菜单
Verify Agent UI browser-visible behavior with Playwright and agent-browser. Use for UI, CSS, layout, transcript, composer, approvals, usage, diagnostics, thread history, examples, mobile, overflow, focus, keyboard, click, hit-test, screenshot, accessibility snapshot, or real-local browser QA work.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/nyosegawa/agent-ui --skill browser-qa命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Integrate, customize, debug, or upgrade Agent UI v3 in external Codex App Server applications. Use for new adopter, first host app, AgentChat preset, headless + primitives, same-origin bridge skeleton, Node >=22, local media helper uploads, thread lifecycle, canonical resume, host-gated workflows, dynamic tools, theming with --aui-* tokens, Agent UI errors, or when the user says Agent UI導入, 新規導入, 初回導入, 最小構成, Codex UI, ローカルCodexアプリ, bridge, attachments, approvals, resume, local media, or upgrade Agent UI.
Plan Agent UI repository features before implementation. Use when the user asks to make a feature plan, plan before coding, research/plan/todo/goal prompt, solve a problem group, architecture plan, 実装前に計画, feature planning, PLAN/TODO作成, or goal-prompt generation for this repo. Do not use for small direct edits, review-only requests, npm release operations, upstream sync, browser QA, or external host-app integration unless the user explicitly asks for a planning package.
Review Agent UI repository changes, pull requests, branches, diffs, or Codex-generated updates for correctness, product boundary, protocol behavior, server bridge safety, package exports, tests, docs, UI regressions, and release risk. Use when the user asks for review, PR review, branch review, diff audit, safety check, or whether Agent UI changes are ready to merge.
正在显示 SKILL.md
基于 SOC 职业分类
| name | browser-qa |
| description | Verify Agent UI browser-visible behavior with Playwright and agent-browser. Use for UI, CSS, layout, transcript, composer, approvals, usage, diagnostics, thread history, examples, mobile, overflow, focus, keyboard, click, hit-test, screenshot, accessibility snapshot, or real-local browser QA work. |
Use this skill for browser-visible Agent UI changes. Playwright is the deterministic CI gate; agent-browser is for exploratory, human-like interaction checks and evidence.
agent-browser.bun run test:e2e:clean-ports before targeted browser tests.visual-route-matrix.e2e.ts before ad-hoc route-by-route screenshots.real-local-layout.e2e.ts.Use matrix tests for broad containment coverage, then use agent-browser for the specific route, viewport, or interaction that still needs human inspection.
Report routes checked, viewport sizes, automated tests, agent-browser actions, screenshots or snapshots captured, failures, and remaining browser risk.