Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
Detect React and TypeScript maintainability smells across the whole component, hook, and module, explain the cost of each, and propose a fix with a source link. Covers prop and API design (naming, booleans, callbacks, variants, controlled state, generics, refs, styling, JSDoc), state and data flow (redundant state, stale closures, context and ref misuse), effects and lifecycle, component structure and hooks, rendering correctness (keys, mutation, impure renders, hydration, the leaked 0 from &&), accessibility and focus management, async handlers, error boundaries, unsafe HTML, TypeScript discipline (any, casts, untyped catch, exhaustiveness), and a cross-file duplication pass. Defers memoization and re-render performance to react-compiler and color literals to theme-colors. Use when reviewing or writing React components or hooks, auditing for maintainability, or asked to sniff, smell-check, lint, or clean up a codebase, folder, file, or pasted snippet. Respects native HTML attributes and library conventions.
Ship a CometChat React v7 integration safely — server-minted auth tokens instead of the Auth Key, correct env prefixes per bundler, bundle hygiene, and a pre-launch checklist. Triggers: 'is this production ready', 'auth token instead of auth key react', 'secure my cometchat react setup', 'production build config react', 'going live checklist react', 'harden cometchat before launch'.
Practical patterns for using fp-ts with React - hooks, state, forms, data fetching. Use when building React apps with functional programming patterns. Works with React 18/19, Next.js 14/15.
Display user-facing alerts, notifications, and feedback messages using toast notifications from the sonner library. Use this skill whenever the user asks to show an alert, notification, success message, error message, warning, or any kind of user feedback popup.
Create modal dialogs in the frontend using a custom Modal component built on top of Radix UI Dialog. Use this skill whenever the user asks to create, add, or modify a modal, dialog, popup, or confirmation prompt in the React application.
Integrate Lenis smooth scroll into React and Next.js projects. Use when the user wants smooth scrolling, scroll-linked animations, parallax effects, GSAP ScrollTrigger sync, Framer Motion sync, programmatic scroll-to navigation, or scroll event listening in a React app. Covers ReactLenis provider setup, useLenis hook, custom scroll containers, SSR/Next.js considerations, and accessibility.
Use when initializing a new React frontend with Vite to connect to a Django backend over HTTPS. Sets up routing, CSRF protection, Axios config, and validates the build. Not for existing React projects.
Initialize vowel.to voice agent in React applications (React 19+, Next.js, TanStack Router, React Router) with complete setup including adapters, providers, hooks, and custom actions. Use when setting up voice agent integration, configuring navigation adapters, implementing custom voice actions, or integrating state management with voice AI. First read vowel-client/SKILL.md for core @vowel.to/client knowledge.
Use when creating email templates with React - welcome emails, password resets, notifications, order confirmations, or transactional emails that need to render across email clients.
Use when building React 18+ applications requiring component architecture, hooks patterns, or state management. Invoke for Server Components, performance optimization, Suspense boundaries, React 19 features.
Full Sentry SDK setup for React Native and Expo. Use when asked to "add Sentry to React Native", "install @sentry/react-native", "setup Sentry in Expo", or configure error monitoring, tracing, profiling, session replay, or logging for React Native applications. Supports Expo managed, Expo bare, and vanilla React Native.
Best practices for React Native and Expo applications. Covers list performance, animations with Reanimated, navigation, UI patterns, and monorepo configuration. Use when building, reviewing, or optimizing React Native / Expo apps.
Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
Zoom Meeting SDK for React Native. Use when embedding Zoom meetings in React Native iOS/Android apps with @zoom/meetingsdk-react-native, JWT auth, join/start flows, platform setup, and native bridge troubleshooting.
Build accessible UI with Primer React, GitHub's design system (Button, IconButton, TextInput, Textarea, Select, Checkbox, FormControl, Heading, Text, Stack, Label, CounterLabel, Flash, StateLabel, BranchName, ProgressBar, Spinner, Timeline, RelativeTime). Use when the user asks for a Primer-styled page, a GitHub-style screen, or wires Primer tokens through @primer/primitives. Triggers: 'primer', 'primer react', '@primer/react', 'github ui', 'octicons'. Scope: components, tokens, assets. Out of scope: tone of voice and marketing copy — route copy rules to a sibling skill. IMPORTANT: this file is an orchestrator. Load the references/ files named in the routing table; SKILL.md alone is insufficient.
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.