image

Run local ComfyUI workflows via the HTTP API. Use when the user asks to run ComfyUI, execute a workflow by file path/name, or supply raw API-format JSON; sup...

Security Scan

The skill's code, instructions, and resource access line up with its stated purpose (running local ComfyUI workflows); nothing requests unrelated credentials or hidden endpoints, though it will write files under your home and download user-supplied model files and a helper binary when asked.

Purpose & Capability

Name/description (ComfyUI runner) match the included scripts and SKILL.md: editing workflow JSON, queuing via the local ComfyUI HTTP API, and downloading model weights are all expected capabilities for this skill.

Instruction Scope

SKILL.md explicitly instructs the agent to read and edit workflow JSON, write a temp JSON, post to a local server (127.0.0.1:8188), and optionally clone/install/start ComfyUI if missing. These actions are within the skill's purpose but give the agent broad discretion to modify workflow files (which may contain sensitive or disallowed prompts). The shipped sample tmp-workflow.json contains an explicit nudity prompt — the agent is instructed to inspect and may run user-supplied or default workflows, so review workflows before running.

Install Mechanism

There is no formal install spec (instruction-only), but the download_weights script can fetch a pget binary from GitHub releases and will write it to ~/.local/bin if missing. Downloading a binary from GitHub releases and saving it to ~/.local/bin is expected for parallel download support but is a higher‑privilege filesystem write than pure instruction-only skills. The pget URL is a GitHub releases host (reasonable), and fallback downloads use Python urllib.

Credentials

The skill does not request environment variables or secrets. It writes files under ~/ComfyUI/models/ and ~/.local/bin/ (pget) and expects a ComfyUI venv at ~/ComfyUI/venv — these file-path needs are coherent with the skill's stated purpose and proportionate to running local ComfyUI workflows.

Persistence & Privilege

The skill is not configured always:true and does not request system-wide configuration changes. Its behavior (writing temp workflow files, saving downloaded model weights, installing pget binary to ~/.local/bin) is normal for a local runner and limited in scope to the user's home directory.

Assessment

This skill appears to do what it says: edit workflow JSON, queue jobs to your local ComfyUI server, and download model weights you provide. Before installing or running: 1) Confirm you trust any model URLs you provide — they will be downloaded into ~/ComfyUI/models and executed by your local model runtime. 2) Review any workflow JSON (default or user-supplied) before running; the agent is instructed to edit and run those files and the sample tmp-workflow includes an explicit nudity prompt. 3) Be aware the download helper may fetch and save the pget binary from GitHub to ~/.local/bin for parallel downloads; verify that URL if you have strict policies. 4) Ensure ~/ComfyUI (and its venv) paths match your environment — SKILL.md expects ~/ComfyUI/venv/bin/python. 5) If you do not want the skill to write files or install pget, do not provide model URL lists or decline installs. Overall the skill is internally consistent with its purpose; review workflows and model sources before running.

ComfyUI Runner

Overview

Run ComfyUI workflows on the local server (default 127.0.0.1:8188) using API-format JSON and return output images.

Editing the workflow before running

The run script only takes --workflow <path>. You must inspect and edit the workflow JSON before running, using your best knowledge of the ComfyUI API format. Do not assume fixed node IDs, class_type names, or _meta.title values — the user may have updated the default workflow or supplied a custom one.

For every run (including the default workflow):

1. Read the workflow JSON (default: skills/comfyui/assets/default-workflow.json, or the path/file the user gave).
2. Identify prompt-related nodes by inspecting the graph: look for nodes that hold the main text prompt — e.g. PrimitiveStringMultiline, CLIPTextEncode (positive text), or any node with _meta.title or class_type suggesting "Prompt" / "positive" / "text". Update the corresponding input (e.g. inputs.value, or the text input to the encoder) to the image prompt you derived from the user (subject, style, lighting, quality). If the user didn't ask for a custom image, you can leave the existing prompt or tweak only if needed.
3. Optionally identify style/prefix nodes — e.g. StringConcatenate, or a second string input that acts as style. Set them if the user asked for a specific style or to clear a default prefix.
4. Optionally set a new seed — find sampler-like nodes (e.g. KSampler, BasicGuider, or any node with a seed input) and set seed to a new random integer so each run can differ.
5. Write the modified workflow to a temp file (e.g. skills/comfyui/assets/tmp-workflow.json). Use ~/ComfyUI/venv/bin/python for any inline Python; do not use bare python.
6. Run: comfyui_run.py --workflow <path-to-edited-json>.

If the workflow structure is unclear or you can't find prompt/sampler nodes, run the file as-is and only change what you can reliably identify. Same approach for arbitrary user-supplied JSON: inspect first, edit at your best knowledge, then run.

Run script (single responsibility)

~/ComfyUI/venv/bin/python skills/comfyui/scripts/comfyui_run.py \
  --workflow <path-to-workflow.json>

The script only queues the workflow and polls until done. It prints JSON with prompt_id and output images. All prompt/style/seed changes are done by you in the JSON beforehand.

If the server isn't reachable

If the run script fails with a connection error (e.g. connection refused or timeout to 127.0.0.1:8188), ComfyUI may not be installed or not running.

Check: Does ~/ComfyUI exist and contain main.py?

• If not installed: Install ComfyUI (e.g. clone the repo, create a venv, install dependencies, then start the server). Example:

  git clone https://github.com/comfyanonymous/ComfyUI.git ~/ComfyUI
  cd ~/ComfyUI
  python3 -m venv venv
  ~/ComfyUI/venv/bin/pip install -r requirements.txt
  

  Then start the server (see below). Tell the user they may need to install model weights into ~/ComfyUI/models/ depending on the workflow.

• If installed but not running: Start the ComfyUI server so the API is available on port 8188. Example:

  ~/ComfyUI/venv/bin/python ~/ComfyUI/main.py --listen 127.0.0.1
  

  Run in the background or in a separate terminal so it keeps running. Then retry the workflow run.

Use ~ (or the user's home) for paths so it works on their machine.

Model weights from URLs

When the user pastes or sends a list of model weight URLs (one per line, or comma-separated), download those files into the ComfyUI installation so the workflow can use them later.

1. Normalize the list — one URL per line; strip empty lines and comments (lines starting with #).
2. Run the download script with the ComfyUI base path (default ~/ComfyUI). The script uses pget for parallel downloads when available; if pget is not in PATH, it installs it to ~/.local/bin automatically (no sudo). If pget cannot be installed (e.g. unsupported OS/arch), it falls back to a built-in download. Use the ComfyUI venv Python so the script runs correctly:

   ~/ComfyUI/venv/bin/python skills/comfyui/scripts/download_weights.py --base ~/ComfyUI
   

   Pass URLs as arguments, or pipe a file/list on stdin:

   echo "https://example.com/model.safetensors" | ~/ComfyUI/venv/bin/python skills/comfyui/scripts/download_weights.py --base ~/ComfyUI
   

   Or save the user's list to a temp file and run:

   ~/ComfyUI/venv/bin/python skills/comfyui/scripts/download_weights.py --base ~/ComfyUI < /tmp/weight_urls.txt
   

   To force the built-in download (no pget): add --no-pget.
3. Subfolder: The script infers the ComfyUI models subfolder from the URL/filename (e.g. vae, clip, loras, checkpoints, text_encoders, controlnet, upscale_models). The user can optionally specify a subfolder per line as url subfolder (e.g. https://.../model.safetensors vae). You can also pass a default with --subfolder loras so all URLs in that run go to models/loras/.
4. Existing files: By default the script skips URLs that already exist on disk; use --overwrite to replace.
5. Paths: Files are written under ~/ComfyUI/models/<subfolder>/. Tell the user where each file was saved and that they can run the workflow once the ComfyUI server is (re)started if needed.

Supported subfolders (under ComfyUI/models/): checkpoints, clip, clip_vision, controlnet, diffusion_models, embeddings, loras, text_encoders, unet, vae, vae_approx, upscale_models, and others. Use --subfolder <name> when the auto-inference is wrong.

After run

Outputs are saved under ComfyUI/output/. Use the images list from the script output to locate the files (filename + subfolder).

Always send the output to the user

After a successful ComfyUI run, you must deliver the generated image(s) to the user. Do not reply with only the filename in text or with NO_REPLY.

1. Parse the script output JSON for images (each has filename, subfolder, type).
2. Build the full path: ComfyUI/output/ + subfolder + filename (e.g. ComfyUI/output/z-image_00007_.png).
3. Send the image to the user via the channel they're on (e.g. use the message/send tool with the image path so the user receives the file). Include a short caption if helpful (e.g. "Here you go." or "Tokyo street scene.").

Every successful run must result in the user receiving the image. Never leave them with only a filename or no delivery.

Resources

scripts/

• comfyui_run.py: Queue a workflow, poll until completion, print prompt_id and images. No args — you edit the JSON before running.
• download_weights.py: Download model weight URLs into ~/ComfyUI/models/<subfolder>/. Uses pget when available (installs to ~/.local/bin if missing); fallback to built-in download. Input: URLs as args or one per line on stdin. Options: --base, --subfolder, --overwrite, --no-pget. Infers subfolder from URL/filename when not given.

assets/

• default-workflow.json: Default workflow. Copy and edit (prompt, style, seed) then run with the edited path; or run as-is for a generic run.