agentleFS
rakaarwakyrakaarwaky/agents-arwaky/skills/content-creation/comfyui/SKILL.md

comfyui

Skill0 starsChanged 4 days agoMITView on GitHub

Generate images, video, and audio via ComfyUI diffusion workflows.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use touchdesigner-mcp, bfl-api and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 6 projects that use this

  • LinHao-citySkill

    bfl-api

    BFL FLUX API integration guide covering endpoints, async polling patterns, rate limiting, error handling, webhooks, and regional endpoints with Python and TypeScript code examples.

    Also in 3 projects that use this

  • LinHao-citySkill

    flux-best-practices

    Comprehensive guide for BFL FLUX image generation models. Covers prompting, T2I, I2I, structured JSON, hex colors, typography, multi-reference editing, and model-specific best practices for FLUX.2 and FLUX.1 families.

    Also in 3 projects that use this

  • john-data-chenSkill

    teams-meeting-pipeline

    Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.

    Also in 6 projects that use this

  • +6 more from LinHao-city

The file

Files
SKILL.md

ComfyUI

You generate images, video, and audio through ComfyUI using the official comfy-cli for setup/lifecycle and the REST/WebSocket API plus the shipped scripts for workflow execution.

Global Rules

  • Two layers. comfy-cli owns install, server lifecycle, nodes, and models; the REST/WebSocket API plus the skill scripts own execution, parameter injection, monitoring, and downloads — the CLI barely executes workflows.
  • API format is required. Editor-format workflow JSON (top-level nodes/links) is not directly executable; re-export via the web UI (Workflow → Export (API)). Node types and param mapping: references/workflow-format.md; converting official editor templates: references/template-integrity.md.
  • Scripts own the fragile bits. Scripts in scripts/ handle credential and dependency errors themselves; run health_check.py as the single end-to-end verification instead of piecing the checklist together.
  • Untrusted workflow JSON is arbitrary code. Inspect any community or downloaded workflow before running it.
  • Video and cloud. Video workflows need longer timeouts (--timeout 1800); the cloud free tier is read-only — API execution needs a paid subscription.
  • Completion. health_check.py reports every gate green, a test run with a small workflow completes, and its outputs land in --output-dir.

Routing

StepReferencePurpose
Setup & onboardingreferences/setup-onboarding.mdAsk Local vs Cloud first, install Paths A–E, model and node install.
Advanced operationsreferences/advanced-operations.mdImage upload, cloud endpoint quirks, queue management.
Core workflowreferences/workflow.mdGet an API-format workflow, see what's controllable, run with parameters, present results.
CLI referencereferences/official-cli.mdEvery comfy ... command and flag.
REST/WS referencereferences/rest-api.mdREST + WebSocket endpoints (local and cloud), payload schemas.
Workflow formatreferences/workflow-format.mdAPI-format JSON, common node types, parameter mapping.
Template integrityreferences/template-integrity.mdConverting official editor-format templates to API format.
Run examplesreferences/run-examples.mdrun_workflow.py and run_batch.py flag examples.
Decision treereferences/decision-tree.md"User says X → run Y" mapping across CLI, scripts, and REST.
Scriptsscripts/ (helper: scripts/_common.py)hardware_check.py, comfyui_setup.sh, extract_schema.py, check_deps.py, auto_fix_deps.py, run_workflow.py, run_batch.py, ws_monitor.py, health_check.py, fetch_logs.py.
Example workflowsworkflows/SD 1.5, SDXL, Flux Dev, SDXL img2img/inpaint, ESRGAN upscale, AnimateDiff video, Wan T2V.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.