agentleFS
badgidsbadgids/comfyui-development-skills/skills/comfyui-workflow-validation/SKILL.md

comfyui-workflow-validation

Skill4 starsChanged 44 days agoMITView on GitHub

Use when a ComfyUI workflow fails to load, validate, queue, execute, or produce expected outputs, or when checking node availability, links, inputs, models, workflow JSON, frontend/API representation, or compatibility before execution.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    If validation is happening because a comfy-cli job failed, inspect the current/version-matched CLI debugging guidance in addition to this …

    line 25
  2. Distinctive:

    Prefer the running target's node definitions over a bundled/static catalog.

    line 29
  3. Very specific:

    When comfy-cli, comfy-mcp, or the official test framework is installed, inspect its current help/docs and use the relevant validation …

    line 35
  4. Distinctive:

    Check whether custom-node imports failed at startup.

    line 45
  5. Distinctive:

    Check resource/model names against target choices.

    line 46
  6. Distinctive:

    Before calling a workflow fixed or valid:

    line 60

≈ “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 Workflow Validation

Validation layers

Validate in this order where applicable:

  1. JSON parse and representation detection;
  2. current/version-matched workflow schema;
  3. live node existence;
  4. input names and required values;
  5. output/link compatibility;
  6. enum/model/resource values exposed by the target;
  7. custom-node-specific constraints;
  8. official validator/test framework when available;
  9. representative execution only after preflight passes.

CLI failure guidance

If validation is happening because a comfy-cli job failed, inspect the current/version-matched CLI debugging guidance in addition to this structural validation skill. Use the CLI guidance for its error envelope and remediation flow; use the target schema/node catalog for workflow correctness.

Live catalog

Prefer the running target's node definitions over a bundled/static catalog. A static catalog cannot prove that the user's installed custom nodes match it.

If the comfyui-development skill is available, use its conservative workflow-preflight helper as a fallback. Activate that skill through the harness rather than assuming its files are reachable from this skill directory. The fallback is not a substitute for a stronger current official validator when one is available.

Official tooling

When comfy-cli, comfy-mcp, or the official test framework is installed, inspect its current help/docs and use the relevant validation command. Do not assume command syntax from an old version.

A command invocation succeeding is not the same as a valid workflow. Read the returned verdict/errors.

Debugging procedure

  1. Preserve the failing workflow before edits.
  2. Capture exact error text and server/browser logs.
  3. Determine frontend vs API representation.
  4. Compare failing node definitions with live target data.
  5. Check whether custom-node imports failed at startup.
  6. Check resource/model names against target choices.
  7. Reduce to a minimal failing graph if the cause remains unclear.
  8. Make one causal fix at a time.
  9. Revalidate.

Do not

  • randomly rewire sockets until the error disappears;
  • replace missing nodes with unrelated alternatives without explaining the semantic change;
  • clear queues/history or delete user data as a diagnostic shortcut;
  • upgrade the user's installation unless the task is specifically an upgrade.

Acceptance gate

Before calling a workflow fixed or valid:

  • preserve the original failing workflow;
  • capture the exact failure evidence;
  • identify the workflow representation;
  • resolve all deterministic validation errors found by the strongest available validator;
  • re-run validation after the fix;
  • report any live/runtime gate that could not be completed instead of treating it as a pass.

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.