agentleFS
Sign inStart free
badgidsbadgids/Story-Film-Skills/skills/comfyui-run/SKILL.md

comfyui-run

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Execute API-format workflows on ComfyUI, keep prompt IDs, poll authoritative history, inspect queue state, cancel selected runs, free ComfyUI memory, capture errors, and record outputs for story-film production.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write a run record under 04_generation/comfyui/runs/ without credentials.

    line 27
  2. Distinctive:

    Prefer targeted job cancellation.

    line 42
  3. Distinctive:

    If the workflow contains partner/API nodes and execution can consume credits, confirm the intended paid run before submission when the user …

    line 46

≈ “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 Run

Read

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

Procedure

  1. Probe the intended server.
  2. Validate the API workflow when practical.
  3. Upload required inputs first.
  4. Submit the workflow and retain prompt_id. When a stable story-film item is being rendered, pass its ID and append the mapping to the project run index at submit time.
  5. For long work, return control to the agent and poll history rather than using one opaque blocking shell command.
  6. On failure, retain the server error and node errors.
  7. On completion, extract both media outputs and text outputs.
  8. Download requested media through the server output endpoint.
  9. Write a run record under 04_generation/comfyui/runs/ without credentials.

Bundled commands:

python scripts/comfyui_control.py --project PROJECT submit --workflow WORKFLOW.json --item-id SHOT-001
python scripts/comfyui_control.py wait PROMPT_ID
python scripts/comfyui_control.py queue
python scripts/comfyui_control.py history --prompt-id PROMPT_ID
python scripts/comfyui_control.py cancel PROMPT_ID
python scripts/comfyui_control.py free --unload-models

Cancellation

Prefer targeted job cancellation. Do not clear every queued job to stop one run.

Paid nodes

If the workflow contains partner/API nodes and execution can consume credits, confirm the intended paid run before submission when the user has not already requested it.

Done

The exact run has a prompt ID, final state, preserved error details if any, and project-linked outputs.

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.

Check your setup, free