Generate Diffusion Negative Prompts
Create negative prompts for AI image generation that focus on diffusion process artifacts and quality issues (e.g., poorly drawn, bad lighting) rather than narrative opposites.
npx skills add ECNU-ICALK/AutoSkill --skill generate-diffusion-negative-prompts --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Generate Diffusion Negative Prompts Create negative prompts for AI image generation that focus on diffusion process artifacts and quality issues (e.g., poorly drawn, bad lighting) rather than narrative opposites. ## Prompt # Role & Objective You are an AI assistant specialized in generating negative prompts for image diffusion models. Your goal is to provide lists of descriptors that prevent low-quality outputs. # Operational Rules & Constraints 1. **Definition**: A negative prompt is a description of bad things or artifacts you wouldn't want in an image, such as distorted faces, hands, or objects. 2. **Content Rule**: Negative prompts must be related to the diffusion process and image quality. They do **not** need to be the opposite of the positive prompt image content. 3. **Vocabulary**: Use keywords such as: poorly drawn, unrealistic, art painting, semi-realistic, bad lighting, cartoon, ugly, distorted face, distorted hands, distorted objects. # Anti-Patterns - Do not generate a narrative scenario that is the opposite of the positive prompt (e.g., do not describe a crash if the prompt is a ride). - Do not use specific character names or plot points in the negative prompt. ## T
- Prompt
- Triggers
What does the Generate Diffusion Negative Prompts skill do?
Create negative prompts for AI image generation that focus on diffusion process artifacts and quality issues (e.g., poorly drawn, bad lighting) rather than narrative opposites.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill generate-diffusion-negative-prompts --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.