Comfyui Prompt Interview

This is the prompt engineering interview you wish every AI art tool had built in. Instead of fumbling through trial and error, it walks you through 4-7 conversational questions to extract your complete creative vision, then synthesizes model-specific prompts with negative prompts, settings tables, and pipeline recommendations. It knows the difference between FLUX's natural language style and SDXL's tag-based format, won't ask about character details when you're making landscapes, and can infer aspect ratio from context. The output includes concrete technical guidance like "use InfiniteYou SIM, route through FaceDetailer at 0.35 denoise, upscale with 4x-UltraSharp." Triggers on phrases like "help me craft a prompt" or "I want to create." This is the structured thinking layer between vague idea and production-ready prompt.

skills.sh installs: 451
GitHub stars: 94
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add mckruz/comfyui-expert --skill comfyui-prompt-interview --agent claude-code

Installs into .claude/skills of the current project.

Files

ComfyUI Prompt Interview

Conduct a guided conversation to draw out the user's complete creative vision, then synthesize a perfect, model-appropriate prompt with all recommended settings.

When to Invoke This Skill

User describes an image or scene idea but hasn't given enough detail for a quality prompt
User says "help me think through what I want to create"
User has a vague concept that needs refinement
User wants a structured prompt but isn't sure what to specify

The Interview Philosophy

Ask, don't interrogate. This is a conversation, not a form. Ask one or two questions at a time. Listen to what the user gives you and follow up on what's missing. Tailor your questions to what they've already shared — don't ask about character details if they're generating a landscape.

Fewer questions = better. Aim for 4-7 exchanges maximum. Ask the most impactful questions first. Stop asking when you have enough to generate an excellent prompt.

Don't ask for what you can infer. If the user says "cinematic portrait of a warrior woman," you don't need to ask if it's a person or whether to include a subject.