agentleFS
badgidsbadgids/comfyui-development-skills/skills/comfyui-subgraphs/SKILL.md

comfyui-subgraphs

Skill4 starsChanged 44 days agoMITView on GitHub

Use when creating, modifying, validating, documenting, or packaging ComfyUI subgraphs or Subgraph Blueprints, or when composing workflows from reusable graph components.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Verify every contained node against the live target when possible.

    line 23
  2. Distinctive:

    Check serialization and reload behavior in the target frontend.

    line 27
  3. Distinctive:

    Before calling a subgraph or blueprint complete:

    line 33
  4. Distinctive:

    verify the representation against the target/current schema.

    line 35
  5. Distinctive:

    verify external inputs and outputs.

    line 37
  6. Distinctive:

    test serialization and reload behavior when practical.

    line 38
  7. Distinctive:

    use the subgraph inside a representative workflow.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Subgraphs

Sources

Use current/version-matched:

  • workflow/subgraph documentation in Comfy-Org/docs;
  • Comfy-Org/Subgraph-Blueprints;
  • relevant Comfy-Org/ComfyUI_frontend implementation;
  • workflow schema/source;
  • live target node catalog.

Procedure

  1. Identify the target ComfyUI/frontend version.
  2. Inspect the current subgraph/blueprint representation instead of assuming fields.
  3. Verify every contained node against the live target when possible.
  4. Define clear external inputs/outputs and avoid hidden install-specific assumptions.
  5. Preserve stable identifiers when editing existing reusable components unless regeneration is required.
  6. Validate expansion/use inside a representative workflow.
  7. Check serialization and reload behavior in the target frontend.

Official blueprints are patterns, not a substitute for checking the current schema/runtime.

Acceptance gate

Before calling a subgraph or blueprint complete:

  • verify the representation against the target/current schema;
  • validate contained nodes against the target when reachable;
  • verify external inputs and outputs;
  • test serialization and reload behavior when practical;
  • use the subgraph inside a representative workflow;
  • state clearly when frontend/runtime checks could not be run.

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.