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 agentmods add skills/liozshor/claude-code-skills/visualizenpx skills add LiozShor/claude-code-skills --skill visualizegit clone --depth 1 https://github.com/LiozShor/claude-code-skillsWrote 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/liozshor/claude-code-skills/visualize)<a href="https://agentmods.dev/skills/liozshor/claude-code-skills/visualize"><img src="https://agentmods.dev/badge/skills/liozshor/claude-code-skills/visualize.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00158 | $0.04466 |
| Opus 5 | $0.00079 | $0.02233 |
| Sonnet 5 | $0.00032 | $0.00893 |
| Haiku 4.5 | $0.00016 | $0.00447 |
Grade A, and why
visualize scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}\n" http://127.0.0.1:8899/<name>.html # expect 200 How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize
Turn any idea, data, or content into a stunning single-file HTML visualization.
This SKILL.md is the operational layer. Detailed patterns live in references/ and are loaded
on demand — see the Reference map at the bottom. Never inline that detail here.
When this triggers
- User says "visualize," "make a deck/slide/dashboard/infographic/poster/carousel," or any visualization-type keyword.
- User pastes data (CSV, JSON, table, numbers) and wants it shown visually.
- User shares a URL and asks for a visual summary.
- User wants a single self-contained
.htmlartifact (no server, no build step).
When this does not trigger
- Figma / mockup / design-system work →
figma-generate-design,figma-use. - Tally form / questionnaire →
tally. - Canva file →
canva-*tools. - Real multi-page website, React/Vue/Next app → not a skill match; build with framework.
- Screenshotting or scraping an existing webpage →
agent-browser. - Editing an existing HTML file the user already has → use plain
Edit.
Required inputs
- The content to visualize (conversation context, pasted data, URL, or explicit description).
- If the visualization renders options for something that already exists (a screen, component, loader, nav, card, color scheme, layout in the user's product) — the actual current implementation. Go read it before writing any HTML. See Ground in the current implementation.
- Optional: visualization type (deck, dashboard, infographic, etc.) — infer if not given.
- Optional: output path (defaults to
~/Downloads/<kebab-case-name>.html).
Workflow
- Pick type. Match the request to a row in the Visualization Types table below. If ambiguous, pick the closest fit and proceed. Detailed per-type patterns: references/types.md.
- Ground in the current implementation — before writing a single line of HTML. If the thing being visualized already exists anywhere (a screen, component, loader, nav, card, palette, layout in the user's product), go find and read the real code, and render the options in that design — not an invented one. Mandatory, no exceptions: see Ground in the current implementation.
- Gather content. Use the conversation context, pasted data, or
WebFetchfor URLs (see Source content). Never use placeholder/Lorem ipsum. - Copy skeleton. Start from references/skeleton.md — never write HTML from scratch. It carries the theme system, exact CSS-property names, menu, animations, print styles, and accessibility hooks the evaluator checks.
- Add content to the
<!-- YOUR CONTENT HERE -->block. Follow the type-specific rules in references/types.md. - Wire libraries as needed — references/libraries.md for CDN URLs + the Chart.js / Reveal.js / Leaflet patterns, references/menu.md for the required hamburger menu, references/animations.md for entrance/scroll animation, references/design-system.md for typography/color/spacing/sizing, references/css-techniques.md for advanced CSS.
- Run the Evaluation checklist below before saving.
- Write the file with
Writeto~/Downloads/<name>.html(kebab-case). - Serve it over localhost, then open it. See Serving and verifying —
file://silently breaks the clipboard export and cannot be inspected with Playwright. Serve the containing directory, open thehttp://127.0.0.1:<port>/<name>.htmlURL, and return that URL in the response. - Verify in the browser before claiming it works. Load the localhost URL with Playwright, check console errors, confirm no horizontal overflow at 375px, and smoke-test the main interaction. Never report a visualization as done on the strength of the HTML source alone.
What ships with it
13 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.
- evals/01-positive-trigger.json 615 B
- evals/02-negative-trigger.json 719 B
- evals/03-edge-case-url-crawl.json 796 B
- references/animations.md 7.3 KB
- references/anthropic-skill-guide-notes.md 1.7 KB
- references/css-techniques.md 31 KB
- references/design-system.md 31 KB
- references/eval.md 2.4 KB
- references/libraries.md 13 KB
- references/menu.md 9.8 KB
- references/pick-and-extract.md 5.9 KB
- references/skeleton.md 16 KB
- references/types.md 18 KB
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.
- 4d ago First seen · 253 lines · 158 tokens per session scan A 77c64b7b8410
visualize is a skill published in the GitHub repository LiozShor/claude-code-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 158 tokens to every session and 4,466 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
feishu-cli-visual
飞书可视化与展示统一入口,负责选择合适载体,并覆盖画板、Slides、妙笔BOX 动态组件、 妙搭 HTML 应用和统一数据可视化设计规范。用户要求画板/whiteboard、架构图、流程图、飞轮、 鱼骨、路线图、海报、插画、SVG/Mermaid、数据图表或 dashboard,创建 Slides/PPT,嵌入会动的 ECharts/地图/3D/window.magic 组件,或用妙搭/Miaoda/spark 发布 HTML 应用时必须使用本 Skill。 消息卡片由 feishu-cli-messaging 构造和发送;Markdown 图表导入由 feishu-cli-docs 执行。.
render-vo-anchored-motion-listicle
Assemble an expert/educator motion-graphic LISTICLE video ad from a config — a spoken authoritative voiceover carries a numbered listicle while N web-animated hyperframe beats (HTML plus the Web Animations API, one branded design system of alternating tiles, big hero numerals, and glass-pill callouts) are rendered…
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
frame-bold-signal
Bold colored card on a dark gradient — big section number, nav breadcrumb, orange card sliding in, title rising.