How do I install the AI Visual skill?

Run npx skillmds@latest add arcasilesgroup/ai-visual in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is AI Visual safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with AI Visual?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is AI Visual free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published AI Visual?

arcasilesgroup (@arcasilesgroup) published this skill. Their other Agent Skills are listed on their SkillMD profile.

AI Visual by arcasilesgroup — Agent Skill

Name: AI Visual
Author: arcasilesgroup

AI Visual

Produces static visual design artifacts (posters, banners, flyers, branding, cover art, identity compositions) by composing named aesthetic philosophies into HTML/SVG, rendered to PDF/PNG. Trigger for 'create a poster', 'design a banner', 'branding visual', 'cover art for', 'identity composition'. Not for UI interfaces; use /ai-design instead. Not for animation; use /ai-animation instead. Not for presentation decks; use /ai-slides instead. Not for AI-generated photographs; use /ai-media instead.

arcasilesgroup e1c7c3c 4 files · 10.9 KB Updated Sep 17, 2026

File contents

Visual

Static visual artifacts: generate a custom, named design philosophy, then express it as 90% visual / 10% essential text. User input is foundation, not constraint.

Workflow

Applies §10.1 KISS (restraint; polish what exists over adding graphics) and §10.7 Clean Code (every spacing, color, alignment is deliberate craft).

Understand the brief — purpose, audience, feeling to evoke.
Load handlers/philosophy.md; create + name a design movement (1-2 words, e.g. "Brutalist Joy", "Chromatic Silence").
Articulate the philosophy (4-6 paragraphs): space/form, color/material, scale/rhythm, composition/balance, visual hierarchy.
Load handlers/canvas-creation.md; apply visual standards + craftsmanship rules.
Deduce the subtle reference — embed conceptual threads within the art (sophisticated for those who know the subject, masterful abstract composition for others). Never announce it.
Create the canvas — 90% visual, 10% essential text.
Self-review — museum/magazine bar? If not, refine. Consult handlers/examples.md for inspiration.

Output rules:

Mode	Rule
Render	Self-contained HTML -> PDF (browser print / Puppeteer); SVG for vector output.
Refine	Polish existing elements only — no new graphics/functions/shapes; make composition more cohesive.
Multi-page	One philosophy, distinct variation per page; bundle as one PDF or multiple PNGs; pages tell a story.

Common Mistakes

Generic stock-photo aesthetics instead of a named philosophy.
Announcing the conceptual reference instead of embedding it subtly.

Integration

Called by: user directly, /ai-design, /ai-media. Consumed by: /ai-slides (aesthetic philosophy), /ai-media (visual direction). Calls: none — produces final artifacts. See also: /ai-design (UI), /ai-animation (motion).

Examples

/ai-visual event poster for Edge Runtime 2026 developer conference

Names a movement (e.g. "Brutalist Compute"), articulates philosophy across space/color/composition, and renders an HTML->PDF poster at 90% visual / 10% text.

$ARGUMENTS

---name: ai-visualdescription: Produces static visual design artifacts (posters, banners, flyers, branding, cover art, identity compositions) by composing named aesthetic philosophies into HTML/SVG, rendered to PDF/PNG. Trigger for 'create a poster', 'design a banner', 'branding visual', 'cover art for', 'identity composition'. Not for UI interfaces; use /ai-design instead. Not for animation; use /ai-animation instead. Not for presentation decks; use /ai-slides instead. Not for AI-generated photographs; use /ai-media instead.---# VisualStatic visual artifacts: generate a custom, named design philosophy, then express it as 90% visual / 10% essential text. User input is foundation, not constraint.## WorkflowApplies §10.1 KISS (restraint; polish what exists over adding graphics) and §10.7 Clean Code (every spacing, color, alignment is deliberate craft).1. Understand the brief — purpose, audience, feeling to evoke.2. Load `handlers/philosophy.md`; create + name a design movement (1-2 words, e.g. "Brutalist Joy", "Chromatic Silence").3. Articulate the philosophy (4-6 paragraphs): space/form, color/material, scale/rhythm, composition/balance, visual hierarchy.4. Load `handlers/canvas-creation.md`; apply visual standards + craftsmanship rules.5. Deduce the subtle reference — embed conceptual threads within the art (sophisticated for those who know the subject, masterful abstract composition for others). Never announce it.6. Create the canvas — 90% visual, 10% essential text.7. Self-review — museum/magazine bar? If not, refine. Consult `handlers/examples.md` for inspiration.Output rules:| Mode | Rule || --- | --- || Render | Self-contained HTML -> PDF (browser print / Puppeteer); SVG for vector output. || Refine | Polish existing elements only — no new graphics/functions/shapes; make composition more cohesive. || Multi-page | One philosophy, distinct variation per page; bundle as one PDF or multiple PNGs; pages tell a story. |## Common Mistakes- Generic stock-photo aesthetics instead of a named philosophy.- Announcing the conceptual reference instead of embedding it subtly.## IntegrationCalled by: user directly, `/ai-design`, `/ai-media`. Consumed by: `/ai-slides` (aesthetic philosophy), `/ai-media` (visual direction). Calls: none — produces final artifacts. See also: `/ai-design` (UI), `/ai-animation` (motion).## Examples```/ai-visual event poster for Edge Runtime 2026 developer conference```Names a movement (e.g. "Brutalist Compute"), articulates philosophy across space/color/composition, and renders an HTML->PDF poster at 90% visual / 10% text.$ARGUMENTS

Frequently asked questions