mcpField
A
ai-artist

ai-artist

github.com/binhmucCreative & media22144 installsUpdated 43w ago
Repository

About ai-artist

A prompt-engineering skill for creating text and image generation prompts. It provides reusable structures, model-specific syntax guidance, and references for varied domains and advanced techniques.

Key features

  1. 01Structured LLM prompt patterns
  2. 02Image prompt templates
  3. 03Model-specific syntax tips
  4. 04Domain-specific prompt references
  5. 05Iteration and A/B testing guidance

Use cases

  1. 01Drafting role-based LLM instructions
  2. 02Describing subjects and styles for image generation
  3. 03Adapting prompts to model syntax

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/binhmuc/autobot-review --skill ai-artist

After installing, type/ai-artistin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
advanced-techniques.md
domain-code.md
domain-data.md
domain-marketing.md
domain-patterns.md
domain-writing.md
image-prompting.md
llm-prompting.md
nano-banana.md
reasoning-techniques.md

Details

From the project README

AI Artist - Prompt Engineering

Craft effective prompts for AI text and image generation models.

Core Principles

  1. Clarity - Be specific, avoid ambiguity
  2. Context - Set scene, role, constraints upfront
  3. Structure - Use consistent formatting (markdown, XML tags, delimiters)
  4. Iteration - Refine based on outputs, A/B test variations

Quick Patterns

LLM Prompts (Claude/GPT/Gemini)
[Role] You are a {expert type} specializing in {domain}.
[Context] {Background information and constraints}
[Task] {Specific action to perform}
[Format] {Output structure - JSON, markdown, list, etc.}
[Examples] {1-3 few-shot examples if needed}
Image Generation (Midjourney/DALL-E/Stable Diffusion)
[Subject] {main subject with details}
[Style] {artistic style, medium, artist reference}
[Composition] {framing, angle, lighting}
[Quality] {resolution modifiers, rendering quality}
[Negative] {what to avoid - only if supported}

Example: Portrait of a cyberpunk hacker, neon lighting, cinematic composition, detailed face, 8k, artstation quality --ar 16:9 --style raw

References

Load for detailed guidance:

TopicFileDescription
LLMreferences/llm-prompting.mdSystem prompts, few-shot, CoT, output formatting
Imagereferences/image-prompting.mdStyle keywords, model syntax, negative prompts
Nano Bananareferences/nano-banana.mdGemini image prompting, narrative style, multi-image input
Advancedreferences/advanced-techniques.mdMeta-prompting, chaining, A/B testing
Domain Indexreferences/domain-patterns.mdUniversal pattern, links to domain files
Marketingreferences/domain-marketing.mdHeadlines, product copy, emails, ads
Codereferences/domain-code.mdFunctions, review, refactoring, debugging
Writingreferences/domain-writing.mdStories, characters, dialogue, editing
Datareferences/domain-data.mdExtraction, analysis, comparison

Model-Specific Tips

ModelKey Syntax
Midjourney--ar, --style, --chaos, --weird, --v 6.1
DALL-E 3Natural language, no parameters, HD quality option
Stable DiffusionWeighted tokens (word:1.2), LoRA, negative prompt
FluxNatural prompts, style mixing, --guidance
Imagen/VeoDescriptive text, aspect ratio, style references

Anti-Patterns

  • Vague instructions ("make it better")
  • Conflicting constraints
  • Missing context for domain tasks
  • Over-prompting with redundant details
  • Ignoring model-specific strengths/limits

Comments

Markdown supported