comfy-cli

38
8
Source

Install, manage, and run ComfyUI instances. Use when setting up ComfyUI, launching servers, installing/updating/debugging custom nodes, downloading models from CivitAI/HuggingFace, managing workspaces, running API workflows, or troubleshooting node conflicts with bisect.

Install

mkdir -p .claude/skills/comfy-cli && curl -L -o skill.zip "https://mcp.directory/api/skills/download/1824" && unzip -o skill.zip -d .claude/skills/comfy-cli && rm skill.zip

Installs to .claude/skills/comfy-cli

About this skill

comfy-cli

CLI tool for managing ComfyUI installations, custom nodes, and models.

Quick start

comfy install                          # Install ComfyUI + ComfyUI-Manager
comfy launch                           # Start ComfyUI server
comfy node install ComfyUI-Impact-Pack # Install a custom node
comfy model download --url "https://civitai.com/api/download/models/12345"

Installation

comfy install                          # Interactive GPU selection
comfy install --nvidia                 # NVIDIA GPU
comfy install --amd                    # AMD GPU (Linux ROCm)
comfy install --m-series               # Apple Silicon
comfy install --cpu                    # CPU only
comfy install --restore                # Restore deps for existing install
comfy install --pr 1234                # Install specific PR
comfy install --version latest         # Latest stable release
comfy install --version 0.2.0          # Specific version

GPU options: --nvidia, --amd, --intel-arc, --m-series, --cpu

CUDA versions (NVIDIA): --cuda 12.9, --cuda 12.6, --cuda 12.4, --cuda 12.1, --cuda 11.8

Other flags: --skip-manager, --skip-torch-or-directml, --skip-requirement, --fast-deps

Launch

comfy launch                           # Foreground mode
comfy launch --background              # Background mode
comfy launch -- --listen 0.0.0.0       # Pass args to ComfyUI
comfy stop                             # Stop background instance
comfy launch --frontend-pr 1234        # Test frontend PR

Workspace selection

Global flags (mutually exclusive):

comfy --workspace /path/to/ComfyUI ... # Explicit path
comfy --recent ...                     # Last used instance
comfy --here ...                       # Current directory
comfy which                            # Show selected instance
comfy set-default /path/to/ComfyUI     # Set default

Custom nodes

comfy node show                        # List installed nodes
comfy node simple-show                 # Compact list
comfy node install <name>              # Install from registry
comfy node install <name> --fast-deps  # Fast dependency install
comfy node reinstall <name>            # Reinstall node
comfy node uninstall <name>            # Remove node
comfy node update all                  # Update all nodes
comfy node disable <name>              # Disable node
comfy node enable <name>               # Enable node
comfy node fix <name>                  # Fix node dependencies

Snapshots:

comfy node save-snapshot               # Save current state
comfy node save-snapshot --output snapshot.json
comfy node restore-snapshot snapshot.json
comfy node restore-dependencies        # Restore deps from nodes

Debugging:

comfy node bisect                      # Binary search for broken node
comfy node deps-in-workflow workflow.json  # Extract deps from workflow
comfy node install-deps --workflow workflow.json  # Install workflow deps

Publishing:

comfy node init                        # Init scaffolding
comfy node scaffold                    # Create project via cookiecutter
comfy node validate                    # Validate before publishing
comfy node pack                        # Package node
comfy node publish                     # Publish to registry

Models

comfy model list                       # List available models
comfy model download --url <url>       # Download from URL
comfy model remove <name>              # Remove model

Sources: CivitAI, Hugging Face, direct URLs

Tokens for gated models:

  • --civitai-token or config civitai_api_token
  • --hf-token or config hf_api_token

Run workflows

comfy run --workflow workflow_api.json
comfy run --workflow workflow.json --wait --verbose
comfy run --workflow workflow.json --host 192.168.1.10 --port 8188

Requires running ComfyUI instance.

ComfyUI-Manager

comfy manager disable-gui              # Hide manager in UI
comfy manager enable-gui               # Show manager in UI
comfy manager clear                    # Clear startup actions

Update

comfy update all                       # Update ComfyUI + nodes
comfy update comfy                     # Update ComfyUI only

Other commands

comfy env                              # Show config and paths
comfy --version                        # Print CLI version
comfy pr-cache list                    # List cached PR builds
comfy pr-cache clean                   # Clear expired caches
comfy standalone                       # Create standalone Python bundle
comfy tracking enable|disable          # Manage analytics
comfy feedback                         # Submit feedback

Config

Location:

  • Linux: ~/.config/comfy-cli/config.ini
  • macOS: ~/Library/Application Support/comfy-cli/config.ini
  • Windows: %APPDATA%\Local\comfy-cli\config.ini

Keys: default_workspace, default_launch_extras, civitai_api_token, hf_api_token

Tips

  • --skip-prompt for non-interactive mode (CI/scripts)
  • Background mode tracks PID for clean comfy stop
  • Snapshots preserve exact node versions for reproducibility
  • comfy node bisect binary-searches to find which node broke your setup
  • PR cache avoids rebuilding frontend PRs you've tested before

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

703267

fivem

openclaw

Fix, create, or validate FiveM server resources for QBCore/ESX (config.lua, fxmanifest.lua, items, housing/furniture, scripts, MLOs). Use when asked to debug resource errors, convert ESX↔QB, update fxmanifest versions, add items, or source scripts from GitHub. Also use for SSH key generation for SFTP access.

328193

research-paper-writer

openclaw

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

74165

keyword-research

openclaw

Discovers high-value keywords with search intent analysis, difficulty assessment, and content opportunity mapping. Essential for starting any SEO or GEO content strategy.

429102

weread

openclaw

WeChat Reading (微信读书) CLI tool for fetching notes and highlights. Use when: (1) user asks about weread/微信读书 notes or highlights, (2) fetching today's or recent reading notes, (3) exporting book highlights, (4) managing reading bookshelf, (5) any task involving reading notes from WeChat Reading.

10384

html-to-ppt

openclaw

Convert HTML/Markdown to PowerPoint presentations using Marp

29679

You might also like

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

2,6042,338

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

2,1111,619

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

3,4311,486

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

2,1951,420

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

2,3121,173

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

1,881941