菜单
Run Browser Validation with Playwright golden-path checks, screenshots, console/network capture, and HTML reporting.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build a lightweight skill index and load full skill instructions only on demand to reduce startup context pressure.
Select and run a multi-agent workflow pattern for work that exceeds one agent's reliable scope. Use for parallel research, independent reviews, cross-domain changes, or high-risk implementation planning.
Select and run a multi-agent workflow pattern for work that exceeds one agent's reliable scope. Use for parallel research, independent reviews, cross-domain changes, or high-risk implementation planning.
Use composable middleware behaviors for provider/tool execution: retry, caching, timeout, telemetry, and budget guards.
Use this skill whenever the agent makes a mistake, the user observes an avoidable failure, a pattern recurs, or someone says "the agent keeps doing X". Files an "Engineer the Harness" entry — Mitchell Hashimoto's discipline: every failure becomes a permanent prevention mechanism. Always invoke this instead of just fixing the immediate symptom.
Use composable middleware behaviors for provider/tool execution: retry, caching, timeout, telemetry, and budget guards.
| name | verify-ui |
| description | Run Browser Validation with Playwright golden-path checks, screenshots, console/network capture, and HTML reporting. |
| allowed-tools | Bash(node .harness/scripts/verify-ui.mjs:*) |
| suggested-turns | 6 |
Runs Tier 4 Browser Validation for a project UI.
node .harness/scripts/verify-ui.mjs --url=http://localhost:3000
node .harness/scripts/verify-ui.mjs --command="npm run dev" --url=http://localhost:3000
node .harness/scripts/verify-ui.mjs --mock --allow-mock-exit-zero
--mock is only a report-generation smoke mode. It is not browser evidence and
must not be used to satisfy a task evidence ui gate.
.harness/ui-validation/<run-id>/.summary.json — machine-readable pass/fail and artifacts.report.html — browser validation dashboard.screenshots/home.png — full-page screenshot when Playwright runs..harness/ui-validation/latest.json — pointer to the latest result.Task evidence that references summary.json requires passing page-load,
screenshot, console-errors, and network-failures summary checks.