mckruz/comfyui-expert

video-publisher

Publish assembled videos to YouTube and other platforms.

View source
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

Video Publisher

Thin orchestrator that routes publishing tasks to existing specialized skills.

Publishing Workflow

PUBLISH REQUEST
    |
    |-- Need to plan content first?
    |   |-- youtube-research-video-topic → Research competitors and gaps
    |   |-- youtube-plan-new-video → Generate title, thumbnail, hook
    |   |-- youtube-strategy → Optimize for discovery
    |
    |-- Ready to upload?
    |   |-- Verify video file is ready (video-assembly checklist passed)
    |   |-- Generate metadata (title, description, tags)
    |   |-- youtube-uploader → Upload with metadata
    |
    |-- Post-publish?
    |   |-- youtube-studio → Monitor analytics
    |   |-- Track performance for future optimization

Skill Delegation

Content Planning

TaskDelegate ToInput
Research topic viabilityyoutube-research-video-topicTopic/niche
Plan title + thumbnail + hookyoutube-plan-new-videoResearch results
Optimize for YouTube algorithmyoutube-strategyContent plan

Upload

TaskDelegate ToInput
Upload video fileyoutube-uploaderVideo file + metadata
Manage channelyoutube-studioChannel operations

Analytics

TaskDelegate ToInput
View performanceyoutube-studioVideo/channel ID
Analyze for improvementsyoutube-video-analystVideo URL

Metadata Generation

When preparing to publish, generate:

Title

  • Use youtube-title skill for optimization
  • Keep under 60 characters
  • Include primary keyword
  • Create curiosity gap

Description

{Hook paragraph - what viewer will learn/see}

{Detailed description with timestamps}

{Links to resources mentioned}

{Social links and subscribe CTA}

---
Tags: {comma-separated relevant tags}

Tags

  • Primary topic keyword
  • Related keywords
  • Tool/software names (ComfyUI, Stable Diffusion, etc.)
  • Technique names
  • "AI video generation", "AI art tutorial", etc.

Thumbnail

  • Use youtube-thumbnail skill (via youtube-plan-new-video)
  • Character close-up or dramatic before/after
  • Bold text overlay (3-5 words max)
  • High contrast, readable at small size

Platform-Specific Settings

YouTube

SettingRecommended
Resolution1920x1080 or 3840x2160
FormatMP4 (H.264)
Frame rate24, 30, or 60 fps
AudioAAC, 192kbps+
Aspect ratio16:9
Max file size256GB (12 hours)

YouTube Shorts

SettingRecommended
Resolution1080x1920 (9:16)
Duration15-60 seconds
FormatMP4 (H.264)

Instagram Reels

SettingRecommended
Resolution1080x1920 (9:16)
Duration15-90 seconds
FormatMP4 (H.264)

TikTok

SettingRecommended
Resolution1080x1920 (9:16)
Duration15-180 seconds
FormatMP4 (H.264)

Pre-Publish Checklist

  • [ ] Video passes quality check (video-assembly checklist)
  • [ ] Title optimized for search + curiosity
  • [ ] Description includes timestamps and links
  • [ ] Tags are relevant and comprehensive
  • [ ] Thumbnail is compelling and readable at small size
  • [ ] Category and audience settings are correct
  • [ ] Schedule time is optimal (check youtube-strategy)
  • [ ] End screen and cards planned
  • [ ] Subtitles/CC file ready (if applicable)

Integration

This skill is the final step in the VideoAgent pipeline:

Research → Plan → Generate → Assemble → Publish

It bridges the ComfyUI production pipeline with the YouTube publishing pipeline.

from this repository

More skills

All skills
mckruz
Community

comfyui-prompt-engineer

Craft model-specific prompts optimized for the target checkpoint and identity method. Handles FLUX, SDXL, SD1.5, and Wan video models with proper syntax, quality tags, and negative prompts. Use when generating or refining prompts for ComfyUI workflows.

installs
1
GitHub stars
91
Updated
Mar 18
mckruz
Community

comfyui-prompt-interview

Guided conversational interview to understand a user's creative vision before generating model-appropriate image prompts. Asks clarifying questions about subject, mood, style, and technical preferences (4-7 exchanges), then synthesizes positive prompt, negative prompt, recommended settings table, and pipeline recommendation. Formats prompts for the target model (SDXL tag-style, FLUX natural language, SD1.5 weighted tokens). Triggers on "I want to create...", "help me make an image of...", "I have an idea for...", "help me craft a prompt", "write me a prompt for...", or any request for help describing a creative vision. Does NOT cover workflow building, prompt debugging/fixing, technical explanations, model training, code generation, or identity-preserving character generation.

installs
1
GitHub stars
91
Updated
Mar 18
mckruz
Community

comfyui-research

Research latest ComfyUI models, techniques, and community discoveries. Monitors YouTube channels, GitHub repos, and HuggingFace. Updates reference files with timestamped findings and flags stale information. Invoke with /research comfyui or automatically at session start for staleness checks.

installs
1
GitHub stars
91
Updated
Mar 18
mckruz
Community

comfyui-troubleshooter

Diagnose ComfyUI errors, workflow failures, and quality issues. Suggests fixes based on error patterns, missing dependencies, and community-known workarounds. Use when ComfyUI workflows fail or produce unexpected results.

installs
1
GitHub stars
91
Updated
Mar 18