Agent skill

Vibecomfy Setup

by peteromallet in peteromallet/VibeComfy

Set up VibeComfy for local or remote ComfyUI use. An agent skill from peteromallet/VibeComfy.

MITAuto-check passedAI & LLM Engineering

Install Vibecomfy Setup

skills CLI
$ npx skills add peteromallet/VibeComfy --skill vibecomfy-setup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install peteromallet/VibeComfy vibecomfy-setup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/peteromallet/VibeComfy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/agent-skill/skills/vibecomfy-setup .claude/skills/vibecomfy-setup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vibecomfy-setup
GitHub stars
150
Token cost
~1.5k tokens
SKILL.md length
543 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Set up VibeComfy for local or remote ComfyUI use. An agent skill from peteromallet/VibeComfy.

  • Works in 3 steps: Runtime → Custom nodes → Models
  • The user asks to install
  • SKILL.md covers First Conversation, Inspect, Runtime Setup and Custom Nodes, plus 3 more sections
  • Calls python

What it does

Vibecomfy Setup is an agent skill from peteromallet/VibeComfy. Set up VibeComfy for local or remote ComfyUI use. Use when the user asks to install, configure, initialize, connect VibeComfy to ComfyUI, choose between pip-installed ComfyUI and their own ComfyUI checkout, configure customnodes/models paths, reuse existing nodes/models, create isolated libraries, or make vibecomfy run stop warning about missing ComfyUI/config.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Diffusion and image models. It works with ComfyUI. The licence is MIT.

When your agent uses it

  • The user asks to install
  • Connect VibeComfy to ComfyUI
  • Choose between pip-installed ComfyUI and their own ComfyUI checkout
  • Configure customnodes/models paths

Example prompts

  • “/vibecomfy-setup”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Runtime
  2. Custom nodes
  3. Models

What it can do on your machine

Read from SKILL.md and the folder at commit b1429c6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vibecomfy Setup loads about 1.5k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 543 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from peteromallet/VibeComfy at commit b1429c6, republished under its MIT licence (© peteromallet). 543 words, ~1,528 tokens.

Download SKILL.mdSave it as .claude/skills/vibecomfy-setup/SKILL.md (or your agent's skills folder).
name
vibecomfy-setup
description
Set up VibeComfy for local or remote ComfyUI use. Use when the user asks to install, configure, initialize, connect VibeComfy to ComfyUI, choose between pip-installed ComfyUI and their own ComfyUI checkout, configure custom_nodes/models paths, reuse existing nodes/models, create isolated libraries, or make `vibecomfy run` stop warning about missing ComfyUI/config.

VibeComfy Setup

Use this when the environment is the problem: VibeComfy cannot find ComfyUI, the user wants to reuse or isolate their custom_nodes / models, or a run needs to target an existing ComfyUI server.

The good setup is explicit. Pick a runtime, pick node/model libraries only when they matter, dry-run dependency changes, then verify.

First Conversation

Before mutating the user's machine, ask for three choices:

  1. Runtime

    • installed/importable comfy package
    • the user's own ComfyUI checkout path
    • an already-running ComfyUI server URL
  2. Custom nodes

    • reuse an existing custom_nodes
    • create/use an isolated custom_nodes
    • skip local custom-node setup for now
  3. Models

    • reuse an existing models
    • create/use an isolated models
    • skip local model setup for now

Also ask whether the config should be global (~/.vibecomfy/config.toml) or repo-local (./vibecomfy.toml). Use global for a personal workstation unless the user wants this checkout to carry the setup.

If they choose an existing server URL, do not force local ComfyUI setup. External server runs only need local node/model paths when VibeComfy is staging files or preparing dependencies on a shared filesystem.

Inspect

Run from the repo root:

bash
vibecomfy config show --json
vibecomfy runtime doctor

If the console script is unavailable in an editable checkout, use python -m vibecomfy.cli ....

Know the two resolution paths:

  • vibecomfy config init detects ComfyUI from COMFYUI_PATH, an importable comfy package, ~/ComfyUI, then the current directory if it has custom_nodes or models.
  • Library paths used by config/model/node helpers prefer env vars first (VIBECOMFY_CUSTOM_NODES_DIR, VIBECOMFY_MODELS_ROOT, COMFY_MODELS_ROOT), then repo config, then global config.

Runtime Setup

For an importable/pip ComfyUI:

bash
python - <<'PY'
import comfy
from pathlib import Path
root = Path(comfy.__file__).resolve().parent.parent
print(root)
print(root / "custom_nodes")
print(root / "models")
PY
vibecomfy config init --yes

For the user's own checkout:

bash
export COMFYUI_PATH=/absolute/path/to/ComfyUI
test -d "$COMFYUI_PATH/custom_nodes"
test -d "$COMFYUI_PATH/models"
vibecomfy config set-library \
  --custom-nodes "$COMFYUI_PATH/custom_nodes" \
  --models "$COMFYUI_PATH/models"

Add --repo to config init or config set-library only when the user wants repo-local config.

For an existing server:

bash
vibecomfy run <workflow.py> --runtime server --server-url http://host:8188
vibecomfy run image/z_image --ready --runtime server --server-url http://host:8188

Python workflows work here: VibeComfy imports build(), compiles the returned VibeWorkflow to ComfyUI API JSON, and queues it to the server.

Show full SKILL.md (251 more words)Show less

Custom Nodes

For python_node.from_installed(...), prepare the actual selected ComfyUI worker and its Python distributions explicitly. Inspection and validation only report readiness; they never install or import the package. Use a complete from_source(...) capsule when the implementation should travel with the workflow, observing its bounded file/archive limits and relative-entrypoint rule. The worker still needs any declared third-party distributions in either mode.

Reuse an existing library:

bash
vibecomfy config set-library --custom-nodes /absolute/path/to/custom_nodes
vibecomfy nodes restore

Use an isolated library:

bash
mkdir -p /absolute/path/to/new-custom_nodes
vibecomfy config set-library --custom-nodes /absolute/path/to/new-custom_nodes --force
vibecomfy nodes restore

Plan before installing:

bash
vibecomfy nodes install-plan <workflow>
vibecomfy nodes ensure --workflow <workflow>
vibecomfy nodes ensure --template <ready_id>

Caveat: nodes restore and single-pack nodes install honor the configured custom-node root. nodes ensure currently installs through the package default custom_nodes path, so verify the install destination before claiming an isolated library was populated.

Skip local nodes:

bash
vibecomfy config set-library --no-custom-nodes

Models

Reuse an existing library:

bash
vibecomfy config set-library --models /absolute/path/to/models

Use an isolated library:

bash
mkdir -p /absolute/path/to/new-models
vibecomfy config set-library --models /absolute/path/to/new-models --force

Plan before downloading:

bash
vibecomfy models stage --select-phase core --dry-run
vibecomfy fetch <workflow> --dry-run

Then install only after the user agrees:

bash
vibecomfy models stage --select-phase core
vibecomfy fetch <workflow>

Skip local models:

bash
vibecomfy config set-library --no-models

Verify

Finish every setup with the canonical candidate still represented by Python; use API JSON only at the runtime boundary:

bash
vibecomfy config show --json
vibecomfy runtime doctor
vibecomfy inspect <workflow>
vibecomfy doctor <workflow> --json

If embedded runtime still cannot find a ComfyUI root or comfy module, local embedded execution is not ready. Either set COMFYUI_PATH, install/import comfy in the active environment, or run with --runtime server --server-url ....

Default Path

When the user has no strong preference:

  1. Run vibecomfy config init --yes.
  2. If ComfyUI is not detected, ask for a ComfyUI path or server URL.
  3. Reuse real existing custom_nodes and models.
  4. Use isolated dirs only when they want to protect their current ComfyUI setup.
  5. Dry-run dependency changes before installs/downloads.
  6. Run runtime doctor, inspect, and doctor before handing off to run-comfy-workflow.

© peteromallet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in docs/agent-skill/skills/vibecomfy-setup of peteromallet/VibeComfy.

Open the folder on GitHubat commit b1429c6

Compare with similar skills

Vibecomfy Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vibecomfy Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vibecomfy Setup this skillpeteromallet/VibeComfy150—~1.5kAutomated safety check: PassMIT
Comfyui AnimatoolShiroEirin/comfyui-good-anima478—~4.6kAutomated safety check: PassGPL-3.0
Comfyui Agent Skill MieMieMieeeee/comfyui-agent-skill116—~3.9kAutomated safety check: PassApache-2.0
Importing SubgraphsComfy-Org/workflow_templates1.3k—~1.5kAutomated safety check: PassMIT
Comfyui Node Addernixified-ai/flake841—~806Automated safety check: PassAGPL-3.0
Managing BundlesComfy-Org/workflow_templates1.3k—~1.2kAutomated safety check: PassMIT

Similar skills

  • Comfyui Animatool

    ShiroEirin/comfyui-good-anima

    Route ALL Anima image generation: validate Danbooru hard anchors, form visual brief, assemble English prompts and args, then load comfyui-manager for workflow execution.

    478 GitHub stars~4.6k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed
  • Comfyui Agent Skill Mie

    MieMieeeee/comfyui-agent-skill

    Agent skill for running registered ComfyUI workflows through a stable CLI, and for importing a user's own ComfyUI workflow into their private registry after review.

    116 GitHub stars~3.9k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed
  • Importing Subgraphs

    Comfy-Org/workflow_templates

    Imports and registers subgraph blueprints into the ComfyUI workflowtemplates repository.

    1.3k GitHub stars~1.5k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Comfyui Node Adder

    nixified-ai/flake

    Adds new custom nodes to the ComfyUI Nix project, including npins fetching, dependency resolution in package.nix, disabling impure pip installs, and verifying the Nix build.

    841 GitHub stars~806 tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Managing Bundles

    Comfy-Org/workflow_templates

    Manages template bundles, categories, and ordering in the ComfyUI template repository.

    1.3k GitHub stars~1.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Headroom

    momori777/Artemis

    SmartCrusher + CCR context compression — crunch large JSON arrays, tool outputs, and search results to save tokens.

    377 GitHub stars~562 tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed

More from peteromallet/VibeComfy

All 9 skills in this repo
  • Add Comfy Workflow Template

    peteromallet/VibeComfy

    Add a durable VibeComfy ready workflow/template from a ComfyUI source workflow.

    150 GitHub stars~700 tokensUpdated 6 days ago
    Auto-check passed
  • Debug Comfy Workflow

    peteromallet/VibeComfy

    Diagnose a VibeComfy or ComfyUI workflow that fails validation, conversion, node/model resolution, runtime execution, or output production.

    150 GitHub stars~609 tokensUpdated 6 days ago
    Auto-check passed
  • Edit Comfy Workflow

    peteromallet/VibeComfy

    Edit an existing VibeComfy or ComfyUI workflow, ready template, recipe, scratchpad, or target graph.

    150 GitHub stars~2.2k tokensUpdated 6 days ago
    Auto-check passed
  • Explain Comfy Workflow

    peteromallet/VibeComfy

    Explain an existing VibeComfy or ComfyUI workflow, ready template, recipe, scratchpad, target graph, node chain, model path, prompt path, or runtime result.

    150 GitHub stars~806 tokensUpdated 6 days ago
    Auto-check passed
  • Reorganise Comfy Workflow

    peteromallet/VibeComfy

    Reorganise an existing ComfyUI workflow layout without changing runtime behavior.

    150 GitHub stars~1.4k tokensUpdated 6 days ago
    Auto-check passed
  • Run Comfy Workflow

    peteromallet/VibeComfy

    Execute an existing VibeComfy/ComfyUI workflow, ready template, recipe, or scratchpad and collect outputs.

    150 GitHub stars~1.8k tokensUpdated 6 days ago
    Auto-check passed

Works with

Questions about Vibecomfy Setup

What does Vibecomfy Setup do?

Set up VibeComfy for local or remote ComfyUI use. An agent skill from peteromallet/VibeComfy. Vibecomfy Setup is an agent skill from peteromallet/VibeComfy. Set up VibeComfy for local or remote ComfyUI use.

When should I use Vibecomfy Setup?

Vibecomfy Setup fits situations like: the user asks to install; connect VibeComfy to ComfyUI; choose between pip-installed ComfyUI and their own ComfyUI checkout; configure customnodes/models paths.

How do I install Vibecomfy Setup in Claude Code?

Run `npx skills add peteromallet/VibeComfy --skill vibecomfy-setup -a claude-code`. Or copy the skill folder (docs/agent-skill/skills/vibecomfy-setup in peteromallet/VibeComfy) into .claude/skills/vibecomfy-setup in your project. Claude Code loads it when a task matches its description.

How do I install Vibecomfy Setup in Codex?

Run `npx skills add peteromallet/VibeComfy --skill vibecomfy-setup -a codex`. Or copy the skill folder (docs/agent-skill/skills/vibecomfy-setup in peteromallet/VibeComfy) into .agents/skills/vibecomfy-setup in your project. Codex loads it when a task matches its description.

Can I use Vibecomfy Setup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add peteromallet/VibeComfy --skill vibecomfy-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vibecomfy-setup, .gemini/skills/vibecomfy-setup, .github/skills/vibecomfy-setup and .opencode/skills/vibecomfy-setup in your project.

What does Vibecomfy Setup need to run?

Going by SKILL.md and its folder, Vibecomfy Setup needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Vibecomfy Setup access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vibecomfy Setup safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vibecomfy Setup use?

Vibecomfy Setup is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vibecomfy Setup use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vibecomfy Setup?

Skills that share tags, products or a category with Vibecomfy Setup: Comfyui Animatool (ShiroEirin/comfyui-good-anima, 478 stars), Comfyui Agent Skill Mie (MieMieeeee/comfyui-agent-skill, 116 stars), Importing Subgraphs (Comfy-Org/workflow_templates, 1.3k stars) and Comfyui Node Adder (nixified-ai/flake, 841 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vibecomfy Setup?

peteromallet (a GitHub user) maintains it in peteromallet/VibeComfy, which has 150 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 1, 2026.

Source: peteromallet/VibeComfy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.