From t-tools
Validates demo tests cover user stories, compile, pass, and outputs structured acceptance reports. Useful for demo quality gates and CI acceptance checks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/t-tools:t-demo-accept [测试文件路径|角色名|all][测试文件路径|角色名|all]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
运行时边界统一参考:`${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md`
运行时边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md
.ai/quality/。/t-demo-accept [target]
target 说明:
demo/e2e/super-admin/super-admin-comprehensive-demo.e2e.tssuper-admin / realm-admin / regular-user / third-party-appall 或留空:验收全部 Demo 测试识别目标测试文件。
若是文件路径:仅处理该文件。
若是角色名:匹配 demo/e2e/** 下对应文件。
若是 all 或空:扫描 demo/e2e/**/*.e2e.ts,排除 fixtures/、templates/、verification/。
用户故事一致性检查(必须)。
读取测试文件顶部注释中的用户故事路径。
校验用户故事文件存在。
核对场景覆盖、角色匹配、关键断言与验收标准。
编译检查(必须)。
cd demo && npm run build
uv run scripts/demo-test-runner.py "[测试文件]" --mode fast --log-level mini
若任一测试失败、超时或编译失败,直接判定该文件 REJECTED。
代码质量检查。
grep -n "verifyTestEnvironment\|cleanupDemoTestData" [测试文件路径]
grep -n "UnifiedLogger\|logger\." [测试文件路径]
grep -n "waitForTimeout" [测试文件路径]
grep -n "data-testid\|getByRole\|getByText" [测试文件路径]
npx jscpd --pattern "**/*.ts" --reporters console demo/e2e
wc -l [测试文件路径]
.ai/quality/demo-accept-[name]-[YYYYMMDD-HHMMSS].md.ai/quality/demo-accept-summary-[YYYYMMDD-HHMMSS].md每个文件产出:
ACCEPTED / ACCEPTED_WITH_IMPROVEMENTS / REJECTED日志路径统一使用仓库相对路径:
log/backend-demo.loglog/frontend-demo.logdemo/test-results/P0 必须全部通过:
允许 ACCEPTED_WITH_IMPROVEMENTS 的前提:
npx claudepluginhub timzaak/web-dev-skillsRuns a single demo E2E test file, diagnoses failures with sub-agents, dispatches fixes, runs layer-specific regression tests, and re-runs until pass.
Validates acceptance tests against AAID BDD quality criteria, checking three-layer architecture, isolation, state management, and stubbing. Produces pass/warn/fail table.
Runs parallel specialized agents to verify implementations, run tests (unit/e2e/integration/perf/LLM), grade quality (0-10 scale), and suggest improvements. Use before merging.