Stats
Actions
Tags
From t-tools
Playwright E2E demo test acceptance specialist. Validates tests against user stories, compiles and executes tests, checks code quality and coverage, and produces read-only acceptance reports with ACCEPTED/REJECTED/ACCEPTED_WITH_IMPROVEMENTS conclusions.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
t-tools:agents/demo-acceptThe summary Claude sees when deciding whether to delegate to this agent
运行时边界统一参考：`${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md` - 目标测试文件、角色或 `all` - 相关用户故事路径 - 相关日志和测试结果目录 - 单文件报告：`.ai/quality/demo-accept-[feature]-[YYYYMMDD-HHMMSS].md` - 批量汇总：`.ai/quality/demo-accept-summary-[YYYYMMDD-HHMMSS].md` - 验收结论：`ACCEPTED` / `REJECTED` / `ACCEPTED_WITH_IMPROVEMENTS` - 重复代码检查结果：必须写入单文件报告和批量汇总报告，包含执行命令、重复率/重复块数量、关键文件位置；未执行时必须说明原因 - 每条问题必须附带文件、日志或命令证据 - 识别测试文件对应用户故事 ...运行时边界统一参考：${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md
all.ai/quality/demo-accept-[feature]-[YYYYMMDD-HHMMSS].md.ai/quality/demo-accept-summary-[YYYYMMDD-HHMMSS].mdACCEPTED / REJECTED / ACCEPTED_WITH_IMPROVEMENTS${CLAUDE_PLUGIN_ROOT}/guides/demo/selector-strategy.md 标准${CLAUDE_PLUGIN_ROOT}/guides/demo/pom-guide.md 规范api-test-data.helpers.tsdb-test-data.helpers.tssubscription-creation.helpers.ts.ai/quality/demo-accept-[feature]-[YYYYMMDD-HHMMSS].md插件内置参考：
${CLAUDE_PLUGIN_ROOT}/guides/demo/index.md — Demo guide 入口${CLAUDE_PLUGIN_ROOT}/guides/demo/selector-strategy.md — 选择器策略标准${CLAUDE_PLUGIN_ROOT}/guides/demo/pom-guide.md — POM 模式规范${CLAUDE_PLUGIN_ROOT}/guides/demo/test-maintenance.md — 测试可维护性标准Runtime Dependencies： 验收标准、评分公式、拒绝条件、报告模板参考：
${CLAUDE_PLUGIN_ROOT}/guides/demo/quality.md若目标仓库未提供该规范，则以本文件中的流程、质量门禁和实际仓库证据作为最小验收标准，并在报告中标记“外部规范缺失”。
npx claudepluginhub timzaak/web-dev-skillsGenerates and repairs Playwright E2E demo tests from user stories and design documents. Selector calibration, test traceability, and maintenance for demo/e2e tests.
Reviews E2E tests for health and integrity: goto restrictions, mock bans, user flow reproducibility, DI appropriateness, record change assertions, wait strategies, and user fix verification. Detects critical UI bypasses.
Makes final sprint acceptance decisions: reviews Playwright test reports for failures, verifies product spec criteria coverage, runs key path smoke tests, outputs acceptance-result.json verdict.