React logo

React

Community
pedronauck
react

Build React 19 components and hooks under React Compiler: state, Effects, memoization, props/refs, Actions, use(), compiler/lint setup, and Vitest tests. Excludes React Native, other frameworks, and backend-only Node.js.

Overview

Publisherpedronauck
Repositoryskills
Skill namereact
Stars
635
Forks
89
Bundled files
8
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 8 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by pedronauck on GitHub. Read the source before you install it.

Installation

Install the React AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pedronauck/skills/tree/main/skills/mine/react
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pedronauck/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/mine/react .claude/skills/react
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable React in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads React on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so React is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

React

Targets React 19.2 and React Compiler 1.0 (babel-plugin-react-compiler), linted by eslint-plugin-react-hooks 7.1+. Read the reference matched by the API or behavior being changed. Load adjacent references only for concerns the change crosses; reuse relevant context already read.

The compiler is the optimizer

The compiler applies the equivalent of memo to every component and memoizes calculations inside components and hooks, at build time. It does this more granularly than hand-written hooks can — it memoizes after early returns, where useMemo is structurally forbidden.

The price is that the Rules of React stopped being style advice and became a build-time contract. When a component violates them, the compiler bails: it silently skips optimizing that component and moves on. The build stays green, the tests stay green, and the component is simply never optimized. Write code the compiler cannot bail on.

Two consequences that invert pre-compiler habits:

  • Reflexive useMemo/useCallback on cheap values is now noise, and an incomplete dependency array is worse than no memoization at all — the compiler refuses to optimize a component whose manual memoization it cannot match.
  • A rule violation costs optimization silently rather than raising an error, so the lint rules are the only thing standing between you and a quietly unoptimized app. Enable them before enabling the compiler.

Decide memoization first

SituationDo
New value or callback consumed only by render/JSXWrite it plainly; the compiler memoizes it
Value feeds a useEffect (or another hook's) dependency array and identity must holdKeep useMemo/useCallback — the escape hatch react.dev names by name
Value crosses to a non-compiled consumer (vanilla lib instance, addEventListener, uncompiled package)Keep manual memoization
Manual memoization you keep for any reasonMake its deps exhaustive, or the component bails
Working memoization in existing codeLeave it — removing it changes compilation output; test before touching
Same expensive call repeated across componentsCompiler memoization is per-component, never shared; hoist to a module-level cache or the data layer
Expensive work in a plain module-level utilNot memoized at all; the compiler only covers components and hooks
memo() with a custom areEqual comparatorKeep it; the compiler has no equivalent

Done when: each memoization added or changed by this task traces to a row above, and no row was satisfied by adding a hook the compiler already covers.

Branches

When you are…Reference
Writing or reviewing any component or hook body — purity, mutation, refs, globalsreferences/rules-of-react.md
Removing, keeping, or debating a useMemo/useCallback/memo, or a component was skipped by the compilerreferences/compiler.md
Installing or configuring the compiler, the lint preset, or adopting it incrementallyreferences/compiler-setup.md
Reaching for useEffect, or deriving/syncing statereferences/effects.md
Shaping components, composition, props, or TypeScript typesreferences/components-and-types.md
Choosing where state lives, wiring context or an external storereferences/state.md
Using use(), Actions, useOptimistic, <Activity>, metadata, or other React 19 APIsreferences/react19-apis.md
Writing or fixing component/hook testsreferences/testing.md

Apply the technical rules relevant to the changed behavior.

Tripwires

Purity — render computes from props, state, and context only. Math.random(), Date.now(), new Date(), crypto.randomUUID(), and performance.now() belong in a state initializer, an event handler, or an effect.

Mutation — props, state, hook arguments, hook return values, and any value already handed to JSX are read-only; copy before changing (setItems([...items].sort())). A value created in this render that never escapes is yours to mutate freely.

Reassignment — treat a destructured prop as read-only: rename on destructure ({ value: valueFromProps }) and derive a new const.

Refs — read and write ref.current in effects and event handlers. During render the only sanctioned touch is one-time lazy init: if (ref.current === null) ref.current = ….

Globals — module scope holds constants; per-render values live in useState/useContext and outward writes in an effect. Counters, arrays, and ad-hoc caches touched during render break Fast Refresh and forfeit compilation.

Components are static — declare components and hooks at module scope. Defining one inside another component (or returning one from a factory) makes a new type every render, resetting state and tearing down DOM.

Effects — an effect exists to synchronize with something outside React. Synchronous setState in an effect to derive or copy state is an error-level lint violation; compute during render instead.

Errors — child render errors are caught by an Error Boundary, never by try/catch around JSX.

Refs are props — forwardRef is deprecated in 19; accept ref in the props type. Likewise <Context value={…}>, not <Context.Provider>.

Escape hatch — "use no memo" is a bisection tool carrying a written reason and a removal plan, not a fix.

Related skills

tanstack for TanStack Query, Router, and Form. xstate-store for @xstate/store. shadcn for component primitives and CVA variants. tailwindcss for styling. vitest for runner configuration beyond references/testing.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the React AI skill do?

Build React 19 components and hooks under React Compiler: state, Effects, memoization, props/refs, Actions, use(), compiler/lint setup, and Vitest tests. Excludes React Native, other frameworks, and backend-only Node.js.

Why use React on TypingMind?

Because you install it once and use it with any model. React is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install React in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pedronauck/skills/tree/main/skills/mine/react. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use React?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with React?

As many as you like. As long as a model supports skills, you can use React with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the React AI skill free?

It is published on GitHub by pedronauck. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇