduled monitoring for time-based deployed-health checks. ## 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 trigger type, repository/change/build/environment identity, required suites and groups, route selections, blocking and review rules, timeout/cancellation behavior, evidence retention, duplicate-run policy, and authorized status/report destinations. ## Plan and AgentWorks tools Use deterministic preparation and finalization for identity, expected-suite set, completeness, and verdict derivation. Run existing suite routes rather than copying their tests. Persist `needs