Illustrated Gallery logo

Illustrated Gallery

Community
majiayu000
illustrated-gallery

Build an illustrated portfolio, creative-studio landing page, or brand showcase with a static art gallery and full-frame ASCII dissolve transitions. Use when the user requests Illustrated Gallery, this visual template, or $illustrated-gallery. Do not use for generic dashboards, standalone ASCII art, or image-to-video generation.

Overview

Publishermajiayu000
Repositoryspellbook
Skill nameillustrated-gallery
Stars
280
Forks
26
Bundled files
16
LicenseMIT
Links
  • 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.

  • 16 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by majiayu000 on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. 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.
2

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/majiayu000/spellbook.git /tmp/spellbook
mkdir -p .claude/skills
cp -r /tmp/spellbook/skills/illustrated-gallery .claude/skills/illustrated-gallery
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Illustrated Gallery 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 Illustrated Gallery 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 Illustrated Gallery 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.

Illustrated Gallery

Create a website from the retained source template. Use artifact-template.json for reference paths. Preserve its visual system and accepted interactions while adapting content to the brief.

Workflow

  1. Inspect the target project and its instructions. For a new site, copy assets/source into a new working directory; leave the skill's source intact. For an existing site, adapt only the requested surface instead of replacing the entire project.
  2. Identify the audience, brand, text, and illustration subjects from the request. The five blue botanical artworks are examples, not mandatory subjects or a fixed image count.
  3. Retain the large artwork stage, fixed text layer, restrained floating card, serif headline hierarchy, and compact navigation unless the user requests changes. Keep images still between transitions.
  4. Replace or generate a coherent image set, then adjust each mobile crop and keep text and cards clear of faces, bird heads, and flower centers.
  5. Validate the complete interaction and responsive layout. Prepare static output only when needed for hosting; use the user's authorized hosting workflow.

Accepted interaction contract

  • Keep the full-frame ASCII dissolve, approximately 1.5 seconds long. Reuse the implementation in app.js; do not substitute an edge wipe or ordinary crossfade as an unsolicited optimization.
  • Keep artwork static. Do not add warping, ripples, floating particles, pointer parallax, or zoom unless explicitly requested. Improve image composition or crop instead when the image feels flat.
  • Treat subject motion, slide transitions, and scroll animation independently. A request to stop image motion must not remove the transition animation.
  • Preserve autoplay, pause, previous/next, direct slide selection, touch swipes, and reduced-motion support. Pause stops autoplay; manual navigation still works.
  • Reuse existing sections without adding dashboards, forms, configuration panels, or theme systems. The sample brief-download form saves a local file; do not describe it as sending a message or collecting a lead.

Artwork direction

Use user-provided images or an available image-generation tool. Keep a consistent palette, drawing medium, lighting, and detail density across the set. If new image generation is required but unavailable, report that limitation rather than claiming example assets were newly generated.

For this composition, start with wide 16:9 artwork, a quiet left region for headlines, and a subject near the center-right. Change this composition when the text layout changes. Structure prompts around purpose, subject, scene, medium, palette, focal placement, and text-free output. For example:

Wide editorial illustration for a creative studio. An ivory heron among lotus leaves, fine blue ink engraving, restrained teal and ivory palette, subject at center-right, quiet dark left region for a headline. No text, logo, or border.

Set each slides[].focus independently for mobile. Never reuse one crop for all subjects without inspecting it. Use full-sized WebP for the stage and smaller WebP thumbnails for the work grid. Preload the current and next full-sized image; load the remainder on demand.

Source and runtime

  • Edit branding and sections in index.html, visual rules in style.css, and image lists, crop positions, and transitions in app.js. The brief download heading and filename derive from the header .brand label and text, so rebranding the header keeps the downloaded markdown in sync without a separate JS edit.
  • Keep the dependency-free HTML/CSS/JavaScript stack for new template sites. Do not introduce a framework solely to reuse the design.
  • When changing image count, synchronize the slide array, initial counter, selection buttons, work cards, and total. Runtime counters use slides.length.
  • Find and edit the relevant CSS declaration or media query rather than appending more overrides to the stylesheet.
  • The retained .openai/hosting.json contains only static output configuration. When using Sites, follow the installed Sites workflow and register a new site. Never restore the original deployment ID or overwrite an unrelated live site.
  • Without Sites, serve or host the same static files using the target project's established workflow. Do not invent an unavailable deployment integration.

Build and verification

There are no build dependencies. In the new project, run node --check app.js. For static hosting, create out/, copy index.html, style.css, app.js, and the referenced WebP assets into it, preserving the assets/ paths. Do not package Git metadata, credentials, runtime files, or unused large image originals.

Done when:

  • Every referenced script and image exists, all images load, and the counts and selection states agree with the actual artwork list.
  • The full transition is observed in a browser, not merely checked for errors; images remain still before and after it.
  • Pause, direct selection, wraparound, touch navigation, and reduced motion work.
  • Desktop and mobile crops preserve subjects, floating cards do not obscure the focal point, and there is no horizontal overflow.
  • The initial page loads only the current and next full-size artwork; work-grid thumbnails do not force all full-size images to load.

Use available browser tooling for these checks. If unavailable, report the exact unverified behavior; syntax checks alone do not prove visual fidelity.

Autonomy and gotchas

Perform requested local edits, previews, and validation directly. Honor explicit local-only requests. Publishing, paid media generation, permissions, and existing production changes require authorization for that action and destination; reuse approval already provided in the conversation.

A still image distorted by a shader is not a generated video. A successful build is not proof of the requested visual effect. If a user rejects an animation, change that specific animation and preserve the other accepted interactions.

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 Illustrated Gallery AI skill do?

Build an illustrated portfolio, creative-studio landing page, or brand showcase with a static art gallery and full-frame ASCII dissolve transitions. Use when the user requests Illustrated Gallery, this visual template, or $illustrated-gallery. Do not use for generic dashboards, standalone ASCII art, or image-to-video generation.

Why use Illustrated Gallery on TypingMind?

Because you install it once and use it with any model. Illustrated Gallery 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 Illustrated Gallery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/majiayu000/spellbook/tree/main/skills/illustrated-gallery. 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 Illustrated Gallery?

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 Illustrated Gallery?

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

Is the Illustrated Gallery AI skill free?

Yes. It is published on GitHub by majiayu000 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇