ephemeral-generative-ui-architect

ephemeral-generative-ui-architect is a skill for Claude Code, Codex from roedyrustam/vibes-plug. It costs 74 tokens per session (1,668 once invoked), scanned A, original, MIT.

A design guide for interfaces that an AI generates and streams while a user interacts with it, using React Server Components, which render parts of a web page on the server.

In plain words
What is it for?
Use it to plan AI-driven chat interfaces, map AI tool calls to React components, and stream temporary interactive widgets through the Vercel AI SDK.
Why use it?
It helps when a fixed screen is not enough and the interface should change with the user's request or data. It focuses on showing interactive charts, forms, and dashboards rather than only text.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan AI-driven chat interfaces, map AI tool calls to React components, and stream temporary interactive widgets through the Vercel AI SDK.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/roedyrustam/vibes-plug/ephemeral-generative-ui-architect
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add roedyrustam/vibes-plug --skill ephemeral-generative-ui-architect
Clone the repo
git clone --depth 1 https://github.com/roedyrustam/vibes-plug

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ephemeral-generative-ui-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/ephemeral-generative-ui-architect/github.svg)](https://agentmods.dev/skills/roedyrustam/vibes-plug/ephemeral-generative-ui-architect)
Your own site
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/ephemeral-generative-ui-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/ephemeral-generative-ui-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ephemeral-generative-ui-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/ephemeral-generative-ui-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/ephemeral-generative-ui-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.01668
Opus 5.5 $0.00030 $0.00667
Sonnet 5.5 $0.00015 $0.00334
Haiku 4.5 $0.00007 $0.00167

Measured 7d ago against content hash e1bd3c947758, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ephemeral-generative-ui-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ephemeral-generative-ui-architect/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ephemeral Generative UI Architect (2026 Edition)

English | Bahasa Indonesia


English

Orchestration & Integration

Connects and orchestrates with vercel-ai-sdk-expert, senior-frontend, ui-ux-pro-max, design-system-architect, gemini-agent-booster, and multi-agent-orchestration.

Description

Standard UIs are static and pre-compiled. In the Gemini 4 Pro era, interfaces are ephemeral: generated in real-time based on the user's immediate intent, and destroyed when no longer needed. This skill orchestrates Generative UI systems using React Server Components (RSC), Tool-Driven UI injection, and Vercel AI SDK, allowing LLMs to directly stream fully functional, interactive components (charts, forms, dashboards) instead of markdown text.

Trigger Conditions

  • The user requests an interface that adapts entirely to the data context (e.g., "Show me a dashboard of my spending" -> AI generates a custom chart component on the fly).
  • Designing AI-native chat interfaces that render interactive widgets (booking forms, map components) instead of plain text responses.
  • Integrating Vercel AI SDK streamUI or tool-call-to-component mappings.

Core Architecture (2026 Standard)

  1. Tool-to-UI Mapping: The AI decides to call a tool (e.g., getWeather). The server intercepts this tool call and streams a <WeatherWidget /> React Server Component directly to the client.
  2. Zero-Client-State (Ephemeral): The UI state exists only within the LLM conversation history. If the chat resets, the UI resets.
  3. Optimistic Rendering: The client immediately renders a loading skeleton (e.g., <WeatherSkeleton />) the millisecond the LLM begins emitting the tool call token, replaced by the final RSC once execution completes.

Sovereign Visual Hierarchy in Ephemeral UI

Even when rendered dynamically on-the-fly, AI-generated components MUST strictly observe Sovereign Visual Hierarchy:

  1. Container Grounding: Wrap streamed widgets in Level 1 Surface containers (bg-white dark:bg-neutral-900 border border-neutral-200/80 dark:border-neutral-800 rounded-xl shadow-xs).
  2. Typographic Rhythm: Eyebrow badge (text-[11px] font-semibold uppercase tracking-wider text-neutral-500) -> Title (text-lg font-semibold tracking-tight text-neutral-900 dark:text-neutral-50) -> Body (text-sm text-neutral-600 dark:text-neutral-300).
  3. Tabular Numerals: Enforce tabular-nums on all streaming counters, prices, metrics, and telemetry stats.
  4. Single Primary CTA: Exactly one primary action per streamed card (e.g., "Confirm Booking"); secondary options use subtle ghost styling.

Read the full file on GitHub · 101 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago Changed e1bd3c947758
  2. 9d ago Changed · +12 lines b4cbc8d9eb9a
  3. 12d ago Changed 3e753e544b4f
  4. 13d ago Changed 361ab0ad4888
  5. 15d ago Changed 29823855b32d
  6. 17d ago First seen · 89 lines · 74 tokens per session scan A 18d98348c3dd

Subscribe to this mod's changes

ephemeral-generative-ui-architect is a skill published in the GitHub repository roedyrustam/vibes-plug (75 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,668 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.

Related

Other skills, from other repositories

shadcnui

Expert shadcn/ui assistance covering Radix UI primitives, Tailwind CSS styling, copy-paste architecture, and accessibility. Use when building modern React component systems and accessible design systems.

G1Joshi/Agent-Skills · 42 tokens

chakraui

Expert Chakra UI assistance covering accessible React components, theme tokens, style props, and dark mode. Use when building modular, accessible React component libraries and dashboards.

G1Joshi/Agent-Skills · 34 tokens

materialui

Expert Material UI (MUI) assistance covering Emotion styled components, theme customization, DataGrid, and accessible icons. Use when building React enterprise dashboards with Google's Material Design.

G1Joshi/Agent-Skills · 37 tokens

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

lingxling/awesome-skills-cn · 64 tokens

antigravity-design-expert

Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.

lingxling/awesome-skills-cn · 39 tokens

antigravity-design-expert

Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.

sickn33/agentic-awesome-skills · 39 tokens