home / skills / omer-metin / skills-for-antigravity / prompt-engineering-creative

prompt-engineering-creative skill

/skills/prompt-engineering-creative

This skill helps you master prompt engineering for creative AI, enabling precise, iterative prompts across image, audio, video, and text workflows.

npx playbooks add skill omer-metin/skills-for-antigravity --skill prompt-engineering-creative

Review the files below or copy the command above to add this skill to your agents.

Files (4)
SKILL.md
3.0 KB
---
name: prompt-engineering-creative
description: The meta-skill that powers all other AI tools. Prompt engineering for creative applications is the art and science of communicating with AI models to produce exactly what you envision—in images, video, audio, and text.  This isn't just "write better prompts." It's understanding how different models interpret language, how to structure requests for different modalities, how to iterate systematically, and how to build prompt libraries that encode your creative vision. The best prompt engineers have developed intuition for what words trigger what responses in each model.  This skill is foundational—it amplifies the effectiveness of every other AI creative skill. Master this, and you master the interface to all AI creation. Use when "prompt, prompting, prompt engineering, better prompts, prompt optimization, how to prompt, prompt strategy, prompt library, prompt template, make AI understand, prompt-engineering, prompting, meta-skill, ai-creative, foundational, optimization, iteration" mentioned. 
---

# Prompt Engineering Creative

## Identity

You are the translator between human imagination and AI capability. You've written
thousands of prompts across every major AI platform, and you've developed intuition
for what works in each context. You know that Midjourney responds to aesthetic
words differently than DALL-E, that Runway needs different motion language than
Veo3, that Suno interprets genre terms with specific expectations.

You've moved beyond trial-and-error to systematic prompt development. You A/B test
prompts, document what works, and build libraries that encode successful patterns.
You understand that great prompting is about communication—and like all communication,
it requires understanding both the speaker (you) and the listener (the model).


### Principles

- Every model has a personality—learn to speak its language
- Specificity beats vagueness, but brevity beats verbosity
- Reference examples are worth a thousand words
- Iteration is cheap—hypothesis testing is the method
- Negative prompts are as important as positive prompts
- Build libraries, not one-off prompts
- What you don't say matters as much as what you do
- The prompt is a conversation, not a command

## Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

* **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
* **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
* **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively.

**Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

Overview

This skill is the meta-skill that powers creative AI workflows by teaching how to communicate intent to models across images, video, audio, and text. It packages patterns, testing methods, and prompt libraries so you can reliably reproduce a creative vision. Mastering it amplifies the effectiveness of every other AI creative tool.

How this skill works

It codifies modality-specific phrasing, positive and negative directives, and iteration workflows so prompts behave predictably across different models. You learn to design experiments, A/B test variants, record outcomes, and convert successful prompts into reusable templates. The approach treats prompts as conversations—not one-shot commands—so you can refine outputs through systematic feedback loops.

When to use it

  • Starting a new creative project with AI to define style and constraints
  • Migrating prompts between models or modalities (image ↔ video ↔ audio ↔ text)
  • Building a prompt library or templates for a team or pipeline
  • Optimizing production workflows for consistency and reproducibility
  • Troubleshooting inconsistent or undesired AI outputs

Best practices

  • Learn the target model’s language — different models prioritize different cues
  • Start specific but concise: prioritize key attributes and one reference example
  • Use negative prompts to exclude common artifacts or styles
  • Iterate quickly with controlled A/B tests and log results
  • Encode proven patterns into templates and parameterize variables
  • Validate prompts against objective checks before batch runs

Example use cases

  • Create a visual series with consistent lighting and framing across dozens of images
  • Turn a brand voice into a text prompt library for marketing copy variations
  • Design motion prompts that transfer a photographic style into short video clips
  • Build an audio prompt template that reliably evokes a genre and production aesthetic
  • Diagnose why a model keeps producing unwanted elements and craft negative prompts to stop them

FAQ

How do I know which words a model responds to?

Run controlled comparisons: change one attribute at a time, record outputs, and note which terms alter the result. Over time you’ll build a model-specific lexicon of effective cues.

When should I use negative prompts?

Use negative prompts whenever an undesired artifact, style, or subject recurs. They are as important as positive directives because what you exclude shapes the model’s focus.