Docs Voice logo

Docs Voice

OrganizationPopular
reactjs
docs-voice

Use when writing any React documentation. Provides voice, tone, and style rules for all doc types.

Overview

Publisherreactjs
Repositoryreact.dev
Skill namedocs-voice
Stars
11.8K
Forks
8K
Bundled files
Instructions only
LicenseCC-BY-4.0
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Docs Voice 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/reactjs/react.dev/tree/main/.claude/skills/docs-voice
  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/reactjs/react.dev.git /tmp/react.dev
mkdir -p .claude/skills
cp -r /tmp/react.dev/.claude/skills/docs-voice .claude/skills/docs-voice
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Docs Voice 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 Docs Voice 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 Docs Voice 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 Docs Voice & Style

Universal Rules

  • Capitalize React terms when referring to the React concept in headings or as standalone concepts:
    • Core: Hook, Effect, State, Context, Ref, Component, Fragment
    • Concurrent: Transition, Action, Suspense
    • Server: Server Component, Client Component, Server Function, Server Action
    • Patterns: Error Boundary
    • Canary: Activity, View Transition, Transition Type
    • In prose: Use lowercase when paired with descriptors: "state variable", "state updates", "event handler". Capitalize when the concept stands alone or in headings: "State is isolated and private"
    • General usage stays lowercase: "the page transitions", "takes an action"
  • Product names: ESLint, TypeScript, JavaScript, Next.js (not lowercase)
  • Bold for key concepts: state variable, event handler
  • Italics for new terms being defined: event handlers
  • Inline code for APIs: useState, startTransition, <Suspense>
  • Avoid: "simple", "easy", "just", time estimates
  • Frame differences as "capabilities" not "advantages/disadvantages"
  • Avoid passive voice and jargon

Tone by Page Type

TypeToneExample
LearnConversational"Here's what that looks like...", "You might be wondering..."
ReferenceTechnical"Call useState at the top level...", "This Hook returns..."
BlogAccurateFocus on facts, not marketing

Note: Pitfall and DeepDive components can use slightly more conversational phrasing ("You might wonder...", "It might be tempting...") even in Reference pages, since they're explanatory asides.

Avoiding Jargon

Pattern: Explain behavior first, then name it.

✅ "React waits until all code in event handlers runs before processing state updates. This is called batching."

❌ "React uses batching to process state updates atomically."

Terms to avoid or explain:

JargonPlain Language
atomicall-or-nothing, batched together
idempotentsame inputs, same output
deterministicpredictable, same result every time
memoizeremember the result, skip recalculating
referentially transparent(avoid - describe the behavior)
invariantrule that must always be true
reify(avoid - describe what's being created)

Allowed technical terms in Reference pages:

  • "stale closures" - standard JS/React term, can be used in Caveats
  • "stable identity" - React term for consistent object references across renders
  • "reactive" - React term for values that trigger re-renders when changed
  • These don't need explanation in Reference pages (readers are expected to know them)

Use established analogies sparingly—once when introducing a concept, not repeatedly:

ConceptAnalogy
Components/ReactKitchen (components as cooks, React as waiter)
Render phasesRestaurant ordering (trigger/render/commit)
State batchingWaiter collecting full order before going to kitchen
State behaviorSnapshot/photograph in time
State storageReact storing state "on a shelf"
State purposeComponent's memory
Pure functionsRecipes (same ingredients → same dish)
Pure functionsMath formulas (y = 2x)
PropsAdjustable "knobs"
Children prop"Hole" to be filled by parent
KeysFile names in a folder
Curly braces in JSX"Window into JavaScript"
Declarative UITaxi driver (destination, not turn-by-turn)
Imperative UITurn-by-turn navigation
State structureDatabase normalization
Refs"Secret pocket" React doesn't track
Effects/Refs"Escape hatch" from React
ContextCSS inheritance / "Teleportation"
Custom HooksDesign system

Common Prose Patterns

Wrong vs Right code:

mdx
\`\`\`js
// 🚩 Don't mutate state:
obj.x = 10;
\`\`\`

\`\`\`js
// ✅ Replace with new object:
setObj({ ...obj, x: 10 });
\`\`\`

Table comparisons:

mdx
| passing a function | calling a function |
| `onClick={handleClick}` | `onClick={handleClick()}` |

Linking:

mdx
[Read about state](/learn/state-a-components-memory)
[See `useState` reference](/reference/react/useState)

Code Style

  • Prefer JSX over createElement
  • Use const/let, never var
  • Prefer named function declarations for top-level functions
  • Arrow functions for callbacks that need this preservation

Version Documentation

When APIs change between versions:

mdx
Starting in React 19, render `<Context>` as a provider:
\`\`\`js
<SomeContext value={value}>{children}</SomeContext>
\`\`\`

In older versions:
\`\`\`js
<SomeContext.Provider value={value}>{children}</SomeContext.Provider>
\`\`\`

Patterns:

  • "Starting in React 19..." for new APIs
  • "In older versions of React..." for legacy patterns

Frequently asked questions

What does the Docs Voice AI skill do?

Use when writing any React documentation. Provides voice, tone, and style rules for all doc types.

Why use Docs Voice on TypingMind?

Because you install it once and use it with any model. Docs Voice 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 Docs Voice in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/reactjs/react.dev/tree/main/.claude/skills/docs-voice. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Docs Voice?

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 Docs Voice?

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

Is the Docs Voice AI skill free?

Yes. It is published on GitHub by reactjs under the CC-BY-4.0 license. 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 👇