Turn an answer into a light visual (flowchart, timeline, comparison, architecture sketch), in any language. Trigger ONLY on an explicit ask: "show me", "visualize this", "draw it", «با شکل نشون بده». Never just because the content is flow-shaped.
Installs into .claude/skills of the current project.
Are you the author of Visualize?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/smk-labs-visualize)
---
name: visualize
description: >-
Turn an answer into a light visual (flowchart, timeline, comparison, architecture sketch), in
any language. Trigger ONLY on an explicit ask: "show me", "visualize this", "draw it", «با شکل
نشون بده». Never just because the content is flow-shaped.
---
# visualize: a shape, only when it says it better
Render ONE light visual with `mcp__visualize__show_widget`. If this is the first widget of the session, call `mcp__visualize__read_me` first (silently) with the closest module (`diagram` for flows and structures, `chart` for data).
Rules:
- SVG first. HTML only for metric cards or side-by-side comparisons.
- Light: a few dozen elements at most, one idea per visual. If it needs more, split it into two visuals or stay in text.
- Colors: only the theme's CSS variables and ramp classes (`c-gray`, `c-purple`, `c-teal`, `c-coral`). Never raw hex that breaks dark mode. 2-3 colors, gray for structural nodes, color only where it encodes meaning.
- Labels stay short (under 5 words). Explanations belong in the chat text, never inside the visual.
- Persian/RTL labels: set `direction="rtl"` on RTL `<text>` elements and keep Latin tokens out of them. Latin-only labels stay LTR.
- If the current reply is already a Persian `<md>` card (readable's RTL hook), embed the visual as a small inline `<svg>` inside that markdown instead of a second widget call.
- Never force it: if no shape genuinely helps, say so and answer in text. This skill runs on explicit request only.
