Write logo

Write

OrganizationPopular
reactjs
write

Use when creating new React documentation pages or updating existing ones. Accepts instructions like "add optimisticKey reference docs", "update ViewTransition with Activity", or "transition learn docs".

Overview

Publisherreactjs
Repositoryreact.dev
Skill namewrite
Stars
11.8K
Forks
8K
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Write 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/write
  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/write .claude/skills/write
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Write 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 Write 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 Write 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.

Documentation Writer

Orchestrates research, writing, and review for React documentation.

Invocation

/write add optimisticKey              → creates new reference docs
/write update ViewTransition Activity → updates ViewTransition docs to cover Activity
/write transition learn docs          → creates new learn docs for transitions
/write blog post for React 20         → creates a new blog post

Workflow

dot
digraph write_flow {
    rankdir=TB;
    "Parse intent" [shape=box];
    "Research (parallel)" [shape=box];
    "Synthesize plan" [shape=box];
    "Write docs" [shape=box];
    "Review docs" [shape=box];
    "Issues found?" [shape=diamond];
    "Done" [shape=doublecircle];

    "Parse intent" -> "Research (parallel)";
    "Research (parallel)" -> "Synthesize plan";
    "Synthesize plan" -> "Write docs";
    "Write docs" -> "Review docs";
    "Review docs" -> "Issues found?";
    "Issues found?" -> "Write docs" [label="yes - fix"];
    "Issues found?" -> "Done" [label="no"];
}

Step 1: Parse Intent

Determine from the user's instruction:

FieldHow to determine
Action"add"/"create"/"new" = new page; "update"/"edit"/"with" = modify existing
TopicThe React API or concept (e.g., optimisticKey, ViewTransition, transitions)
Doc type"reference" (default for APIs/hooks/components), "learn" (for concepts/guides), "blog" (for announcements)
Target fileFor updates: find existing file in src/content/. For new: determine path from doc type

If the intent is ambiguous, ask the user to clarify before proceeding.

Step 2: Research (Parallel Agents)

Spawn these agents in parallel:

Agent 1: React Expert Research

Use a Task agent (subagent_type: general-purpose) to invoke /react-expert <topic>. This researches the React source code, tests, PRs, issues, and type signatures.

Prompt:

Invoke the /react-expert skill for <TOPIC>. Follow the skill's full workflow:
setup the React repo, dispatch all 6 research agents in parallel, synthesize
results, and save to .claude/research/<topic>.md. Return the full research document.
Agent 2: Existing Docs Audit

Use a Task agent (subagent_type: Explore) to find and read existing documentation for the topic.

Prompt:

Find all existing documentation related to <TOPIC> in this repo:
1. Search src/content/ for files mentioning <TOPIC>
2. Read any matching files fully
3. For updates: identify what sections exist and what's missing
4. For new pages: identify related pages to understand linking/cross-references
5. Check src/sidebarLearn.json and src/sidebarReference.json for navigation placement

Return: list of existing files with summaries, navigation structure, and gaps.
Agent 3: Use Case Research

Use a Task agent (subagent_type: general-purpose) with web search to find common use cases and patterns.

Prompt:

Search the web for common use cases and patterns for React's <TOPIC>.
Focus on:
1. Real-world usage patterns developers actually need
2. Common mistakes or confusion points
3. Migration patterns (if replacing an older API)
4. Framework integration patterns (Next.js, Remix, etc.)

Return a summary of the top 5-8 use cases with brief code sketches.
Do NOT search Stack Overflow. Focus on official docs, GitHub discussions,
and high-quality technical blogs.

Step 3: Synthesize Writing Plan

After all research agents complete, create a writing plan that includes:

  1. Page type (from docs-writer-reference decision tree or learn/blog type)
  2. File path for the new or updated file
  3. Outline with section headings matching the appropriate template
  4. Content notes for each section, drawn from research:
    • API signature and parameters (from react-expert types)
    • Usage examples (from react-expert tests + use case research)
    • Caveats and pitfalls (from react-expert warnings/errors/issues)
    • Cross-references to related pages (from docs audit)
  5. Navigation changes needed (sidebar JSON updates)

Present this plan to the user and confirm before proceeding.

Step 4: Write Documentation

Dispatch a Task agent (subagent_type: general-purpose) to write the documentation.

The agent prompt MUST include:

  1. The full writing plan from Step 3
  2. An instruction to invoke the appropriate skill:
    • /docs-writer-reference for reference pages
    • /docs-writer-learn for learn pages
    • /docs-writer-blog for blog posts
  3. An instruction to invoke /docs-components for MDX component patterns
  4. An instruction to invoke /docs-sandpack if adding interactive code examples
  5. The research document content (key findings, not the full dump)

Prompt template:

You are writing React documentation. Follow these steps:

1. Invoke /docs-writer-<TYPE> to load the page template and conventions
2. Invoke /docs-components to load MDX component patterns
3. Invoke /docs-sandpack if you need interactive code examples
4. Write the documentation following the plan below

PLAN:
<writing plan from Step 3>

RESEARCH FINDINGS:
<key findings from Step 2 agents>

Write the file to: <target file path>
Also update <sidebar JSON> if adding a new page.

Step 5: Review Documentation

Invoke /review-docs on the written files. This dispatches parallel review agents checking:

  • Structure compliance (docs-writer-*)
  • Voice and style (docs-voice)
  • Component usage (docs-components)
  • Sandpack patterns (docs-sandpack)

Step 6: Fix Issues

If the review finds issues:

  1. Present the review checklist to the user
  2. Fix the issues identified
  3. Re-run /review-docs on the fixed files
  4. Repeat until clean

Important Rules

  • Always research before writing. Never write docs from LLM knowledge alone.
  • Always confirm the plan with the user before writing.
  • Always review with /review-docs after writing.
  • Match existing patterns. Read neighboring docs to match style and depth.
  • Update navigation. New pages need sidebar entries.

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 Write AI skill do?

Use when creating new React documentation pages or updating existing ones. Accepts instructions like "add optimisticKey reference docs", "update ViewTransition with Activity", or "transition learn docs".

Why use Write on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/reactjs/react.dev/tree/main/.claude/skills/write. 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 Write?

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 Write?

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

Is the Write 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 👇