Art Direction

Organization

KyaniteLabs

art-direction

Imagery, illustration, and iconography direction for web UI. Use for hero images, photo treatment, illustration style, icon sets, favicons, OG/social cards, decorative graphics, image-shaped holes, and removing generic AI imagery.

Overview

Publisher	KyaniteLabs
Repository	`tastecheck`
Skill name	`art-direction`
Stars	10
Forks	7
Bundled files	3
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by KyaniteLabs on GitHub. Read the source before you install it.

Installation

Install the Art Direction AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/KyaniteLabs/tastecheck/tree/main/skills/art-direction
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/KyaniteLabs/tastecheck.git /tmp/tastecheck
mkdir -p .claude/skills
cp -r /tmp/tastecheck/skills/art-direction .claude/skills/art-direction

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Art Direction in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Art Direction on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Art Direction is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Art Direction

Art direction gives imagery a job: orient, explain, establish trust, or create a controlled emotional cue. It is not a list of adjectives.

Set the visual job before selecting assets

Write a one-line stance: audience, moment, desired response, and what imagery communicates that copy cannot. Choose one primary treatment and fallback: documentary detail, diagrammatic illustration, editorial crop, icon system, or no image.

Decision	Specify	Reject when
Subject	people, object, place, or abstract concept	it repeats the headline without adding evidence
Point of view	distance, angle, energy, inclusion	it turns a serious task into decoration
Composition	focal zone, text-safe area, responsive crop	the message disappears at narrow widths
Surface	palette, texture, line weight, lighting	it conflicts with product semantic states
Rights	source, license, attribution, expiry	ownership or reuse is unknown

Turn the stance into an asset contract

For each asset, record source, allowed use, focal subject, wide/narrow crop anchors, overlay, and alt decision. Without an approved library, deliver a search or commissioning brief—not fabricated filenames or claimed licenses.

Make the narrow crop independently legible; do not assume a desktop crop merely shrinks.
Reserve readable text space in the composition before applying an overlay.
Prefer a coherent series over unrelated stock images. Inclusion must be credible to the subject and setting.
Use decorative alt only when removing the image loses no task-relevant information. Otherwise state the information in concise alt text or adjacent copy.

Prove it in the rendered layout

Show wide and narrow compositions with real headline, navigation, and state colors. Check crop survival, overlay contrast, repeated-card noise, and icon legibility at rendered size.

Deliver a treatment board: stance, primary/fallback, two assets or search terms, crop notes, rights status, alt strategy, and reject criterion. Source URLs, licenses, and approval status are evidence, not ornamental credits.

Use decision records when competing treatments require a documented trade-off.

Favicons and app icons

Ship an SVG favicon primary (<link rel="icon" href="/favicon.svg" type="image/svg+xml">) with a PNG fallback. Derive the mark from the stance; test at 16×16 pixels—a bold glyph outperforms a detailed logo. Apple Touch Icon (180), manifest icons (192/512), and OG preview are separate deliverables with their own crop/contrast needs. See patterns.

Ship check

The treatment explains a product or content need that copy alone cannot.
Every selected image has source, rights, crop, and alt decisions.
The narrow composition and text-over-image state have been reviewed.
A missing or unlicensed asset is represented as a brief, not an invented deliverable.

Contract (generated)

Canonical detail: contract.json.

Route: A product needs a committed imagery, illustration, or iconography system with source and rights decisions.; avoid: The request is only a color, type, or layout decision.
Exclude: Do not use placeholder imagery when the brief requires a real asset plan. (+1 in contract.json)
Stop / handoff: Stop when source or rights constraints cannot be verified. (+1 in contract.json); receives [design-system-interview, improve-existing-website, tasteroll] -> sends [responsive-layout, a11y-pass, deslop-ui, tastecheck-pass]
Output: source-aware visual treatment and asset plan
Evidence: table_with_evidence with status, reason, remediation, evidence, provenance.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Art Direction AI skill do?

Why use Art Direction on TypingMind?

Because you install it once and use it with any model. Art Direction is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Art Direction in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/KyaniteLabs/tastecheck/tree/main/skills/art-direction. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Art Direction?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Art Direction?

As many as you like. As long as a model supports skills, you can use Art Direction with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Art Direction AI skill free?

Yes. It is published on GitHub by KyaniteLabs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Archify

NousResearch

OrganizationPopular

Validated interactive HTML diagrams, upstream-maintained.

Auteur

Design and build cinematic, award-level web pages.

Concept Diagrams

Generate flat, minimal educational SVG visuals as HTML.

Hyperframes

Render MP4/WebM videos from HTML compositions.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Art Direction

Set the visual job before selecting assets

Turn the stance into an asset contract

Prove it in the rendered layout

Favicons and app icons

Ship check

Contract (generated)

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now