Comfyui Workflow Builder
Turns natural language into executable ComfyUI workflow JSON with proper node connections, output indices, and model settings. It checks your inventory first to confirm you have the right checkpoints, LoRAs, and custom nodes before generating anything. Handles the usual suspects: txt2img, img2img, identity preservation with InstantID or PuLID, video generation via Wan or AnimateDiff, upscaling, and face detailing. The VRAM estimation table is genuinely useful if you're trying to avoid out-of-memory crashes. Won't help you install ComfyUI or write custom nodes, but if you already have a working setup and just want to skip the tedious JSON wiring, this does the job.
- install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
- 9
- skills.sh installs
- 2.2K
- GitHub stars
- 94
- last updated
- Jul 14, 2026
Install
$ npx -y skills add mckruz/comfyui-expert --skill comfyui-workflow-builder --agent claude-codeInstalls into .claude/skills of the current project.
Files
ComfyUI Workflow Builder
Translates natural language requests into executable ComfyUI workflow JSON. Always validates against inventory before generating.
Workflow Generation Process
Step 1: Understand the Request
Parse the user's intent into:
- Output type: Image, video, or audio
- Source material: Text-only, reference image(s), existing video
- Identity method: None, zero-shot (InstantID/PuLID), LoRA, Kontext
- Quality level: Draft (fast iteration) vs production (maximum quality)
- Special requirements: ControlNet, inpainting, upscaling, lip-sync
Step 2: Check Inventory
Read state/inventory.json to determine:
- Available checkpoints → select best match for task
- Available identity models → determine which methods are possible
- Available ControlNet models → enable pose/depth control if available
- Custom nodes installed → verify all required nodes exist
- VRAM available → optimize settings accordingly
Step 3: Select Pipeline Pattern
Based on request + inventory, choose from:
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/mckruz/comfyui-expert
- Categories
- Automation & Workflows, Generative Media
- First seen
- May 16, 2026
More from mckruz/comfyui-expert
All 10Recommended
More Automation & Workflows
workflow-from-chatscursor/pluginsExtract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine fe2.2Kskills.sh installs
skill-authoring-workflowdeanpeters/product-manager-skillsTurn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking standards.2.2Kskills.sh installs
video-translationnoizai/skillsTranslate and dub videos from one language to another, replacing the original audio with TTS while keeping the video intact.2.1Kskills.sh installs
icon-set-generatorjezweb/claude-skillsGenerate cohesive, project-specific SVG icon sets for websites and applications. Use this skill whenever the user needs custom icons, an icon set for a website 2Kskills.sh installs
novel-writer-workflow-guidewordflowlab/novel-writer-skillsUse when user starts a novel project or asks how to organize their writing - guides through novel-writer's seven-step methodology and ensures proper workflow2Kskills.sh installs
cupynumeric-parallel-data-loadnvidia/skillsLoad a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual part1.9Kskills.sh installs