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

comfyui-troubleshoot

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Diagnose ComfyUI connection failures, invalid workflows, unknown node classes, missing required inputs, missing models, queue and history problems, generation errors, VRAM pressure, remote-target confusion, and dependency issues without random installs or broad destructive changes.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Check input uploads and server-returned filenames.

    line 26
  2. Distinctive:

    Check free VRAM for heavy execution failures.

    line 27
  3. Distinctive:

    Do not solve a connection problem by exposing ComfyUI on all network interfaces without explicit user intent and an appropriate security …

    line 45

≈ “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 Troubleshoot

Read

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

Order

  1. Confirm the exact server URL and whether it is local or remote.
  2. Probe system stats and queue state.
  3. Capture the exact HTTP error, ComfyUI execution error, and node_errors.
  4. Validate workflow format.
  5. Compare required class types against live /object_info.
  6. Compare loader selections against live input choices or model categories.
  7. Check input uploads and server-returned filenames.
  8. Check free VRAM for heavy execution failures.
  9. Identify the smallest corrective action.
  10. Revalidate before rerunning.

Missing node

An unknown class does not justify guessing a repository. If comfy-cli or comfy-mcp can resolve workflow dependencies to a registry package, present that package and obtain approval before installation.

Missing model

Report the exact loader node, required value, and live available choices. Do not rename a different model into place or download a large replacement without user intent.

VRAM

POST /free can unload ComfyUI-held models and cache. It cannot free memory held by another application. Do not claim it can stop or unload an external LLM runtime.

Connection

Do not solve a connection problem by exposing ComfyUI on all network interfaces without explicit user intent and an appropriate security boundary.

Done

The root cause is tied to observed server/workflow evidence, and the proposed fix is the smallest change that addresses it.

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.