CopilotKit/OpenGenerativeUI is an open-source showcase for AI-generated user interfaces, where an agent creates live interactive HTML and SVG visualizations instead of returning only text. It is used to build algorithm demonstrations, 3D scenes, charts, diagrams, forms, simulations, and mathematical plots rendered in sandboxed iframes. The catalogue skills and instruction support working with this generative UI project.
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.
npx skills add CopilotKit/OpenGenerativeUI --skill advanced-visualizationgit clone --depth 1 https://github.com/CopilotKit/OpenGenerativeUIWrote 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.
[](https://agentmods.dev/skills/copilotkit/opengenerativeui/advanced-visualization)<a href="https://agentmods.dev/skills/copilotkit/opengenerativeui/advanced-visualization"><img src="https://agentmods.dev/badge/skills/copilotkit/opengenerativeui/advanced-visualization/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.
<a href="https://agentmods.dev/skills/copilotkit/opengenerativeui/advanced-visualization"><img src="https://agentmods.dev/badge/skills/copilotkit/opengenerativeui/advanced-visualization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 129 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 380 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.08460 |
| Opus 5.5 | $0.00015 | $0.03384 |
| Sonnet 5.5 | $0.00007 | $0.01692 |
| Haiku 4.5 | $0.00004 | $0.00846 |
Grade A, and why
Advanced Visualization Techniques 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 963 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Visualization Skills — Volume 2: Advanced Techniques
Prerequisite: Volume 1 (SVG diagrams, basic interactive widgets, Chart.js, Mermaid). This volume covers: UI mockups, dashboards, advanced interactivity, generative art, simulations, math visualizations, and the design system that ties everything together.
Part 0: The Tool Contract — generateSandboxedUi
Everything in this volume ships through the generateSandboxedUi tool. The UI
streams as you generate it, so emit the parameters in this EXACT order:
initialHeight— estimated height of the finished UI in px.placeholderMessages— 2-4 short, playful progress messages.css— ALL styles, up front. The user sees a placeholder until css is complete, so keep it lean and put every style here for the css-first reveal.html— clean body markup, streamed in live. No<style>blocks (the css parameter owns all styles), no monolithic inline<script>blocks.jsFunctions— named function declarations: the reusable toolbox of behavior.jsExpressions— small statements invoking those functions, applied one-by-one so the user watches each take effect.
Write parameterized generators in jsFunctions (drawWing(color), not
drawRedWing()). A well-parameterized toolbox lets a later refinement turn —
"make the wings red" — append ONE new expression to jsExpressions instead of
regenerating the whole document.
The sandbox iframe has NO same-origin access: no localStorage, sessionStorage,
cookies, IndexedDB, or same-origin fetch. The host bridge is
await Websandbox.connection.remote.sendPrompt({ text }) and
await Websandbox.connection.remote.openLink({ url }) (https only). The design
system (Part 1) and an importmap for three, gsap, d3, and chart.js
(Part 7) are pre-injected.
Part 1: The Design System
Every visual you produce should feel native to the host interface — not like an embedded iframe from somewhere else. These rules apply to ALL output types.
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.
- 1mo ago First seen · 963 lines · 37 tokens per session scan A b134d0b46656
Advanced Visualization Techniques is a skill published in the GitHub repository CopilotKit/OpenGenerativeUI (1,591 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 8,460 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
Advanced Visualization Techniques
UI mockups, dashboards, advanced interactivity, generative art, simulations, math visualizations, and design system rules for producing rich HTML widget output.
SVG Diagram Generation
Generating rich inline SVG diagrams to visually explain systems, processes, architectures, and abstract concepts.
Master Agent Playbook
Philosophy, decision-making framework, and technical skills for delivering visual, interactive, and educational AI responses.
paperclip-capsules
Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.
sage-review
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.
design-critique
Run a heuristic evaluation of a UI design (image, HTML, Figma, URL, or flow) the way an experienced designer would. Evaluates 4 categories (Visual & hierarchy, Usability & interaction, Accessibility, Content) using recognized frameworks, NN/g 0-4 severity, and evaluability-aware prioritization that never judges what…