Everything on the browser side of a LangWatch module: createUi and the shell, a module's browser-half layer order (model/behavior/ui), host services vs components (browser-host vs design-system), where shared code goes now that kits are gone (record §3.4), building a new browser module end to end (defineBrowserModule, screens, drawers, lends, the module's *HostApi, the derived tRPC client), drawers as routed singletons, and frontend testing (colocated __tests__, jsdom docblock, component tests as integration level). Use whenever someone is building a screen, drawer, or shell chrome; writing or extending a module's browser/ package; asking how a screen reads host services (tokens, its own `*HostApi`); sharing a component, hook or data with another module (design system, contract, `<name>-client`); or writing/reviewing a component test.
Steady19 mentions in 2 weeks
44 projects use a version of this
5k20d agoReviewMountCreate a free account to mount
Implement and review the Cursor BYOK React/Tauri desktop frontend. Use for changes under apps/desktop involving routing, page layout, window chrome, settings UI, scrolling, virtualization, charts, themes, or frontend component architecture.
3.2k58d agoReviewMountCreate a free account to mount
Build and change LLM Gateway Next.js frontends — apps/ui, apps/playground, apps/code, apps/airside, and ee/admin — including API calls, data fetching, navigation, dashboard routes, dialogs and popovers, charts, number formatting, and user settings. Use when editing React components or pages in those apps, adding a dashboard page, calling the API from the UI, or formatting displayed values.
Steady9 mentions in 2 weeks
44 projects use a version of this
1.7k9d agoReviewMountCreate a free account to mount
Use when building or changing anything in the frontend: a page, a component, a layout, styling, copy on screen. Produces distinctive, production-grade UI that fits this project's existing design, covers every state, is accessible, and is checked in a browser before it is called done.
35111d agoReviewMountCreate a free account to mount
Use when building, designing, redesigning, or reviewing any UI in the dashboard React frontend (client/dashboard, including the inlined Speakeasy Elements code) — a new page, tab, card, table, form, dialog, sheet, empty or error state, settings section, or UI copy — and when addressing design feedback or Gutternote comments on a preview. Triggers: "build a page for", "add UI for", "make this look better", "redesign", "the UX is confusing", "layout shift", "overflow", "add a tab", "dashboard component".
2759d agoReviewMountCreate a free account to mount
Use when making architecture-level React decisions — component decomposition, choosing where state should live, selecting a state manager (Context vs Redux vs Zustand) or a data-fetching library (TanStack Query vs SWR), or planning a rendering-performance budget. For advanced hook patterns, use react.
1906mo agoReviewMountCreate a free account to mount
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence, or to make a feature reel (see reel mode below). Do not use for generic code review, PR review, "check my changes", CI debugging, or security audit; use qa-team, debugging-ci-failures, or security-audit instead. QA runs in PR mode or local mode, plans adaptive browser and visual checks, drives browser MCP/tooling such as Playwright MCP or Chrome DevTools MCP, captures evidence, and applies only approved/narrow fixes. Reel mode makes a feature reel instead: a short, sharp animated WebP of one UI flow for a PR description. Use it when asked for a reel, GIF, or animated demo, or when writing-pr-descriptions calls for a reel: a new action and its effect that one screenshot cannot show.
40k12d agoReviewMountCreate a free account to mount
Generic frontend development patterns for VeChain dApps — React Query, Turborepo architecture, state management, Chakra UI, i18n, loading states, and transaction UX.
158mo agoReviewMountCreate a free account to mount
Context-led frontend design: art direction derived from product, audience, brand and the existing system, not generic defaults. Named mood variants listed inside. Triggers: frontend, UI, CSS, styling, visual, theme, component, layout, responsive, accessibility, animation.
143mo agoReviewMountCreate a free account to mount
React, components, state management, and modern frontend concepts. Activated when Claude works with .jsx/.tsx files or React-related code. Most vibecoded apps use React.
148mo agoReviewMountCreate a free account to mount
Frontend engineering for browser-facing applications: TypeScript trust boundaries, semantic accessibility, UI systems, responsive browser behavior, security, resilient user states, and feature ownership. Use when building or auditing frontend contracts, styling infrastructure, browser integrations, or file organization. Use react for React composition, state, effects, Suspense, and rendering; use nextjs-app-architecture for Next.js-specific mechanics.
1423d agoReviewMountCreate a free account to mount
Frontend scaffolding for Magento 2: themes, RequireJS modules, Knockout components, LESS/CSS, transactional email templates, static asset wiring. Use to add frontend behaviour or a theme. Detects Luma, Hyva, or a custom theme and generates matching scaffolds. For Swissup Breeze stores (magento2-tools:context theme.breeze) defer theme creation to magento2-tools:breeze-theme and widget/JS work to magento2-tools:breeze-adapt. For a CMS widget (etc/widget.xml) use magento2-tools:widget.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
langwatchSkill
