metis: Skill for Claude Code

.claude/skills/20-interactive-widgets/SKILL.md

interactive-widgets is a skill for Claude Code from terrene-foundation/metis. It costs 73 tokens per session (921 once invoked), scanned A, original, Apache-2.0.

A collection of patterns for building AI interfaces with interactive widgets instead of text alone. These widgets can include generated components, forms, streamed structured responses and actions that return results.

In plain words
What is it for?
Use it when designing a widget protocol, generating forms from AI responses, streaming structured components, rendering widgets in the browser, handling widget events, or managing their state and errors.
Why use it?
It gives developers a way to design how an AI backend describes interface elements and how a front end displays and handles them. This avoids inventing a separate approach for every dynamic AI screen.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is terrene-foundation/metis's own configuration. It tells Claude Code how to work on metis itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything metis configures →

Reuse

Borrowing it

Nothing to install: this file belongs to terrene-foundation/metis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/terrene-foundation/metis/main/.claude/skills/20-interactive-widgets/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/metis

Made for: Claude Code.

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 interactive-widgets

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrene-foundation/metis/20-interactive-widgets.svg)](https://agentmods.dev/skills/terrene-foundation/metis/20-interactive-widgets)
Your own site
<a href="https://agentmods.dev/skills/terrene-foundation/metis/20-interactive-widgets"><img src="https://agentmods.dev/badge/skills/terrene-foundation/metis/20-interactive-widgets.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 921 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 $0.00073 $0.00921
Opus 5 $0.00036 $0.00461
Sonnet 5 $0.00015 $0.00184
Haiku 4.5 $0.00007 $0.00092

Measured 8d ago against content hash ecfc4cd19ec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

interactive-widgets 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 8d 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.

.claude/skills/20-interactive-widgets/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interactive Widget System

Production-ready patterns for building interactive widget systems that integrate with AI/LLM backends for dynamic, structured user interfaces.

Overview

Interactive widget patterns for:

  • LLM-driven widget generation
  • Streaming response with structured components
  • Dynamic form builders
  • Action-response patterns
  • Widget protocol design

Reference Documentation

System Overview

  • overview - Widget system architecture and navigation
    • System components
    • Documentation structure
    • Quick reference

Technical Specification

  • technical-spec - Complete technical specification
    • Widget protocol design
    • Backend integration
    • Frontend rendering
    • State management
    • Error handling

Implementation Guide

  • implementation-guide - Step-by-step implementation
    • Backend widget generation
    • Frontend widget rendering
    • Event handling
    • Real-world examples

Quick Patterns

Widget Protocol (JSON)

{
  "type": "form",
  "id": "user-input-form",
  "content": {
    "fields": [
      {
        "type": "text",
        "name": "query",
        "label": "Enter your question",
        "required": true
      }
    ],
    "actions": [
      {
        "type": "submit",
        "label": "Send",
        "action": "submit_query"
      }
    ]
  }
}

Backend Widget Generation (Python)

def generate_widget_response(user_query: str) -> dict:
    """Generate structured widget response from LLM."""
    response = llm.generate(
        prompt=f"Generate a widget response for: {user_query}",
        output_schema=WidgetSchema
    )
    return {
        "type": response.widget_type,
        "content": response.content,
        "actions": response.available_actions
    }

Frontend Widget Renderer (Dart)

Widget buildWidget(Map<String, dynamic> widgetData) {
  switch (widgetData['type']) {
    case 'form':
      return FormWidget(data: widgetData['content']);
    case 'card':
      return CardWidget(data: widgetData['content']);
    case 'table':
      return TableWidget(data: widgetData['content']);
    default:
      return TextWidget(data: widgetData['content']);
  }
}

Read the full file on GitHub · 142 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 142 lines · 73 tokens per session scan A ecfc4cd19ec2

Subscribe to this mod's changes

interactive-widgets is a skill published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 921 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

chakra-ui-builder

Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…

chakra-ui/chakra-ui · 214 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 50 tokens

frontend-visual-qa

Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…

daymade/claude-code-skills · 145 tokens

prototype-web

A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.

nexu-io/html-anything · 24 tokens

animation-principles

Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.

Owl-Listener/designer-skills · 59 tokens

refactoring-ui

Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…

wondelai/skills · 132 tokens