Agent skill

Assistant UI Streaming

Guide for assistant-stream package and streaming protocols. An agent skill from compozy/compozy.

MITAuto-check passedDevelopment

Install Assistant UI Streaming

skills CLI

$ npx skills add compozy/compozy --skill assistant-ui-streaming -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install compozy/compozy assistant-ui-streaming --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/compozy/compozy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/assistant-ui/assistant-ui-streaming .claude/skills/assistant-ui-streaming && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "assistant-ui-streaming" agent skill from https://github.com/compozy/compozy/tree/main/.agents/skills/assistant-ui/assistant-ui-streaming into .claude/skills/assistant-ui-streaming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assistant-ui-streaming", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/compozy/compozy/tree/main/.agents/skills/assistant-ui/assistant-ui-streaming

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add compozy/compozy --skill assistant-ui-streaming -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install compozy/compozy assistant-ui-streaming --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/compozy/compozy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/assistant-ui/assistant-ui-streaming .agents/skills/assistant-ui-streaming && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "assistant-ui-streaming" agent skill from https://github.com/compozy/compozy/tree/main/.agents/skills/assistant-ui/assistant-ui-streaming into .agents/skills/assistant-ui-streaming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assistant-ui-streaming", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add compozy/compozy --skill assistant-ui-streaming -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install compozy/compozy assistant-ui-streaming --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/compozy/compozy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/assistant-ui/assistant-ui-streaming .cursor/skills/assistant-ui-streaming && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "assistant-ui-streaming" agent skill from https://github.com/compozy/compozy/tree/main/.agents/skills/assistant-ui/assistant-ui-streaming into .cursor/skills/assistant-ui-streaming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assistant-ui-streaming", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/compozy/compozy.git --path .agents/skills/assistant-ui/assistant-ui-streaming

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add compozy/compozy --skill assistant-ui-streaming -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install compozy/compozy assistant-ui-streaming --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/compozy/compozy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/assistant-ui/assistant-ui-streaming .gemini/skills/assistant-ui-streaming && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "assistant-ui-streaming" agent skill from https://github.com/compozy/compozy/tree/main/.agents/skills/assistant-ui/assistant-ui-streaming into .gemini/skills/assistant-ui-streaming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assistant-ui-streaming", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install compozy/compozy assistant-ui-streaming

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add compozy/compozy --skill assistant-ui-streaming -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/compozy/compozy.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/assistant-ui/assistant-ui-streaming .github/skills/assistant-ui-streaming && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "assistant-ui-streaming" agent skill from https://github.com/compozy/compozy/tree/main/.agents/skills/assistant-ui/assistant-ui-streaming into .github/skills/assistant-ui-streaming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assistant-ui-streaming", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add compozy/compozy --skill assistant-ui-streaming -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install compozy/compozy assistant-ui-streaming --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/compozy/compozy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/assistant-ui/assistant-ui-streaming .opencode/skills/assistant-ui-streaming && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "assistant-ui-streaming" agent skill from https://github.com/compozy/compozy/tree/main/.agents/skills/assistant-ui/assistant-ui-streaming into .opencode/skills/assistant-ui-streaming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assistant-ui-streaming", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: assistant-ui-streaming
GitHub stars: 2.8k
Token cost: ~813 tokens
SKILL.md length: 113 words
Files: 4 (incl. references)
Skills in repo: 47
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Guide for assistant-stream package and streaming protocols. An agent skill from compozy/compozy.

Implementing streaming backends
SKILL.md covers References, When to Use, Installation and Custom Streaming Response, plus 4 more sections
Calls npm
Custom protocols

What it does

Assistant UI Streaming is an agent skill from compozy/compozy. Guide for assistant-stream package and streaming protocols. Use when implementing streaming backends, custom protocols, or debugging stream issues.

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/assistant-transport.md`, `references/data-stream.md` and `references/encoders.md`).

It sits in Development, covering Debugging. The repository describes itself as: An operating system for AI agents. Plug in the agent CLIs you already use (Claude Code, Codex, Gemini CLI, Cursor) and they become a team: they split the work, hand tasks to each… The licence is MIT.

When your agent uses it

Implementing streaming backends
Custom protocols
Debugging stream issues

Example prompts

“/assistant-ui-streaming”

Requirements

Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit c46be43. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- assistant-ui.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Assistant UI Streaming loads about 813 tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 113 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~43
When it runs · the whole SKILL.md, loaded when a task matches: ~813
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from compozy/compozy at commit c46be43, republished under its MIT licence (© compozy). 113 words, ~813 tokens.

Download SKILL.mdSave it as .claude/skills/assistant-ui-streaming/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: assistant-ui-streaming
description: Guide for assistant-stream package and streaming protocols. Use when implementing streaming backends, custom protocols, or debugging stream issues.
version: 0.0.1
license: MIT

assistant-ui Streaming

Always consult assistant-ui.com/llms.txt for latest API.

The assistant-stream package handles streaming from AI backends.

References

./references/data-stream.md -- AI SDK data stream format
./references/assistant-transport.md -- Native assistant-ui format
./references/encoders.md -- Encoders and decoders

When to Use

Using Vercel AI SDK?
├─ Yes → toUIMessageStreamResponse() (no assistant-stream needed)
└─ No → assistant-stream for custom backends

Installation

bash

npm install assistant-stream

Custom Streaming Response

import { createAssistantStreamResponse } from "assistant-stream";

export async function POST(req: Request) {
  return createAssistantStreamResponse(async (stream) => {
    stream.appendText("Hello ");
    stream.appendText("world!");

    // Tool call example
    const tool = stream.addToolCallPart({ toolCallId: "1", toolName: "get_weather" });
    tool.argsText.append('{"city":"NYC"}');
    tool.argsText.close();
    tool.setResponse({ result: { temperature: 22 } });

    stream.close();
  });
}

With useLocalRuntime

useLocalRuntime expects ChatModelRunResult chunks. Yield content parts for streaming:

tsx

import { useLocalRuntime } from "@assistant-ui/react";

const runtime = useLocalRuntime({
  model: {
    async *run({ messages, abortSignal }) {
      const response = await fetch("/api/chat", {
        method: "POST",
        body: JSON.stringify({ messages }),
        signal: abortSignal,
      });

      const reader = response.body?.getReader();
      const decoder = new TextDecoder();
      let buffer = "";

      while (reader) {
        const { done, value } = await reader.read();
        if (done) break;

        buffer += decoder.decode(value, { stream: true });
        const parts = buffer.split("\n");
        buffer = parts.pop() ?? "";

        for (const chunk of parts.filter(Boolean)) {
          yield { content: [{ type: "text", text: chunk }] };
        }
      }
    },
  },
});

Debugging Streams

import { AssistantStream, DataStreamDecoder } from "assistant-stream";

const stream = AssistantStream.fromResponse(response, new DataStreamDecoder());
for await (const event of stream) {
  console.log("Event:", JSON.stringify(event, null, 2));
}

Stream Event Types

part-start with part.type = "text" | "reasoning" | "tool-call" | "source" | "file"
text-delta with streamed text
result with tool results
step-start, step-finish, message-finish
error strings

Common Gotchas

Stream not updating UI

Check Content-Type is text/event-stream
Check for CORS errors

Tool calls not rendering

addToolCallPart needs both toolCallId and toolName
Register tool UI with makeAssistantToolUI

Partial text not showing

Use text-delta events for streaming

Files

SKILL.md and 3 other files (references) in .agents/skills/assistant-ui/assistant-ui-streaming of compozy/compozy.

SKILL.md
references/assistant-transport.md
references/data-stream.md
references/encoders.md

Open the folder on GitHubat commit c46be43

Compare with similar skills

Assistant UI Streaming next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Assistant UI Streaming compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Assistant UI Streaming this skillcompozy/compozy	2.8k	—	~813	Automated safety check: Pass	MIT	today
Trellis Session Insightmindfold-ai/Trellis	15k	4 repos	~1.7k	Automated safety check: Pass	AGPL-3.0	8 days ago
Native Data FetchingCherryHQ/cherry-studio-app	4k	6 repos	~2.9k	Automated safety check: Notes	MIT	4 days ago
Aoti Debugpytorch/pytorch	104k	1 repos	~1.7k	Automated safety check: Pass	Custom licence	today
Herdr Throwaway Reproductionherdrdev/herdr	43k	—	~2.4k	Automated safety check: Pass	Apache-2.0	today
Systematic Debuggingultralisp/ultralisp	258	51 repos	~2.4k	Automated safety check: Pass	None	24 days ago

Similar skills

Trellis Session Insight
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
15k GitHub starsUsed in 4 repos~1.7k tokens
DevelopmentAuto-check passed
Native Data Fetching
CherryHQ/cherry-studio-app
A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.
4k GitHub starsUsed in 6 repos~2.9k tokens
DevelopmentAuto-check: notes
Aoti Debug
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
104k GitHub starsUsed in 1 repo~1.7k tokens
DevelopmentAuto-check passed
Herdr Throwaway Reproduction
herdrdev/herdr
Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.
43k GitHub stars~2.4k tokensUpdated today
DevelopmentAuto-check passed
Systematic Debugging
ultralisp/ultralisp
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes
258 GitHub starsUsed in 51 repos~2.4k tokens
DevelopmentAuto-check passed
OpenLogi macOS Permissions Triage
AprilNEA/OpenLogi
Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.
23k GitHub stars~2.5k tokensUpdated 4 days ago
DevelopmentAuto-check: notes

Questions about Assistant UI Streaming

What does Assistant UI Streaming do?

Guide for assistant-stream package and streaming protocols. An agent skill from compozy/compozy. Assistant UI Streaming is an agent skill from compozy/compozy. Guide for assistant-stream package and streaming protocols.

When should I use Assistant UI Streaming?

Assistant UI Streaming fits situations like: implementing streaming backends; custom protocols; debugging stream issues.

How do I install Assistant UI Streaming in Claude Code?

Run `npx skills add compozy/compozy --skill assistant-ui-streaming -a claude-code`. Or copy the skill folder (.agents/skills/assistant-ui/assistant-ui-streaming in compozy/compozy) into .claude/skills/assistant-ui-streaming in your project. Claude Code loads it when a task matches its description.

How do I install Assistant UI Streaming in Codex?

Run `npx skills add compozy/compozy --skill assistant-ui-streaming -a codex`. Or copy the skill folder (.agents/skills/assistant-ui/assistant-ui-streaming in compozy/compozy) into .agents/skills/assistant-ui-streaming in your project. Codex loads it when a task matches its description.

Can I use Assistant UI Streaming in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add compozy/compozy --skill assistant-ui-streaming -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/assistant-ui-streaming, .gemini/skills/assistant-ui-streaming, .github/skills/assistant-ui-streaming and .opencode/skills/assistant-ui-streaming in your project.

What does Assistant UI Streaming need to run?

Going by SKILL.md and its folder, Assistant UI Streaming needs the command-line tools its instructions call (npm). Our summary lists: Node.js.

Does Assistant UI Streaming access the network?

SKILL.md names 1 domain. As links in the text: assistant-ui.com. This is read from the text; nothing was executed.

Is Assistant UI Streaming safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Assistant UI Streaming use?

Assistant UI Streaming is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Assistant UI Streaming use?

About 813 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.9k tokens, read only when the agent opens those files.

What are the alternatives to Assistant UI Streaming?

Skills that share tags, products or a category with Assistant UI Streaming: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Aoti Debug (pytorch/pytorch, 104k stars) and Herdr Throwaway Reproduction (herdrdev/herdr, 43k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Assistant UI Streaming?

compozy (a GitHub organization) maintains it in compozy/compozy, which has 2,791 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on October 7, 2026.

Source: compozy/compozy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Assistant UI Streaming

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

assistant-ui Streaming

References

When to Use

Installation

Custom Streaming Response

With useLocalRuntime

Debugging Streams

Stream Event Types

Common Gotchas

Files

Compare with similar skills

Similar skills

More from compozy/compozy

Related

Questions about Assistant UI Streaming