agent-pi

Boot and control iOS Simulators and Android Emulators for QA testing using agent-device CLI. Manage sessions, capture screenshots, launch apps, and control devices across platforms. Invoke when user says "bring up simulators", "boot the device", "take a screenshot", "launch the app", "compare iOS and Android", "test both platforms", "visual parity check", or any task requiring device/simulator lifecycle management.

QA test skill for verifying scroll-based media feeds — video autoplay, scroll navigation, mute/unmute, and playback progression. Uses the CDP + agent-device dual-driver architecture. Works with any React Native app using expo-video or similar video player libraries. Invoke when user says "test scroll feed", "test video playback", "QA the feed", "verify video autoplay", "run scroll tests", "test media player", or any task requiring scroll-based media feed verification.

Verify and install all dependencies for the QA Automation skill package. Checks for agent-device, agent-browser, Node.js, iOS/Android tools, and the 'ws' WebSocket library. Installs missing tools automatically. Invoke when user says "check qa setup", "install qa tools", "verify qa dependencies", "set up qa automation", "prepare for testing", or any task requiring QA tool verification.

QA test skill for verifying UI state persistence across navigation. Tests that state changes (likes, bookmarks, cart items, form inputs) survive scrolling away and returning. Uses CDP + agent-device dual-driver architecture. Works with any React Native app that uses list-based feeds or scrollable content. Invoke when user says "test state persistence", "test like state", "verify bookmark persists", "QA the state", "test data survives scroll", "verify UI state", or any task requiring state persistence verification across navigation.

Automated UI test flow framework using CDP + agent-device for native apps and agent-browser for web apps. Zero-framework approach — bash scripts orchestrate simulators with no Detox, Maestro, or Appium dependencies. Provides test lifecycle, screenshot capture, assertion helpers, and JSON report generation. Invoke when user says "run tests", "test the app", "smoke test", "regression test", "verify flows", "run e2e tests", or any task requiring automated UI testing.

QA test skill for web applications using agent-browser. Tests forms, navigation, responsive layouts, state persistence via cookies/localStorage, and visual regression. The web counterpart to agent-device — together they cover native + web testing. Invoke when user says "test the web app", "test localhost", "QA the website", "test the form", "verify responsive layout", "run web tests", "test browser", or any task requiring automated web application testing.

LOCAL browser automation CLI for AI agents. The ONLY tool that can access localhost, 127.0.0.1, and local network URLs. Use for ALL browser tasks including testing local dev servers, navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, and automation. Triggers include requests to "open a website", "test localhost", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "test my local server", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Autonomous Goal-directed Iteration. Apply Karpathy's autoresearch principles to ANY task. Loops autonomously — modify, verify, keep/discard, repeat. Invoke with /skill:autoresearch or when user says "work autonomously", "iterate until done", "keep improving", or "run overnight".

@expo/ui/jetpack-compose package lets you use Jetpack Compose Views and modifiers in your app.

@expo/ui/swift-ui package lets you use SwiftUI Views and modifiers in your app.

Sandboxed bash execution using just-bash from Vercel Labs. Use when you need to run shell commands safely without modifying the real filesystem, process data files, or test scripts in an isolated sandbox with read-only FS, no network, and in-memory writes.

Generate or edit images with OpenRouter using the google/gemini-3.1-flash-image-preview model. Use when the user asks for image generation, wants a new visual from a text prompt, or wants modifications to an existing screenshot or image and expects an image file back.

Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (useLoaderData).

Slack web automation via agent-browser. Use when the user asks to check Slack, read messages, send messages, reply in threads, search Slack, check notifications, react to messages, send DMs, or any Slack communication task. Triggers include "check my Slack", "send a message on Slack", "reply to that Slack thread", "search Slack for...", "what's new on Slack", "read my DMs", "react to that message", "check Slack notifications", "message [person] on Slack".