Docs Writer Learn logo

Docs Writer Learn

OrganizationPopular
reactjs
docs-writer-learn

Use when writing or editing files in src/content/learn/. Provides Learn page structure and tone.

Overview

Publisherreactjs
Repositoryreact.dev
Skill namedocs-writer-learn
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 Writer Learn 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-writer-learn
  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-writer-learn .claude/skills/docs-writer-learn
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Docs Writer Learn 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 Writer Learn 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 Writer Learn 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.

Learn Page Writer

Persona

Voice: Patient teacher guiding a friend through concepts Tone: Conversational, warm, encouraging

Voice & Style

For tone, capitalization, jargon, and prose patterns, invoke /docs-voice.

Page Structure Variants

1. Standard Learn Page (Most Common)

mdx
---
title: Page Title
---

<Intro>
1-3 sentences introducing the concept. Use *italics* for new terms.
</Intro>

<YouWillLearn>

* Learning outcome 1
* Learning outcome 2
* Learning outcome 3-5

</YouWillLearn>

## Section Name {/*section-id*/}

Content with Sandpack examples, Pitfalls, Notes, DeepDives...

## Another Section {/*another-section*/}

More content...

<Recap>

* Summary point 1
* Summary point 2
* Summary points 3-9

</Recap>

<Challenges>

#### Challenge title {/*challenge-id*/}

Description...

<Hint>
Optional guidance (single paragraph)
</Hint>

<Sandpack>
{/* Starting code */}
</Sandpack>

<Solution>
Explanation...

<Sandpack>
{/* Fixed code */}
</Sandpack>
</Solution>

</Challenges>

2. Chapter Introduction Page

For pages that introduce a chapter (like describing-the-ui.md, managing-state.md):

mdx
<YouWillLearn isChapter={true}>

* [Sub-page title](/learn/sub-page-name) to learn...
* [Another page](/learn/another-page) to learn...

</YouWillLearn>

## Preview Section {/*section-id*/}

Preview description with mini Sandpack example

<LearnMore path="/learn/sub-page-name">

Read **[Page Title](/learn/sub-page-name)** to learn how to...

</LearnMore>

## What's next? {/*whats-next*/}

Head over to [First Page](/learn/first-page) to start reading this chapter page by page!

Important: Chapter intro pages do NOT include <Recap> or <Challenges> sections.

3. Tutorial Page

For step-by-step tutorials (like tutorial-tic-tac-toe.md):

mdx
<Intro>
Brief statement of what will be built
</Intro>

<Note>
Alternative learning path offered
</Note>

Table of contents (prose listing of major sections)

## Setup {/*setup*/}
...

## Main Content {/*main-content*/}
Progressive code building with ### subsections

No YouWillLearn, Recap, or Challenges

Ends with ordered list of "extra credit" improvements

4. Reference-Style Learn Page

For pages with heavy API documentation (like typescript.md):

mdx
<YouWillLearn>

* [Link to section](#section-anchor)
* [Link to another section](#another-section)

</YouWillLearn>

## Sections with ### subsections

## Further learning {/*further-learning*/}

No Recap or Challenges

Heading ID Conventions

All headings require IDs in {/*kebab-case*/} format:

markdown
## Section Title {/*section-title*/}
### Subsection Title {/*subsection-title*/}
#### DeepDive Title {/*deepdive-title*/}

ID Generation Rules:

  • Lowercase everything
  • Replace spaces with hyphens
  • Remove apostrophes, quotes
  • Remove or convert special chars (:, ?, !, ., parentheses)

Examples:

  • "What's React?" → {/*whats-react*/}
  • "Step 1: Create the context" → {/*step-1-create-the-context*/}
  • "Conditional (ternary) operator (? :)" → {/*conditional-ternary-operator--*/}

Teaching Patterns

Problem-First Teaching

Show broken/problematic code BEFORE the solution:

  1. Present problematic approach with // 🔴 Avoid: comment
  2. Explain WHY it's wrong (don't just say it is)
  3. Show the solution with // ✅ Good: comment
  4. Invite experimentation

Progressive Complexity

Build understanding in layers:

  1. Show simplest working version
  2. Identify limitation or repetition
  3. Introduce solution incrementally
  4. Show complete solution
  5. Invite experimentation: "Try changing..."

Numbered Step Patterns

For multi-step processes:

As section headings:

markdown
### Step 1: Action to take {/*step-1-action*/}
### Step 2: Next action {/*step-2-next-action*/}

As inline lists:

markdown
To implement this:
1. **Declare** `inputRef` with the `useRef` Hook.
2. **Pass it** as `<input ref={inputRef}>`.
3. **Read** the input DOM node from `inputRef.current`.

Interactive Invitations

After Sandpack examples, encourage experimentation:

  • "Try changing X to Y. See how...?"
  • "Try it in the sandbox above!"
  • "Click each button separately:"
  • "Have a guess!"
  • "Verify that..."

Decision Questions

Help readers build intuition:

"When you're not sure whether some code should be in an Effect or in an event handler, ask yourself why this code needs to run."

Component Placement Order

  1. <Intro> - First after frontmatter
  2. <YouWillLearn> - After Intro (standard/chapter pages)
  3. Body content with <Note>, <Pitfall>, <DeepDive> placed contextually
  4. <Recap> - Before Challenges (standard pages only)
  5. <Challenges> - End of page (standard pages only)

For component structure and syntax, invoke /docs-components.

Code Examples

For Sandpack file structure, naming conventions, code style, and pedagogical markers, invoke /docs-sandpack.

Cross-Referencing

When to Link

Link to /learn:

  • Explaining concepts or mental models
  • Teaching how things work together
  • Tutorials and guides
  • "Why" questions

Link to /reference:

  • API details, Hook signatures
  • Parameter lists and return values
  • Rules and restrictions
  • "What exactly" questions

Link Formats

markdown
[concept name](/learn/page-name)
[`useState`](/reference/react/useState)
[section link](/learn/page-name#section-id)
[MDN](https://developer.mozilla.org/...)

Section Dividers

Important: Learn pages typically do NOT use --- dividers. The heading hierarchy provides sufficient structure. Only consider dividers in exceptional cases like separating main content from meta/contribution sections.

Do's and Don'ts

Do:

  • Use "you" to address the reader
  • Show broken code before fixes
  • Explain behavior before naming concepts
  • Build concepts progressively
  • Include interactive Sandpack examples
  • Use established analogies consistently
  • Place Pitfalls AFTER explaining concepts
  • Invite experimentation with "Try..." phrases

Don't:

  • Use "simple", "easy", "just", or time estimates
  • Reference concepts not yet introduced
  • Skip required components for page type
  • Use passive voice without reason
  • Place Pitfalls before teaching the concept
  • Use --- dividers between sections
  • Create unnecessary abstraction in examples
  • Place consecutive Pitfalls or Notes without separating prose (combine or separate)

Critical Rules

  1. All headings require IDs: ## Title {/*title-id*/}
  2. Chapter intros use isChapter={true} and <LearnMore>
  3. Tutorial pages omit YouWillLearn/Recap/Challenges
  4. Problem-first teaching: Show broken → explain → fix
  5. No consecutive Pitfalls/Notes: See /docs-components Callout Spacing Rules

For component patterns, invoke /docs-components. For Sandpack patterns, invoke /docs-sandpack.

Frequently asked questions

What does the Docs Writer Learn AI skill do?

Use when writing or editing files in src/content/learn/. Provides Learn page structure and tone.

Why use Docs Writer Learn on TypingMind?

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

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

Which AI models can use Docs Writer Learn?

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 Writer Learn?

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

Is the Docs Writer Learn 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 👇