Docs Writer Blog logo

Docs Writer Blog

OrganizationPopular
reactjs
docs-writer-blog

Use when writing or editing files in src/content/blog/. Provides blog post structure and conventions.

Overview

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

Use it in TypingMind

Enable Docs Writer Blog 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 Blog 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 Blog 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.

Blog Post Writer

Persona

Voice: Official React team voice Tone: Accurate, professional, forward-looking

Voice & Style

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


Frontmatter Schema

All blog posts use this YAML frontmatter structure:

yaml
---
title: "Title in Quotes"
author: Author Name(s)
date: YYYY/MM/DD
description: One or two sentence summary.
---

Field Details

FieldFormatExample
titleQuoted string"React v19", "React Conf 2024 Recap"
authorUnquoted, comma + "and" for multipleThe React Team, Dan Abramov and Lauren Tan
dateYYYY/MM/DD with forward slashes2024/12/05
description1-2 sentences, often mirrors introSummarizes announcement or content

Title Patterns by Post Type

TypePatternExample
Release"React vX.Y" or "React X.Y""React v19"
Upgrade"React [VERSION] Upgrade Guide""How to Upgrade to React 18"
Labs"React Labs: [Topic] – [Month Year]""React Labs: What We've Been Working On – February 2024"
Conf"React Conf [YEAR] Recap""React Conf 2024 Recap"
Feature"Introducing [Feature]" or descriptive"Introducing react.dev"
Security"[Severity] Security Vulnerability in [Component]""Critical Security Vulnerability in React Server Components"

Author Byline

Immediately after frontmatter, add a byline:

markdown
---

Month DD, YYYY by [Author Name](social-link)

---

Conventions

  • Full date spelled out: December 05, 2024
  • Team posts link to /community/team: [The React Team](/community/team)
  • Individual authors link to Twitter/X or Bluesky
  • Multiple authors: Oxford comma before "and"
  • Followed by horizontal rule ---

Examples:

markdown
December 05, 2024 by [The React Team](/community/team)

---
markdown
May 3, 2023 by [Dan Abramov](https://bsky.app/profile/danabra.mov), [Sophie Alpert](https://twitter.com/sophiebits), and [Andrew Clark](https://twitter.com/acdlite)

---

Universal Post Structure

All blog posts follow this structure:

  1. Frontmatter (YAML)
  2. Author byline with date
  3. Horizontal rule (---)
  4. <Intro> component (1-3 sentences)
  5. Horizontal rule (---) (optional)
  6. Main content sections (H2 with IDs)
  7. Closing section (Changelog, Thanks, etc.)

Post Type Templates

Major Release Announcement

markdown
---
title: "React vX.Y"
author: The React Team
date: YYYY/MM/DD
description: React X.Y is now available on npm! In this post, we'll give an overview of the new features.
---

Month DD, YYYY by [The React Team](/community/team)

---

<Intro>

React vX.Y is now available on npm!

</Intro>

In our [Upgrade Guide](/blog/YYYY/MM/DD/react-xy-upgrade-guide), we shared step-by-step instructions for upgrading. In this post, we'll give an overview of what's new.

- [What's new in React X.Y](#whats-new)
- [Improvements](#improvements)
- [How to upgrade](#how-to-upgrade)

---

## What's new in React X.Y {/*whats-new*/}

### Feature Name {/*feature-name*/}

[Problem this solves. Before/after code examples.]

For more information, see the docs for [`Feature`](/reference/react/Feature).

---

## Improvements in React X.Y {/*improvements*/}

### Improvement Name {/*improvement-name*/}

[Description of improvement.]

---

## How to upgrade {/*how-to-upgrade*/}

See [How to Upgrade to React X.Y](/blog/YYYY/MM/DD/react-xy-upgrade-guide) for step-by-step instructions.

---

## Changelog {/*changelog*/}

### React {/*react*/}

* Add `useNewHook` for [purpose]. ([#12345](https://github.com/react/react/pull/12345) by [@contributor](https://github.com/contributor))

---

_Thanks to [Name](url) for reviewing this post._

Upgrade Guide

markdown
---
title: "React [VERSION] Upgrade Guide"
author: Author Name
date: YYYY/MM/DD
description: Step-by-step instructions for upgrading to React [VERSION].
---

Month DD, YYYY by [Author Name](social-url)

---

<Intro>

[Summary of upgrade and what this guide covers.]

</Intro>

<Note>

#### Stepping stone version {/*stepping-stone*/}

[If applicable, describe intermediate upgrade steps.]

</Note>

In this post, we will guide you through the steps for upgrading:

- [Installing](#installing)
- [Codemods](#codemods)
- [Breaking changes](#breaking-changes)
- [New deprecations](#new-deprecations)

---

## Installing {/*installing*/}

```bash
npm install --save-exact react@^X.Y.Z react-dom@^X.Y.Z

Codemods {/codemods/}

Run all React [VERSION] codemods {/run-all-codemods/}
bash
npx codemod@latest react/[VERSION]/migration-recipe

Breaking changes {/breaking-changes/}

Removed: apiName {/removed-api-name/}

apiName was deprecated in Month YYYY (vX.X.X).

js
// Before
[old code]

// After
[new code]

Codemod [description]:

bash
npx codemod@latest react/[VERSION]/codemod-name

New deprecations {/new-deprecations/}

Deprecated: apiName {/deprecated-api-name/}

[Explanation and migration path.]


Thanks to Contributor for reviewing this post.


### React Labs Research Update

```markdown
---
title: "React Labs: What We've Been Working On – [Month Year]"
author: Author1, Author2, and Author3
date: YYYY/MM/DD
description: In React Labs posts, we write about projects in active research and development.
---

Month DD, YYYY by [Author1](url), [Author2](url), and [Author3](url)

---

<Intro>

In React Labs posts, we write about projects in active research and development. We've made significant progress since our [last update](/blog/previous-labs-post), and we'd like to share our progress.

</Intro>

[Optional: Roadmap disclaimer about timelines]

---

## Feature Name {/*feature-name*/}

<Note>

`<FeatureName />` is now available in React's Canary channel.

</Note>

[Description of feature, motivation, current status.]

### Subsection {/*subsection*/}

[Details, examples, use cases.]

---

## Research Area {/*research-area*/}

[Problem space description. Status communication.]

This research is still early. We'll share more when we're further along.

---

_Thanks to [Reviewer](url) for reviewing this post._

Thanks for reading, and see you in the next update!

React Conf Recap

markdown
---
title: "React Conf [YEAR] Recap"
author: Author1 and Author2
date: YYYY/MM/DD
description: Last week we hosted React Conf [YEAR]. In this post, we'll summarize the talks and announcements.
---

Month DD, YYYY by [Author1](url) and [Author2](url)

---

<Intro>

Last week we hosted React Conf [YEAR] [where we announced [key announcements]].

</Intro>

---

The entire [day 1](youtube-url) and [day 2](youtube-url) streams are available online.

## Day 1 {/*day-1*/}

_[Watch the full day 1 stream here.](youtube-url)_

[Description of day 1 opening and keynote highlights.]

Watch the full day 1 keynote here:

<YouTubeIframe src="https://www.youtube.com/embed/VIDEO_ID" />

## Day 2 {/*day-2*/}

_[Watch the full day 2 stream here.](youtube-url)_

[Day 2 summary.]

<YouTubeIframe src="https://www.youtube.com/embed/VIDEO_ID" />

## Q&A {/*q-and-a*/}

* [Q&A Title](youtube-url) hosted by [Host](url)

## And more... {/*and-more*/}

We also heard talks including:
* [Talk Title](youtube-url) by [Speaker](url)

## Thank you {/*thank-you*/}

Thank you to all the staff, speakers, and participants who made React Conf [YEAR] possible.

See you next time!

Feature/Tool Announcement

markdown
---
title: "Introducing [Feature Name]"
author: Author Name
date: YYYY/MM/DD
description: Today we are announcing [feature]. In this post, we'll explain [what this post covers].
---

Month DD, YYYY by [Author Name](url)

---

<Intro>

Today we are [excited/thrilled] to announce [feature]. [What this means for users.]

</Intro>

---

## tl;dr {/*tldr*/}

* Key announcement point with [relevant link](/path).
* What users can do now.
* Availability or adoption information.

## What is [Feature]? {/*what-is-feature*/}

[Explanation of the feature/tool.]

## Why we built this {/*why-we-built-this*/}

[Motivation, history, problem being solved.]

## Getting started {/*getting-started*/}

To install [feature]:

<TerminalBlock>
npm install package-name
</TerminalBlock>

[You can find more documentation here.](/path/to/docs)

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

[Future plans and next steps.]

## Thank you {/*thank-you*/}

[Acknowledgments to contributors.]

---

Thanks to [Reviewer](url) for reviewing this post.

Security Announcement

markdown
---
title: "[Severity] Security Vulnerability in [Component]"
author: The React Team
date: YYYY/MM/DD
description: Brief summary of the vulnerability. A fix has been published. We recommend upgrading immediately.

---

Month DD, YYYY by [The React Team](/community/team)

---

<Intro>

[One or two sentences summarizing the vulnerability.]

We recommend upgrading immediately.

</Intro>

---

On [date], [researcher] reported a security vulnerability that allows [description].

This vulnerability was disclosed as [CVE-YYYY-NNNNN](https://www.cve.org/CVERecord?id=CVE-YYYY-NNNNN) and is rated CVSS [score].

The vulnerability is present in versions [list] of:

* [package-name](https://www.npmjs.com/package/package-name)

## Immediate Action Required {/*immediate-action-required*/}

A fix was introduced in versions [linked versions]. Upgrade immediately.

### Affected frameworks {/*affected-frameworks*/}

[List of affected frameworks with npm links.]

### Vulnerability overview {/*vulnerability-overview*/}

[Technical explanation of the vulnerability.]

## Update Instructions {/*update-instructions*/}

### Framework Name {/*update-framework-name*/}

```bash
npm install package@version

Timeline {/timeline/}

  • November 29th: [Researcher] reported the vulnerability.
  • December 1st: Fix was created and validated.
  • December 3rd: Fix published and CVE disclosed.

Attribution {/attribution/}

Thank you to Researcher Name for discovering and reporting this vulnerability.


---

## Heading Conventions

### ID Syntax

All headings require IDs using CSS comment syntax:

```markdown
## Heading Text {/*heading-id*/}

ID Rules

  • Lowercase
  • Kebab-case (hyphens for spaces)
  • Remove special characters (apostrophes, colons, backticks)
  • Concise but descriptive

Heading Patterns

ContextExample
Feature section## New Feature: Automatic Batching {/*new-feature-automatic-batching*/}
New hook### New hook: \useActionState` {/new-hook-useactionstate/}`
API in backticks### \` {/activity/}`
Removed API#### Removed: \propTypes` {/removed-proptypes/}`
tl;dr section## tl;dr {/*tldr*/}

Component Usage Guide

Blog-Appropriate Components

ComponentUsage in Blog
<Intro>Required - Opening summary after byline
<Note>Callouts, caveats, important clarifications
<Pitfall>Warnings about common mistakes
<DeepDive>Optional technical deep dives (use sparingly)
<TerminalBlock>CLI/installation commands
<ConsoleBlock>Console error/warning output
<ConsoleBlockMulti>Multi-line console output
<YouTubeIframe>Conference video embeds
<Diagram>Visual explanations
<InlineToc />Auto-generated table of contents

<Intro> Pattern

Always wrap opening paragraph:

markdown
<Intro>

React 19 is now available on npm!

</Intro>

<Note> Patterns

Simple note:

markdown
<Note>

For React Native users, React 18 ships with the New Architecture.

</Note>

Titled note (H4 inside):

markdown
<Note>

#### React 18.3 has also been published {/*react-18-3*/}

To help with the upgrade, we've published `react@18.3`...

</Note>

<TerminalBlock> Pattern

markdown
<TerminalBlock>
npm install react@latest react-dom@latest
</TerminalBlock>

<YouTubeIframe> Pattern

markdown
<YouTubeIframe src="https://www.youtube.com/embed/VIDEO_ID" />

Link Patterns

Internal Links

TypePatternExample
Blog post/blog/YYYY/MM/DD/slug/blog/2024/12/05/react-19
API reference/reference/react/HookName/reference/react/useState
Learn section/learn/topic-name/learn/react-compiler
Community/community/team/community/team

External Links

TypePattern
GitHub PR[#12345](https://github.com/react/react/pull/12345)
GitHub user[@username](https://github.com/username)
Twitter/X[@username](https://x.com/username)
Bluesky[Name](https://bsky.app/profile/handle)
CVE[CVE-YYYY-NNNNN](https://www.cve.org/CVERecord?id=CVE-YYYY-NNNNN)
npm package[package](https://www.npmjs.com/package/package)

"See docs" Pattern

markdown
For more information, see the docs for [`useActionState`](/reference/react/useActionState).

Changelog Format

Bullet Pattern

markdown
* Add `useTransition` for concurrent rendering. ([#10426](https://github.com/react/react/pull/10426) by [@acdlite](https://github.com/acdlite))
* Fix `useReducer` observing incorrect props. ([#22445](https://github.com/react/react/pull/22445) by [@josephsavona](https://github.com/josephsavona))

Structure: Verb + backticked API + description + ([#PR](url) by [@user](url))

Verbs: Add, Fix, Remove, Make, Improve, Allow, Deprecate

Section Organization

markdown
## Changelog {/*changelog*/}

### React {/*react*/}

* [changes]

### React DOM {/*react-dom*/}

* [changes]

Acknowledgments Format

Post-closing Thanks

markdown
---

Thanks to [Name](url), [Name](url), and [Name](url) for reviewing this post.

Or italicized:

markdown
_Thanks to [Name](url) for reviewing this post._

Update Notes

For post-publication updates:

markdown
<Note>

[Updated content]

-----

_Updated January 26, 2026._

</Note>

Tone & Length by Post Type

TypeToneLengthKey Elements
ReleaseCelebratory, informativeMedium-longFeature overview, upgrade link, changelog
UpgradeInstructional, preciseLongStep-by-step, codemods, breaking changes
LabsTransparent, exploratoryMediumStatus updates, roadmap disclaimers
ConfEnthusiastic, community-focusedMediumYouTube embeds, speaker credits
FeatureExcited, explanatoryMediumtl;dr, "why", getting started
SecurityUrgent, factualShort-mediumImmediate action, timeline, CVE

Do's and Don'ts

Do:

  • Focus on facts over marketing
  • Say "upcoming" explicitly for unreleased features
  • Include FAQ sections for major announcements
  • Credit contributors and link to GitHub
  • Use "we" voice for team posts
  • Link to upgrade guides from release posts
  • Include table of contents for long posts
  • End with acknowledgments

Don't:

  • Promise features not yet available
  • Rewrite history (add update notes instead)
  • Break existing URLs
  • Use hyperbolic language ("revolutionary", "game-changing")
  • Skip the <Intro> component
  • Forget heading IDs
  • Use heavy component nesting in blogs
  • Make time estimates or predictions

Updating Old Posts

  • Never break existing URLs; add redirects when URLs change
  • Don't rewrite history; add update notes instead:
    markdown
    <Note>
    
    [Updated information]
    
    -----
    
    _Updated Month Year._
    
    </Note>

Critical Rules

  1. Heading IDs required: ## Title {/*title-id*/}
  2. <Intro> required: Every post starts with <Intro> component
  3. Byline required: Date + linked author(s) after frontmatter
  4. Date format: Frontmatter uses YYYY/MM/DD, byline uses Month DD, YYYY
  5. Link to docs: New APIs must link to reference documentation
  6. Security posts: Always include "We recommend upgrading immediately"

Components Reference

For complete MDX component patterns, invoke /docs-components.

Blog posts commonly use: <Intro>, <Note>, <Pitfall>, <TerminalBlock>, <ConsoleBlock>, <YouTubeIframe>, <DeepDive>, <Diagram>.

Prefer inline explanations over heavy component usage.

Frequently asked questions

What does the Docs Writer Blog AI skill do?

Use when writing or editing files in src/content/blog/. Provides blog post structure and conventions.

Why use Docs Writer Blog on TypingMind?

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

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

Which AI models can use Docs Writer Blog?

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 Blog?

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

Is the Docs Writer Blog 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 👇