检查 Superset 的使用情况,找出适合当前工作方式但尚未使用的功能,给出建议并介绍选项;用户选定后,可协助设置定时运行、并行工作区或共享任务等功能。
- 查找尚未使用的 Superset 功能
- 设置定时运行的智能体
- 在多个工作区并行处理任务
在云端工作区通过 EAS 的 iOS 模拟器启动移动应用,并查看界面、检查代码变更。可重新加载应用或启动新会话;需要配置 `EXPO_TOKEN` 和仓库的 `.env`。
Launch and iterate on apps/mobile from a cloud sandbox (no local Xcode or simulator) on an EAS cloud iOS simulator. Use when asked to run, start, open, or show the mobile app from a cloud workspace, or to verify a mobile change there. On a machine with real Xcode, use mobile-sim-verification instead.
实测评分 未实测
查看安装方法此技能从云端工作区运行 apps/mobile/scripts/eas-dev.sh,在 EAS 的 iOS 模拟器中启动移动应用。如果已有连接会话,就会继续使用;否则会选择与当前检出代码相匹配的模拟器构建并启动新会话。缺少所需构建时会创建构建。使用 --reload 可通过 Metro 重新加载应用,使用 --new 可切换到新会话。技能还会通过 agent-device 查看屏幕、点击、输入文字和截屏,以确认代码变更是否显示在应用中。添加 --user 可使用开发账号登录。
当本地没有 Xcode 或 iOS 模拟器,但需要在云端工作区打开应用、查看界面或确认改动时,可以使用此技能。
需要设置 EXPO_TOKEN 并提供仓库的 .env。如果安装的 bun 版本与 .bun-version 不同,就无法进行构建匹配查询。在配有实际 Xcode 环境的机器上,应使用单独的 mobile-sim-verification 技能。
本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。
AI 根据 SKILL.md 的内容检查了需要注意的操作和使用前提。评分只依据实际运行的结果(实测对比)。
不计入评分。 由 AI(OpenAI Codex)于 2026年10月29日 评估。仅供参考,安装前请同时查看原文。
安装前可以查看交给 AI 代理的指令内容。
A cloud sandbox is Linux: no xcrun, no simctl. apps/mobile/scripts/eas-dev.sh is the one command
that gets the real dev-client app running on an EAS cloud iOS simulator, connected to this sandbox's
own Metro and API. Run it:
apps/mobile/scripts/eas-dev.sh
It reuses this checkout's running session when there is one. Otherwise it installs the finished
simulator build whose native fingerprint matches this checkout and starts a session, about two minutes.
It builds only when no such build exists (the first time, or after a native change), about fifteen
minutes. apps/mobile/AGENTS.md's "Verifying in the real app" section records why the script does
each step.
apps/mobile/scripts/eas-dev.sh --reload # load the app from Metro again; starts nothing
apps/mobile/scripts/eas-dev.sh --new # stop the running session and start a fresh one
apps/mobile/scripts/eas-dev.sh --user maya@local.test # sign the app in as this dev account
Switch accounts with --user name@local.test. It runs db:seed-dev for the account, which
creates it with the shared dev password and makes it an onboarded member of admin@local.test's
Pro organization. Then it signs out in Settings and signs in through "Sign in with email (dev)".
It needs no app code and takes about 20 s. It works alone on a running session or with --new
and --reload. Only @local.test accounts: to test as your real account, use the token that
setup bakes in for the first launch.
Reload with --reload. It opens the dev-client URL and waits for a new iOS Bundled line in the
Metro log, three tries. Never agent-device open Superset: that relaunches the app without the
Metro URL and it fails with "Could not connect to the server".
Switch sessions with --new, never eas simulator by hand. The egress client is bound to the
session it started with, so the script stops the old client and starts one for the new session.
With no flag it keeps a connected client and restarts one that died.
When the script started Metro, each run that (re)starts the tunnel ends only when Metro has served the app a bundle; otherwise it exits non-zero and names the Metro and egress logs. With a Metro started some other way it opens the app but cannot confirm the load.
The dev-client URL carries disableAutoLaunch=1&disableFab=1, so no dev menu opens at launch and
no gear button covers the toolbar. Each session is a fresh install, so every load passes them.
Logs and PID files are in .tmp/eas-dev/ of the checkout, so two checkouts do not stop each
other's tunnel.
The fingerprint lookup refuses to run when bun --version differs from .bun-version. The
dependencies that bun installs give a fingerprint no build has, and EAS would start a 15-minute
build that also fails. A cloud workspace made before the pin changed has the old bun: make a new
one.
The session is tagged with the workspace id. The desktop Mobile pane lists the workspace's tagged
sessions, so the person can watch the simulator there without a link. The script also prints an
expo.dev/simulator-preview/... URL for a browser.
Load the session and call agent-device directly:
cd apps/mobile && set -a && . ./.env.eas-simulator && set +a
agent-device snapshot -i # what is on screen, with @refs
agent-device press 'label="Continue"' --settle # acts, waits, prints what changed
agent-device fill @e16 "hello" --settle
agent-device screenshot /tmp/screen.png
agent-device help # the rest
agent-device keeps one session per working directory. Run it from apps/mobile every time.eas simulator:exec npx agent-device each command takes about 25 s. Install it globally
(npm install -g agent-device) when it is missing.Continue, then Close.@expo/ui Menu) are not in agent-device snapshot. Open the menu, take a
screenshot, and tap the item by coordinate: agent-device press <x> <y>. This is a limit of the
tool, not of the app.MOBILE_EAS_IDLE_MINUTES). Stop it sooner with
eas simulator:stop from apps/mobile.Needs EXPO_TOKEN and this repo's .env (.superset/setup.sh or .superset/setup.cloud.sh).
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
检查 Superset 的使用情况,找出适合当前工作方式但尚未使用的功能,给出建议并介绍选项;用户选定后,可协助设置定时运行、并行工作区或共享任务等功能。
把重复任务配置为 Superset 自动化,整理智能体指令、定时或事件触发条件及运行工作区。经明确确认后创建设置,检查已保存的条件,并查看首次运行结果以调整指令。
通过 Superset 工作区的浏览器查看网页、点击、输入并检查截图或控制台信息,可用于预览运行中的网页应用、检查界面操作和表单流程。
依据 Stripe 官方文档和 API 参数定义实现支付、订阅、发票及 Webhook 集成,涵盖产品选择、沙盒测试和事件处理,并通过 Webhook 判断支付与订阅状态。
通过 Chrome DevTools Protocol 操作正在运行的 Electron 桌面应用,复现界面问题并验证修改。按实际操作流程检查页面跳转,记录截图,并对照路由、滚动位置、焦点元素和保存状态等信息。
分析 GitHub Actions 失败日志,定位最早的有效错误,区分代码缺陷、环境问题、间歇性失败和原有故障,并对照基准分支说明失败与 PR 的关系及后续处理建议。