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 Kocoro-lab/Kocoro --skill kocoro-generative-uigit clone --depth 1 https://github.com/Kocoro-lab/KocoroWrote 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/kocoro-lab/kocoro/kocoro-generative-ui)<a href="https://agentmods.dev/skills/kocoro-lab/kocoro/kocoro-generative-ui"><img src="https://agentmods.dev/badge/skills/kocoro-lab/kocoro/kocoro-generative-ui/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/kocoro-lab/kocoro/kocoro-generative-ui"><img src="https://agentmods.dev/badge/skills/kocoro-lab/kocoro/kocoro-generative-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 71 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 | $0.00082 | $0.02640 |
| Opus 5 | $0.00041 | $0.01320 |
| Sonnet 5 | $0.00016 | $0.00528 |
| Haiku 4.5 | $0.00008 | $0.00264 |
Grade A, and why
kocoro-generative-ui 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 10d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kocoro Generative UI
You produce rich visual content — SVG diagrams and HTML interactive widgets — that renders inline in the Kocoro Desktop conversation, token-by-token, in a WKWebView sandbox.
Channel availability: This skill is only exposed to the LLM on Desktop / TUI / direct API paths. The Kocoro daemon suppresses it on cloud-distributed channels (Feishu, Lark, WeCom, Slack, LINE, Telegram, webhook) because their clients render markdown but not html-artifact fences — see
internal/daemon/skill_filter.go(desktopOnlySkills).
Output Contract
Wrap every widget in a markdown fenced code block with info string
html-artifact:
```html-artifact title="Q1 revenue" id=art_a1 mime=text/html
<style>.bar{background:var(--color-background-info)}</style>
<h2 class="sr-only">Bar chart of Q1 revenue across three regions</h2>
<div style="position:relative;height:240px"><canvas id="c1"></canvas></div>
<script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.js"></script>
<script>
new Chart(document.getElementById('c1'), { /* ... */ });
</script>
```
title— required; shown to the user and used as export filename stemid— optional; if absent, host generates a UUIDmime—text/html(default) orimage/svg+xmltheme—auto(default),light, ordark- The content is a fragment. Do NOT write
<!DOCTYPE>,<html>,<head>,<body>— the host wraps them. - Explanatory prose goes OUTSIDE the fence, in your normal reply.
- Max 3 artifacts per reply.
- When you need to show the user the fence syntax itself (e.g., teaching this feature), insert a zero-width space (U+200B) between the backticks in the example: ```html-artifact. This prevents your example from being captured as a real artifact.
Streaming Safety
Output streams token-by-token. Structure code so useful content appears early and the script tag last:
- HTML:
<style>(short) → content HTML →<script>last. Scripts execute after the fence closes, not during streaming. - SVG:
<defs>(markers) → visual elements. - Avoid gradients, shadows, blur — they flash during streaming DOM diffs. Use solid flat fills.
- No
<!-- HTML comments -->or/* CSS comments */. They waste tokens and may land mid-stream in ways that confuse rendering.
What ships with it
5 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.
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.
- 10d ago First seen · 232 lines · 82 tokens per session scan A c9558557f97f
kocoro-generative-ui is a skill published in the GitHub repository Kocoro-lab/Kocoro (408 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 2,640 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 2026-08-30.
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…
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.
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…
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.
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.
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…