OpenSkillIndex← back to search
claude-code

Awesome-omni-skill dalle

DALL-E OpenAI image generation. Use for image creation.

install
source · Clone the upstream repo
git clone https://github.com/diegosouzapw/awesome-omni-skill
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/diegosouzapw/awesome-omni-skill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/ai-agents/dalle" ~/.claude/skills/diegosouzapw-awesome-omni-skill-dalle && rm -rf "$T"
manifest: skills/ai-agents/dalle/SKILL.md
source content

DALL-E 3 / 4

DALL-E is OpenAI's image model. It excels at Prompt Adherence—it draws exactly what you ask for, including complex text.

When to Use

  • ChatGPT Integration: "Draw a diagram of..." inside a chat flow.
  • Complex Instructions: "A cat holding a sign that says 'Hello World'".
  • Safety: Strict guardrails against NSFW/Copyright.

Core Concepts

Integration

Available via OpenAI API (

dall-e-3
) and ChatGPT.

Editing

In ChatGPT, you can select an area of the image and say "Make the cat blue".

Best Practices (2025)

Do:

  • Use via ChatGPT: The conversational refinement is its superpower.
  • Ask for JSON: The API can return the image or a revised prompt.

Don't:

  • Don't expect photorealism: It often has a "plastic" or "smooth" look compared to Midjourney.

References