agentleFS
badgidsbadgids/Story-Film-Skills/skills/comfyui-assets/SKILL.md

comfyui-assets

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Stage ComfyUI workflow input media through server uploads, use returned server names instead of guessed paths, extract all file-shaped outputs from history, download outputs safely, and keep project-relative media records.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not copy arbitrary host filesystem paths into workflow JSON.

    line 22
  2. Distinctive:

    Read the completed history record.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ComfyUI Assets

Read

  • ../../references/COMFYUI_NATIVE_API.md
  • ../../references/COMFYUI_SECURITY.md

Input procedure

  1. Confirm the local source file exists.
  2. Upload it as an input asset.
  3. Record the returned name, subfolder, and type.
  4. Patch the workflow input using those returned values or the exact loader format required by the live node schema.
  5. Do not copy arbitrary host filesystem paths into workflow JSON.

Bundled command:

python scripts/comfyui_control.py upload PATH --subfolder project-inputs

Output procedure

  1. Read the completed history record.
  2. Inspect every node output for file-shaped records containing filename.
  3. Preserve the producing node ID.
  4. Download through /view using filename, subfolder, and type.
  5. Sanitize local filenames and keep results under the project output directory requested by the user.

Bundled commands:

python scripts/comfyui_control.py outputs PROMPT_ID
python scripts/comfyui_control.py download PROMPT_ID --out-dir 04_generation/comfyui/outputs

Done

Inputs use server-recognized references and outputs are downloaded without arbitrary path construction or loss of producing-node identity.

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.