Markstream React logo

Markstream React

CommunityPopular
Simon-He95
markstream-react

Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, `next`, or `server` entrypoint, import CSS correctly, choose between `content` and `nodes`, keep client boundaries safe, add renderer-local `streamingComponents` or `htmlComponents`, use parser transforms, or prepare a repo for `react-markdown` migration.

Overview

PublisherSimon-He95
Repositorymarkstream-vue
Skill namemarkstream-react
Stars
3K
Forks
188
Bundled files
1
LicenseMIT
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 Simon-He95 on GitHub. Read the source before you install it.

Installation

Install the Markstream 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/Simon-He95/markstream-vue/tree/main/.agents/skills/markstream-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/Simon-He95/markstream-vue.git /tmp/markstream-vue
mkdir -p .claude/skills
cp -r /tmp/markstream-vue/.agents/skills/markstream-react .claude/skills/markstream-react
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Markstream 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 Markstream 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 Markstream 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.

Markstream React

Use this skill when the host app is React or Next and the task is to wire Markstream safely.

Workflow

  1. Confirm the repo is React 18+ or a compatible Next host and accepts a beta renderer API.
  2. Install markstream-react plus only the requested optional peers.
  3. Import markstream-react/index.css from the app shell or client entry.
  4. Choose the entrypoint that matches the rendering boundary.
    • Use markstream-react for the normal client renderer.
    • Use markstream-react/next for the Next-specific component surface.
    • Use markstream-react/server for server rendering without client hooks.
  5. Start with content.
    • For streaming or high-frequency AI output, keep content and use built-in smooth streaming first.
      • smoothStreaming="auto" is the default and activates when typewriter={true} or maxLiveNodes <= 0.
      • typewriter only controls the blinking cursor and defaults to false.
      • fade controls node enter and streamed-text fade animations and defaults to true.
    • Streaming vs recovering history: in chat UIs the same renderer starts streaming and later switches to history when final={true}.
      • Streaming: smoothStreaming="auto", fade={false}, typewriter={true}. This is a conservative visual/performance choice, not an API incompatibility. This adapter has not adopted Vue 3's bounded append fades, so verify its animation behavior before enabling both.
      • Recovering history: smoothStreaming={false}, fade={true}, typewriter={false}. Content is already complete — pacing would slow it down, but fade gives a polished entry animation.
      • Dynamic switch: smoothStreaming={isStreaming ? 'auto' : false}, fade={!isStreaming}.
    • Move to nodes + final only for worker-preparsed content, shared AST stores, or custom AST control.
    • Remember that htmlPolicy now defaults to safe, and Mermaid strict mode is on by default through mermaidProps.
  6. Respect SSR boundaries in Next.
    • Prefer use client, dynamic imports with ssr: false, or other client-only boundaries when browser-only peers are involved.
  7. Use renderer-local components before custom parser work.
    • streamingComponents receives parser-backed NodeComponentProps, supports incomplete custom tags, and automatically contributes its keys to the effective customHtmlTags list.
    • htmlComponents receives sanitized HTML attributes plus children; it does not receive the parser node/loading contract.
    • Prefer defineStreamingComponents(...) and defineHtmlComponents(...) for typed maps.
    • Keep scoped setCustomComponents for built-in node overrides or shared compatibility registration.
    • Use parseOptions transforms only when migration requires token or AST changes.
  8. Validate with the smallest useful dev, build, or typecheck command.

Default Decisions

  • Renderer wiring first, migration cleanup second.
  • If the repo already uses react-markdown, pair this skill with markstream-migration.
  • Prefer content with built-in smooth streaming for most AI chat / token streaming surfaces.
  • Streaming vs recovering history: when a chat message transitions from streaming to history (e.g. final becomes true), switch props dynamically — smoothStreaming="auto", fade={false} for streaming; smoothStreaming={false}, fade={true} for history. See docs/guide/ai-chat-streaming.md for full examples.
  • Move to nodes only when another layer owns parsing or AST transforms.
  • Prefer renderer-local custom-tag maps over global registry mutation.
  • Prefer the smallest client-only boundary that solves the SSR issue.
  • Avoid smoothStreaming={true} for first-screen SSR content unless intentionally starting from blank; auto mode uses the mounted gate.
  • Keep htmlPolicy="safe" and Mermaid strict mode unless the request is preserving trusted legacy rendering.
  • If a trusted surface needs older behavior, use htmlPolicy="trusted" and mermaidProps={{ isStrict: false }} only on that surface and explain why.

Useful Doc Targets

  • docs/guide/react-quick-start.md
  • docs/guide/react-installation.md
  • docs/guide/react-components.md
  • docs/guide/react-next-ssr.md
  • docs/guide/react-markdown-migration.md
  • docs/guide/component-overrides.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 Markstream React AI skill do?

Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, `next`, or `server` entrypoint, import CSS correctly, choose between `content` and `nodes`, keep client boundaries safe, add renderer-local `streamingComponents` or `htmlComponents`, use parser transforms, or prepare a repo for `react-markdown` migration.

Why use Markstream React on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Simon-He95/markstream-vue/tree/main/.agents/skills/markstream-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 Markstream 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 Markstream React?

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

Is the Markstream React AI skill free?

Yes. It is published on GitHub by Simon-He95 under the MIT 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 👇