brand-illustrator — community brand-illustrator, skills-kit, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Creative Agents needing custom, on-brand illustration generation with warm off-white canvas and confident black ink lines. An opinionated collection of Agent Skills I use daily in my work.

nibzard nibzard
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The brand-illustrator skill by nibzard is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for Creative Agents needing custom, on-brand illustration generation with warm off-white canvas and confident black ink lines.

Core Value

Empowers agents to generate hand-drawn line illustrations as reusable, procedural SVG files using a bold accent color system, ensuring consistent visual identity through confident black ink lines and warm off-white canvas.

Capabilities Granted for brand-illustrator

Generating icon illustrations with primary objects isolated for quick visual impact
Creating on-brand concept proposals with three distinct design options
Producing final image files consistently using the Builder Methods style and color system

! Prerequisites & Limits

  • Requires specific brand visual identity guidelines
  • Limited to generating illustrations with one bold accent color
  • Needs selection input from user for concept proposal
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

brand-illustrator

Install brand-illustrator, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Builder Methods Brand Illustrator

Generate hand-drawn line illustrations that match the Builder Methods visual identity: warm off-white canvas, confident black ink lines, and one bold accent color.

This Skill is designed to be reusable and procedural:

  • you gather requirements
  • you propose three on-brand concepts
  • you get a selection
  • you generate final image(s) consistently using our style + color system

What this Skill produces

  • Icon: 1 primary object, isolated, quick punctuation.
  • Scene: 2–4 objects, suggested environment, hero/header moments.
  • Periphery: 1–3 objects, used as corner/edge elements or decorative supports.

See references/visual-world.md for the world + constraints and references/style.md for rendering rules.

Requirements

  • Python 3.8+ for running the generation script
  • google-genai package: pip install google-genai
  • GEMINI_API_KEY environment variable: Set your Google Gemini API key as GEMINI_API_KEY (alternatively GOOGLE_API_KEY or GENAI_API_KEY)

Get an API key from: https://ai.google.dev/

Quick Start

  1. Create a project folder (recommended) in projects/ with today's date and a short slug.

    Example:

    bash
    1mkdir -p projects/2026-01-13-blog-hero
  2. Gather requirements — use the AskUserQuestion tool for each missing piece one at a time. Required inputs:

    • Content context: topic + the core idea (insight), or paste article/transcript
    • Visual context: where the illustration will live (page screenshot, layout notes), or “n/a”
    • Accent color: coral | teal | indigo | amber
    • Image type: icon | scene | periphery
    • Dimensions (px): width × height

    Defaults:

    • scene: 1200×630
    • icon: 512×512
    • periphery: 500×500
  3. Generate 3 concept options using references/idea-mapping.md:

    • Present Option A / B / C
    • Each option includes: connection type, category (Builder’s World / Metaphor / Digital Artifact), object list, and why it fits the content.
    • Keep options meaningfully different (object choice, metaphor, or mood), but all on-brand.
  4. Get user choice — use AskUserQuestion and let them pick A/B/C (or “Other” for feedback).

  5. Document the project — create project.md inside the project folder with:

    • requirements
    • A/B/C concepts
    • chosen direction
    • final prompt + parameters
    • output filenames
  6. Craft prompt and generate once a concept is approved, saving outputs to the project folder.

    Example:

    bash
    1python3 ${CLAUDE_PLUGIN_ROOT}/skills/brand-illustrator/scripts/generate.py \ 2 --prompt "A worn leather notebook open to a page with handwritten wireframe sketches" \ 3 --color coral \ 4 --type scene \ 5 --width 1200 \ 6 --height 630 \ 7 --output projects/2026-01-13-blog-hero/illustration-v1.png

Color System

See references/colors.md for all hex values (single source of truth).

Available accent colors: Coral, Teal, Indigo, Amber

Rules

  • Use ONE accent color per illustration.
  • Most of the image is warm off-white background with confident black lines.
  • Accent color should fill ~20–30% of the illustration.
  • Shadow/depth color is used sparingly (~5–10%), mostly as grounding.

Style Requirements (non-negotiable)

These are enforced by prompt + review. See references/style.md for full details.

  • Hand-drawn ink line art; no photorealism, no 3D, no gradients
  • Restrained compositions: focus objects over scenery
  • Suggest environment with a few cues; do not render full rooms
  • Leave negative space for text overlays when used as a hero image

Concepting Guidance

Use the mapping doc to ensure every illustration is connected to the content:

  • references/idea-mapping.md — connection types, object lists, metaphors, quick reference by meaning
  • references/visual-world.md — what “belongs” in the Builder Methods world
  • references/prompts.md — prompt templates and proven patterns

Safety / Brand Guardrails

  • Avoid trademarks/logos/brand names on devices, mugs, screens, or apparel.
  • Avoid depicting real identifiable people.
  • Keep UI/terminal content generic (nonsense code is fine; no secrets).
  • No violence, gore, or sensitive themes—Builder Methods illustrations should feel calm and inviting.

Project Documentation Template

Copy into projects/<date>-<slug>/project.md:

md
1# Project: <slug> 2 3## Requirements 4- Content context: 5- Core idea: 6- Visual context: 7- Accent color: 8- Image type: 9- Dimensions: 10 11## Concepts 12### Option A 13- Connection type: 14- Category: 15- Objects: 16- Rationale: 17 18### Option B 19... 20 21### Option C 22... 23 24## Selected Direction 25- Chosen option: 26- Notes / tweaks: 27 28## Final Prompt 29```text 30<final prompt here>

Generation Params

  • color:
  • type:
  • width:
  • height:
  • output:

Outputs

  • illustration-v1.png
  • illustration-v2.png

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is brand-illustrator?

Perfect for Creative Agents needing custom, on-brand illustration generation with warm off-white canvas and confident black ink lines. An opinionated collection of Agent Skills I use daily in my work.

How do I install brand-illustrator?

Run the command: npx killer-skills add nibzard/skills-kit. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for brand-illustrator?

Key use cases include: Generating icon illustrations with primary objects isolated for quick visual impact, Creating on-brand concept proposals with three distinct design options, Producing final image files consistently using the Builder Methods style and color system.

Which IDEs are compatible with brand-illustrator?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for brand-illustrator?

Requires specific brand visual identity guidelines. Limited to generating illustrations with one bold accent color. Needs selection input from user for concept proposal.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add nibzard/skills-kit. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use brand-illustrator immediately in the current project.

Related Skills

Looking for an alternative to brand-illustrator or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI