browser-verificationlisted

# Purpose Canonical procedure for verifying UI behavior in a real browser through the Playwright MCP tools (`mcp__plugin_playwright_playwright__browser_*`). Extracted from duplicated agent sections — @tech-lead, @ui-developer, @verification-agent, and @code-reviewer reference this skill and keep only their role-specific invariants. # Guardrails (never violate) - Confirm a live target first: `browser_navigate`, then verify the response — never assume a URL is up. - Snapshot before acting — never act on assumed DOM state. - Use throwaway/seed data; never mutate real records. - `browser_run_code_unsafe` / `browser_evaluate` run arbitrary JS in the page — authorized local/staging targets only, **never a production origin**. - Always `browser_close` when finished to release the browser session. - A browser check confirms behavior; it does not replace the automated test suite or the quality gate. Read-only verifiers keep findings supplementary and warning-level — they never flip a deterministic PASS/FAIL verdict. # Resources - Read `resources/verification-procedure.md` when running a verification — target discovery, the core loop, the observation-only variant, domain E2E routing, inputs, and related skills. # How to use ## What it does Gives you one repeatable procedure for checking UI behavior in a real browser: navigate to the page, take an accessibility snapshot, drive the flow, and capture screenshots, console errors, and network failures as evidence. It also fixes the