openui-forge-anthropic
installsforks
How to install openui-forge-anthropic?
othmanadi/openui-forge/openui-forge-anthropic
$npx -y skills add OthmanAdi/openui-forge --skill openui-forge-anthropicOpenUI generative UI with Anthropic Claude SDK backend. Stream conversion to OpenAI NDJSON format.
SKILL.md
| 1 | # OpenUI Forge — Anthropic |
| 2 | |
| 3 | Build generative UI apps with OpenUI + Anthropic Claude. Converts Anthropic streaming events to OpenAI-compatible NDJSON. |
| 4 | |
| 5 | ## Activation Triggers |
| 6 | |
| 7 | - "openui anthropic", "openui claude", "openui sonnet" |
| 8 | - "generative ui claude", "claude streaming ui" |
| 9 | |
| 10 | ## Prerequisites |
| 11 | |
| 12 | - Node.js >= 22 (24 LTS recommended), React >= 18.3.1 (19+ recommended) |
| 13 | - `ANTHROPIC_API_KEY` environment variable set |
| 14 | - Next.js project (App Router recommended) |
| 15 | |
| 16 | ## Quick Start |
| 17 | |
| 18 | 1. Install dependencies: |
| 19 | ```bash |
| 20 | npm install @openuidev/react-ui @openuidev/react-headless @openuidev/react-lang lucide-react zod @anthropic-ai/sdk |
| 21 | ``` |
| 22 | 2. Add the CSS import to `app/layout.tsx`: |
| 23 | ```tsx |
| 24 | import "@openuidev/react-ui/components.css"; |
| 25 | ``` |
| 26 | 3. Create the API route and frontend page below |
| 27 | 4. Run `npm run dev` and test |
| 28 | |
| 29 | ## Full Code |
| 30 | |
| 31 | ### Backend: `app/api/chat/route.ts` |
| 32 | |
| 33 | The backend streams from Anthropic and converts each event into OpenAI-compatible SSE chunks that `openAIAdapter()` expects (`data: {json}\n\n` lines, terminated by `data: [DONE]`). |
| 34 | |
| 35 | ```typescript |
| 36 | import { openuiChatLibrary } from "@openuidev/react-ui/genui-lib"; |
| 37 | import Anthropic from "@anthropic-ai/sdk"; |
| 38 | |
| 39 | const client = new Anthropic(); |
| 40 | |
| 41 | export async function POST(req: Request) { |
| 42 | const { messages } = await req.json(); |
| 43 | |
| 44 | const systemPrompt = openuiChatLibrary.prompt({ |
| 45 | preamble: "You are a helpful assistant that generates interactive UIs.", |
| 46 | additionalRules: ["Always use Stack as root when combining multiple components."], |
| 47 | }); |
| 48 | |
| 49 | // ANTHROPIC_MODEL alternatives: claude-opus-4-8, claude-haiku-4-5, claude-fable-5 |
| 50 | const stream = client.messages.stream({ |
| 51 | model: process.env.ANTHROPIC_MODEL ?? "claude-sonnet-4-6", |
| 52 | max_tokens: 4096, |
| 53 | system: systemPrompt, |
| 54 | messages, |
| 55 | }); |
| 56 | |
| 57 | const encoder = new TextEncoder(); |
| 58 | const readableStream = new ReadableStream({ |
| 59 | async start(controller) { |
| 60 | const id = `chatcmpl-${Date.now()}`; |
| 61 | for await (const event of stream) { |
| 62 | if ( |
| 63 | event.type === "content_block_delta" && |
| 64 | event.delta.type === "text_delta" |
| 65 | ) { |
| 66 | const chunk = { |
| 67 | id, |
| 68 | object: "chat.completion.chunk", |
| 69 | choices: [ |
| 70 | { |
| 71 | index: 0, |
| 72 | delta: { content: event.delta.text }, |
| 73 | finish_reason: null, |
| 74 | }, |
| 75 | ], |
| 76 | }; |
| 77 | controller.enqueue( |
| 78 | encoder.encode(`data: ${JSON.stringify(chunk)}\n\n`) |
| 79 | ); |
| 80 | } |
| 81 | } |
| 82 | const done = { |
| 83 | id, |
| 84 | object: "chat.completion.chunk", |
| 85 | choices: [{ index: 0, delta: {}, finish_reason: "stop" }], |
| 86 | }; |
| 87 | controller.enqueue(encoder.encode(`data: ${JSON.stringify(done)}\n\n`)); |
| 88 | controller.enqueue(encoder.encode("data: [DONE]\n\n")); |
| 89 | controller.close(); |
| 90 | }, |
| 91 | }); |
| 92 | |
| 93 | return new Response(readableStream, { |
| 94 | headers: { "Content-Type": "text/event-stream" }, |
| 95 | }); |
| 96 | } |
| 97 | ``` |
| 98 | |
| 99 | ### Frontend: `app/chat/page.tsx` |
| 100 | |
| 101 | ```tsx |
| 102 | "use client"; |
| 103 | import { FullScreen } from "@openuidev/react-ui"; |
| 104 | import { openuiChatLibrary } from "@openuidev/react-ui/genui-lib"; |
| 105 | import { |
| 106 | openAIAdapter, |
| 107 | openAIMessageFormat, |
| 108 | } from "@openuidev/react-headless"; |
| 109 | |
| 110 | export default function ChatPage() { |
| 111 | return ( |
| 112 | <FullScreen |
| 113 | componentLibrary={openuiChatLibrary} |
| 114 | streamProtocol={openAIAdapter()} |
| 115 | messageFormat={openAIMessageFormat} |
| 116 | apiUrl="/api/chat" |
| 117 | /> |
| 118 | ); |
| 119 | } |
| 120 | ``` |
| 121 | |
| 122 | > The backend emits SSE (`data: {json}\n\n`). Pair it with `openAIAdapter()` on the frontend — `openAIReadableStreamAdapter()` is for NDJSON (no `data:` prefix) and will silently produce no output here. |
| 123 | |
| 124 | ## Component Creation |
| 125 | |
| 126 | ```tsx |
| 127 | import { defineComponent } from "@openuidev/react-lang"; |
| 128 | import { z } from "zod"; |
| 129 | |
| 130 | export const StatusCard = defineComponent({ |
| 131 | name: "StatusCard", |
| 132 | description: "Displays a status with label and color indicator", |
| 133 | props: z.object({ |
| 134 | label: z.string().describe("Status label text"), |
| 135 | status: z.enum(["ok", "warning", "error"]).describe("Current status level"), |
| 136 | }), |
| 137 | component: ({ props }) => { |
| 138 | const colors = { ok: "#22c55e", warning: "#eab308", error: "#ef4444" }; |
| 139 | return ( |
| 140 | <div style={{ display: "flex", alignItems: "center", gap: 8 }}> |
| 141 | <span style={{ width: 10, height: 10, borderRadius: "50%", background: colors[props.status] }} /> |
| 142 | <span>{props.label}</span> |
| 143 | </div> |
| 144 | ); |
| 145 | }, |
| 146 | }); |
| 147 | ``` |
| 148 | |
| 149 | ## System Prompt Generation |
| 150 | |
| 151 | ```bash |
| 152 | npx @openuidev/cli generate ./src/lib/library.ts --out src/generated/system-prompt.txt |
| 153 | ``` |
| 154 | |
| 155 | Or at runtime: `openuiChatLibrary.prompt({ preamble: "...", additionalRules: [...] })`. |
| 156 | |
| 157 | ## Validation Checklist |
| 158 | |
| 159 | - [ ] `ANTHROPIC_API_KEY` is set in `.env.local` |
| 160 | - [ ] CSS import present in root layout |
| 161 | - [ ] Backend converts Anthropic `content_block_delta` events to OpenAI-compatible SSE |
People who liked this also viewed
6 picksType
- web-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".SkillsJul 2026
- lark-slides飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 SkillsJul 2026
- design-taste-frontendTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop SkillsJul 2026
- ui-ux-pro-maxUI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presSkillsJul 2026
- caveman-helpQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".SkillsJul 2026
- codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-nSkillsJul 2026
