add-chat-model
Add a new chat model id to @aituber-onair/chat and wire it through constants, provider implementation, tests, example UI selector, docs, and versioning updates. Use when requests include adding a new model, supporting a specific model id, adding a provider model, or updating supported models for providers such as claude, gemini, and openai.
devup-ui
Zero-runtime CSS-in-JS preprocessor for React. Transforms JSX styles to static CSS at build time. TRIGGER WHEN: - Writing/modifying Devup UI components (Box, Flex, Grid, Text, Button, etc.) - Using styling APIs: css(), globalCss(), keyframes() - Configuring devup.json theme (colors, typography, extends) - Setting up build plugins (Vite, Next.js, Webpack, Rsbuild, Bun) - Debugging "Cannot run on the runtime" errors - Working with responsive arrays, pseudo-selectors (_hover, _dark, etc.) - Using polymorphic `as` prop or `selectors` prop - Working with @devup-ui/components (Button, Input, Select, Toggle, etc.)
Scrapling MCP Server
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
claude-a11y-audit
Use when reviewing UI diffs, accessibility audits, or flaky UI tests to catch a11y regressions, semantic issues, keyboard/focus problems, and to recommend minimal fixes plus role-based test selectors.
trulens-evaluation-setup
Configure feedback functions and selectors for TruLens evaluations
Dart Query
Dart AI task management MCP with batch operations, DartQL selectors, CSV import, zero context rot
interactive-testing
Smoke-test the running Lightcode Electron app end-to-end via Chrome DevTools Protocol. Use when the user asks to "smoke test", "test the app", "verify the refactor in the UI", "open the app and click through", or otherwise wants Claude to drive the real running app instead of relying on unit tests. Boots dev server + Electron with CDP enabled, uses raw CDP or agent-browser as appropriate, walks the surfaces most relevant to the current diff (provider selector, ThreadDraftView, ChatPane, ThreadRuntimeRequestPanel, Browser panel), and reports findings with screenshots.
actionbook
Access pre-computed website action manuals containing page descriptions, functionality, DOM structure, and element selectors for browser automation. Use when you need CSS/XPath selectors for UI elements, building browser-based AI agents, or looking up how to interact with a website's UI.
e2e-tester
Playwright E2E testing patterns. Trigger: When writing Playwright E2E tests (Page Object Model, selectors, MCP exploration workflow).
AIR SDK
Collective intelligence for browser automation agents. Site capabilities, selectors, and extraction.
pupu-test-api
Use when running QA / regression tests against PuPu, when verifying a code change actually works in the running app, or when reading PuPu UI/state without screenshotting manually. Triggers on tasks like "test that PuPu still creates chats correctly", "verify the new model selector works end-to-end", "send a message and check the response", "what's PuPu's current state?". Phase 1 covers chat lifecycle, message send (blocking), model/toolkit/character switching, logs, state snapshot, screenshot, eval.
iOS Simulator Interaction
Use `iosef` (via Bash) as the primary tool for all iOS simulator interactions. Compared to `idb` and `simctl`, it: * Lets you interact by AX-tree selectors (`--name`, `--role`, `--identifier`) instead of only bare coordinates * Scales screenshots so pixel coordinates match iOS point space â no tra
agent-fetch
Fetch and extract full article content from URLs. Returns complete text with structure (headings, links, lists) instead of summaries. Multiple extraction strategies, browser impersonation, cookies, crawling, custom selectors, 200-700ms.