Comfyui Prompt Engineer
Install when you generate or refine ComfyUI prompts for FLUX, SDXL, SD1.5, or Wan video checkpoints with correct CFG, quality tags, and negative-prompt conventions.
Overview
ComfyUI Prompt Engineer is an agent skill for the Build phase that crafts model-specific prompts optimized for FLUX, SDXL, SD1.5, and Wan video in ComfyUI workflows.
Install
npx skills add https://github.com/mckruz/comfyui-expert --skill comfyui-prompt-engineerWhat is this skill?
- Model-specific rules for FLUX (natural language, CFG 3.5–4, minimal quality tags), SDXL (front-loaded quality tags, CFG
- Documented prompt structure templates such as subject, setting, lighting, and camera/style for photorealistic FLUX portr
- Explicit good vs bad FLUX examples showing why excess masterpiece/8k tags hurt FLUX outputs
- Handles identity-method-aware prompting called out in the skill description for checkpoint-aligned generation
- User-invocable OpenClaw skill with cross-platform metadata for darwin, linux, and win32
- Documents FLUX CFG range 3.5–4 and SDXL CFG range 7–9
- Covers four model families: FLUX, SDXL, SD1.5, and Wan video
Adoption & trust: 554 installs on skills.sh; 69 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You keep getting muddy or over-tagged images because FLUX and SDXL need opposite prompt habits, and your agent defaults to one generic style.
Who is it for?
Indie creators and solo SaaS marketers who batch ComfyUI renders and want an agent that respects per-model prompt grammar.
Skip if: Teams that only use DALL·E or Midjourney APIs with no ComfyUI graph—or beginners who have not installed a target checkpoint yet.
When should I use this skill?
Use when generating or refining prompts for ComfyUI workflows, including model-specific syntax, quality tags, and negative prompts.
What do I get? / Deliverables
You get checkpoint-aligned prompts with appropriate CFG, length, quality tags, and negatives ready to paste into ComfyUI graphs or automation scripts.
- Model-aligned positive prompt text with recommended CFG and length
- Negative prompt set appropriate to the chosen checkpoint family
Recommended Skills
Journey fit
Prompt engineering for ComfyUI is build-phase work: you are producing assets and tuning agent-assisted generation pipelines, not validating market fit. Agent-tooling fits because the skill teaches model-specific syntax your coding agent applies inside ComfyUI workflow generation and iteration loops.
How it compares
Skill-level prompt recipes for ComfyUI checkpoints, not a hosted image API or LoRA training pipeline.
Common Questions / FAQ
Who is comfyui-prompt-engineer for?
Solo builders and creative technologists using Claude Code, Cursor, or Codex to draft and refine ComfyUI prompts across multiple diffusion and video checkpoints.
When should I use comfyui-prompt-engineer?
During Build while wiring agent-tooling for asset pipelines—whenever you generate or refine prompts for ComfyUI workflows or swap between FLUX and SDXL families.
Is comfyui-prompt-engineer safe to install?
It is prompt guidance only, but install from the mckruz repo only after you review the Security Audits panel on this Prism page and restrict agent permissions around model paths and scripts.
SKILL.md
READMESKILL.md - Comfyui Prompt Engineer
# ComfyUI Prompt Engineer Generates optimized prompts tailored to specific models and identity methods. Different models respond differently to prompts. ## Model-Specific Prompt Rules ### FLUX.1 (dev/schnell/Kontext) - **Style**: Natural language descriptions work best - **CFG**: 3.5-4 (very low) - **Quality tags**: Minimal - FLUX doesn't need "masterpiece, best quality" - **Length**: Medium (50-100 words) - **Structure**: `{subject description}, {setting}, {lighting}, {camera/style}` **Good FLUX prompt:** ``` photorealistic portrait of a woman with auburn hair and green eyes, freckles across her nose and cheeks, wearing a cream knit sweater, sitting in a cafe with warm ambient lighting, shallow depth of field, shot on Sony A7IV, 85mm lens ``` **Bad FLUX prompt (too many quality tags):** ``` masterpiece, best quality, 8k uhd, highly detailed, photorealistic portrait... ``` ### SDXL (RealVisXL, Juggernaut, etc.) - **Style**: Quality tags at front help significantly - **CFG**: 7-9 - **Quality tags**: Include `masterpiece, best quality, photorealistic` - **Length**: Medium-long (50-150 words) - **Structure**: `{quality tags}, {trigger word}, {subject}, {details}, {setting}, {style}` - **Weighted syntax**: Supported `(important:1.3)` or `((very important))` **Good SDXL prompt:** ``` masterpiece, best quality, sage_character, photorealistic portrait of a woman, detailed skin texture with freckles, emerald green eyes, auburn copper hair, natural lighting from window, indoor setting, shallow depth of field, RAW photo quality, 8k uhd, film grain ``` ### SD 1.5 - **Style**: Tag-based works best - **CFG**: 7-8 - **Quality tags**: Essential - **Length**: Shorter (30-80 words) - **Structure**: `{quality}, {trigger}, {subject}, {details}, {style tags}` ### Wan 2.1/2.2 (Video) - **Style**: Concise motion descriptions - **CFG**: 5-7 - **Quality tags**: Minimal - **Length**: Short (20-50 words) - **Focus**: Describe the motion, not just the appearance - **Structure**: `{subject}, {action/motion}, {setting}, {quality}` **Good Wan prompt:** ``` young woman with auburn hair, talking naturally with gentle hand gestures, seated at a modern desk, soft studio lighting, high quality ``` ### AnimateDiff - **Style**: Same as base model (SD1.5/SDXL) but add motion keywords - **Motion keywords**: Include camera/subject motion description - **Length**: Same as base model ## With Identity Methods ### InstantID Prompts **Key adjustments:** - DO NOT describe specific facial features (the model provides them) - DO describe everything else: clothing, pose, setting, lighting - Keep CFG at 4-5 ``` photorealistic portrait, wearing black leather jacket, standing in an alley, dramatic side lighting, urban setting, moody atmosphere, 8k quality ``` ### PuLID Prompts **Key adjustments:** - Can include some facial descriptions (PuLID is more tolerant) - Method "neutral" for realistic, "fidelity" for exact match - CFG 5-7 ``` sage_character, photorealistic portrait, green eyes visible, natural makeup, professional headshot, neutral grey background, studio lighting ``` ### IP-Adapter FaceID **Key adjustments:** - Describe the style you want, not the face - weight_type "style transfer" for 3D→realistic - Standard CFG for base model ``` photorealistic portrait, DSLR photo quality, natural skin texture, warm indoor lighting, bokeh background, professional photography ``` ### FLUX Kontext (Editing) **Key adjustments:** - Describe the EDIT, not the full image - Be specific about what to change - Mention what to preserve ``` Change the outfit to a formal black