MCKRUZ/ComfyUI-Expert

View on GitHub

9 skills discovered in this repository.

38
$npx skills add MCKRUZ/ComfyUI-Expert

Skills in this Repository

#SkillScore
1
Build ComfyUI image workflows from natural language

Generate valid ComfyUI workflow JSON from natural language. Handles txt2img, img2img, ControlNet, identity, video, upscaling, inpainting.

4.5
2
Connect to ComfyUI and queue image generation workflows

Connect to ComfyUI REST API to queue image generation workflows, monitor progress, and retrieve outputs with validation.

4.5
3
Conduct a structured creative interview to synthesize model-appropriate image prompts

Conduct guided interviews to extract creative vision and synthesize model-appropriate image prompts with settings recommendations.

4.0
4
Diagnose and resolve ComfyUI workflow errors

Systematically diagnose and fix ComfyUI errors, workflow failures, and quality issues using error patterns and community workarounds.

4.0
5
Train character LoRAs for consistent image generation

Guide to preparing datasets, configuring LoRA training for FLUX and SDXL, and evaluating checkpoints for character consistency in image generation.

4.0
6
Monitor ComfyUI developments and keep agent knowledge current

Track ComfyUI models, nodes, and techniques across YouTube, GitHub, and HuggingFace. Extract timestamped findings and flag stale information.

3.8
7
Assemble video from clips, audio, and assets using FFmpeg or Remotion

Combine clips, audio, and assets into final videos using FFmpeg or Remotion. Handles mixing, normalization, subtitles, and format conversion.

3.5
8
Manage video production project lifecycle and assets

Create and maintain video production projects with character profiles, workflow histories, and asset tracking in ComfyUI.

2.8
9
Orchestrate video publishing and distribution across platformsContent Marketing

Orchestrate video publishing to YouTube, Shorts, Instagram Reels, and TikTok with optimized metadata generation and pre-publish checklists.

2.8