Agent skill

Illustrated Gallery

by majiayu000 in majiayu000/spellbook

Art-direct complete illustrated websites and write project-specific image-generation prompts.

MITAuto-check passedMedia & Creative

Install Illustrated Gallery

skills CLI
$ npx skills add majiayu000/spellbook --skill illustrated-gallery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install majiayu000/spellbook illustrated-gallery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/majiayu000/spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/illustrated-gallery .claude/skills/illustrated-gallery && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
illustrated-gallery
GitHub stars
287
Token cost
~1.6k tokens
SKILL.md length
861 words
Files
3 (incl. references)
Skills in repo
97
Repo updated
First seen
Licence
MIT

At a glance

Art-direct complete illustrated websites and write project-specific image-generation prompts.

  • The user requests Illustrated Gallery
  • SKILL.md covers Start with the project, Design the whole page, Generate original artwork and Interaction and implementation, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • A gallery-inspired visual style

What it does

Illustrated Gallery is an agent skill from majiayu000/spellbook. Art-direct complete illustrated websites and write project-specific image-generation prompts. Use when the user requests Illustrated Gallery, a gallery-inspired visual style, or $illustrated-gallery. Covers visual direction, original artwork, and page-wide composition; not a fixed website clone, standalone image task, or generic dashboard skill.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/art-direction.md`).

It sits in Media & Creative, covering Design to code and Image generation. The repository describes itself as: Cross-runtime skills for Claude Code, Codex, and multi-agent workflows. The licence is MIT.

When your agent uses it

  • The user requests Illustrated Gallery
  • A gallery-inspired visual style
  • $illustrated-gallery

Example prompts

  • “/illustrated-gallery”

What it can do on your machine

Read from SKILL.md and the folder at commit ed52af7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Illustrated Gallery loads about 1.6k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 92 tokens; SKILL.md has 861 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from majiayu000/spellbook at commit ed52af7, republished under its MIT licence (© majiayu000). 861 words, ~1,597 tokens.

Download SKILL.mdSave it as .claude/skills/illustrated-gallery/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
illustrated-gallery
description
Art-direct complete illustrated websites and write project-specific image-generation prompts. Use when the user requests Illustrated Gallery, a gallery-inspired visual style, or $illustrated-gallery. Covers visual direction, original artwork, and page-wide composition; not a fixed website clone, standalone image task, or generic dashboard skill.

This is an art-direction and image-prompting guide, not a ready-made website. It ships no images, brand, page markup, or fixed asset list. Create the visual language and artwork for the user's project; never import a previous project's pictures or content simply because it used this skill.

Start with the project

Identify the audience, primary task, actual content, and requested scope. Respect existing integration requirements. When the user rejects the current UI, inspect only what is needed to preserve data and behavior, not to reuse its appearance.

Choose a visual direction using direction examples. These are starting points, not presets or a closed menu. Palette, medium, subjects, composition, density, and motion can vary independently. State the chosen direction briefly and proceed; do not turn routine design choices into an approval interview.

Keep the useful qualities of a gallery: considered composition, strong type hierarchy, expressive artwork, and enough quiet space to read. Blue botanicals, serif headlines, floating cards, dark backgrounds, and carousels are optional, not requirements. Let the subject and user task determine their use.

Design the whole page

Before implementing, give every requested section a purpose and layout. A complete redesign includes navigation, the main content, search and filters if present, onboarding, supporting sections, empty states, and the footer. Changing a hero image while leaving the rest of the rejected UI intact is not a complete redesign.

Carry a coherent palette, typographic scale, spacing, and visual motifs through the page, while varying composition to suit each section. A directory may need a category index and readable resource rows; a portfolio may need large project images. Do not impose portfolio cards or a studio contact form on unrelated tasks. Preserve collected content and useful behavior when reorganizing an existing site.

Do not decorate every row with an unrelated generated image. Put artwork where it helps explain a concept or orient the reader; use typography and layout for dense information. Do not invent project screenshots, ratings, test results, or endorsements.

Generate original artwork

Use user-provided project assets where appropriate, otherwise use an available image-generation tool. Follow its documented workflow. Choose image count and aspect ratios from the actual layout, never from a fixed sample collection.

For each asset, write a prompt covering:

  • Role and meaning: its page section and the project idea it should express.
  • Subject: a concrete scene or visual metaphor relevant to that idea.
  • Medium: illustration, collage, material study, photography, or another chosen treatment.
  • Palette and light: how it belongs to this page's visual direction.
  • Composition: focal point, text-safe areas, framing, and likely mobile crop.
  • Constraints: no baked-in UI text, invented logos, or misleading product depictions.

Write actual project-specific prompts, not unfilled templates. Across a set, keep shared medium, material, or lighting coherent while changing subjects and framing. A style reference guides composition and treatment; it is not an asset to deliver unless the user explicitly requests that particular image.

Inspect generated images before integrating them. Adjust composition or regenerate if a subject conflicts with text, a mobile crop loses the focal point, or the result has misleading labels. Describe conceptual artwork as artwork, not a real product screenshot or measurement. Store final images in the target project, never in this skill; record the generation prompts and asset sources in the project's existing source notes when available.

If suitable images or the generation capability are unavailable, report the missing asset and continue independent layout work. Ask for the needed asset or an alternative; do not silently substitute old sample images or claim the design is complete.

Show full SKILL.md (274 more words)Show less

Interaction and implementation

Use the project's existing stack. A static page does not need a framework solely for this design. Keep content readable without depending on decorative effects.

Choose motion to fit the composition. A still illustration needs no animation. When a gallery and ASCII dissolve are requested, render a roughly 1.5-second full-frame transition, sampling the outgoing and incoming image into character cells; keep the artwork still between changes. Do not substitute a wipe or add warping, parallax, or continuous zoom without a reason grounded in the brief.

For a carousel, provide pause, previous/next, direct selection, keyboard-operable controls, touch navigation, and reduced-motion support. Pause stops autoplay but not manual selection. Separate image movement, transitions, and scrolling behavior. Load only the initial artwork eagerly; defer other full-size images as appropriate.

Gotchas and completion checks

Use the target project's checks and inspect the complete page in a browser.

  • Artwork, wording, and section purposes fit this project; no copied sample content.
  • Every section in the requested scope has been reviewed, including the lower page.
  • Desktop and mobile layouts preserve the focal point, readable contrast, and usable controls.
  • Navigation, search, filtering, empty states, and any gallery interactions work.
  • Images load, transitions are actually observed if used, and reduced motion is respected.
  • Resource records and useful existing functionality survive the redesign.
  • There are no unrelated images in the published output and no horizontal overflow.

Report any unverified behavior rather than treating syntax checks as visual proof. Perform authorized local edits and checks directly. Reuse existing authorization for image generation and deployment; request missing authorization only when the next action exceeds the user's scope. Never publish to an unrelated site.

© majiayu000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/illustrated-gallery of majiayu000/spellbook.

  • SKILL.md
  • agents/openai.yaml
  • references/art-direction.md

Open the folder on GitHubat commit ed52af7

Compare with similar skills

Illustrated Gallery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Illustrated Gallery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Illustrated Gallery this skillmajiayu000/spellbook287—~1.6kAutomated safety check: PassMIT
CarouselsTheCraigHewitt/skills159—~2.3kAutomated safety check: PassMIT
Website Style ImagesLeoYeAI/openclaw-master-skills2.2k—~4.1kAutomated safety check: PassMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
Structured Image Generationbytedance/deer-flow84k4 repos~2.9kAutomated safety check: PassMIT
Canghe Comicfreestylefly/canghe-skills4618 repos~3.2kAutomated safety check: PassNone

Similar skills

  • Carousels

    TheCraigHewitt/skills

    Turns a piece of Craig's content (an email, a YouTube script, an essay, or pasted text) into a polished image carousel publishable to both LinkedIn and Instagram from one set of 1080x1350 slides.

    159 GitHub stars~2.3k tokensUpdated 4 mo ago
    Media & CreativeAuto-check passed
  • Website Style Images

    LeoYeAI/openclaw-master-skills

    Generate images matching a website's visual style. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~4.1k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Structured Image Generation

    bytedance/deer-flow

    Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.

    84k GitHub starsUsed in 4 repos~2.9k tokens
    Media & CreativeAuto-check passed
  • Canghe Comic

    freestylefly/canghe-skills

    Knowledge comic creator supporting multiple art styles and tones.

    461 GitHub starsUsed in 8 repos~3.2k tokens
    Media & CreativeAuto-check passed
  • Figma to HyperFrames

    heygen-com/hyperframes

    Imports Figma assets, brand tokens, components and motion into a HyperFrames video composition, using the Figma REST API with a connector or native export for shaders.

    60k GitHub starsUsed in 3 repos~4.5k tokens
    Media & CreativeAuto-check: notes

More from majiayu000/spellbook

All 97 skills in this repo
  • Skill Ecosystem Doctor

    majiayu000/spellbook

    Audits and repairs how coding-agent Skills are owned, copied and exposed across runtimes, from canonical sources to quarantine and retirement.

    287 GitHub stars~3k tokensUpdated 3 days ago
    Auto-check passed
  • AGENTS.md Scaffold

    majiayu000/spellbook

    Scans a repository for real evidence and proposes, or on request writes, a small stack of root and scoped AGENTS.md files with validation commands and generated-file boundaries.

    287 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed
  • Product Demo Builder

    majiayu000/spellbook

    Plans, produces or diagnoses evidence-backed product demo videos: script, capture plan, pacing checks and verified final media built on real product behavior.

    287 GitHub stars~3.3k tokensUpdated 3 days ago
    Auto-check passed
  • Flowguard Task Guard

    majiayu000/spellbook

    Single entry point that routes long or ambiguous agent tasks, checks live state, bounds autonomous loops and leaves a resumable handoff.

    287 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check passed
  • npm Supply Chain Check

    majiayu000/spellbook

    Scans a repository, its lockfiles and node_modules for known malicious npm package versions and install-time indicators, using a read-only Python scanner.

    287 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed
  • Product Manager Toolkit

    majiayu000/spellbook

    Product management helpers: a RICE scoring script, an interview transcript analyzer and PRD templates for prioritizing features, synthesizing research and writing requirements.

    287 GitHub stars~2.2k tokensUpdated 3 days ago
    Auto-check passed

Questions about Illustrated Gallery

What does Illustrated Gallery do?

Art-direct complete illustrated websites and write project-specific image-generation prompts. Illustrated Gallery is an agent skill from majiayu000/spellbook. Art-direct complete illustrated websites and write project-specific image-generation prompts.

When should I use Illustrated Gallery?

Illustrated Gallery fits situations like: the user requests Illustrated Gallery; A gallery-inspired visual style; $illustrated-gallery.

How do I install Illustrated Gallery in Claude Code?

Run `npx skills add majiayu000/spellbook --skill illustrated-gallery -a claude-code`. Or copy the skill folder (skills/illustrated-gallery in majiayu000/spellbook) into .claude/skills/illustrated-gallery in your project. Claude Code loads it when a task matches its description.

How do I install Illustrated Gallery in Codex?

Run `npx skills add majiayu000/spellbook --skill illustrated-gallery -a codex`. Or copy the skill folder (skills/illustrated-gallery in majiayu000/spellbook) into .agents/skills/illustrated-gallery in your project. Codex loads it when a task matches its description.

Can I use Illustrated Gallery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add majiayu000/spellbook --skill illustrated-gallery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/illustrated-gallery, .gemini/skills/illustrated-gallery, .github/skills/illustrated-gallery and .opencode/skills/illustrated-gallery in your project.

What does Illustrated Gallery need to run?

SKILL.md names no scripts, command-line tools or credentials: Illustrated Gallery is instructions for the agent only.

Does Illustrated Gallery access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Illustrated Gallery safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Illustrated Gallery use?

Illustrated Gallery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Illustrated Gallery use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 818 tokens, read only when the agent opens those files.

What are the alternatives to Illustrated Gallery?

Skills that share tags, products or a category with Illustrated Gallery: Carousels (TheCraigHewitt/skills, 159 stars), Website Style Images (LeoYeAI/openclaw-master-skills, 2.2k stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars) and Structured Image Generation (bytedance/deer-flow, 84k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Illustrated Gallery?

majiayu000 (a GitHub user) maintains it in majiayu000/spellbook, which has 287 GitHub stars. The repository holds 97 skills in this directory. The repository was last updated on October 8, 2026.

Source: majiayu000/spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.