agentleFS
witnesstodarkwitnesstodark/mr-mak-workspace/.agents/skills/higgsfield-workflow/SKILL.md

higgsfield-workflow

Skill800 starsChanged 23 days agoMITView on GitHub

Use the official Higgsfield CLI or its Blender integration to discover models, generate requested assets and resume recorded jobs.

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:

    Keep estimated credits separate from observed billing.

    line 31
  2. Distinctive:

    Do not replay numbered project scripts that can submit jobs or depend on old checkpoints.

    line 35

≈ “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

Higgsfield operations

Install the official CLI and vendor skills from their maintained sources. Use the recipient's own account. The CLI and a Blender-native integration have different execution contexts; preserve the working route selected by the task.

Read-only discovery:

higgsfield --version
higgsfield model list --json
higgsfield model get <job-type> --json
higgsfield workflow list --json
higgsfield generate get <job-id> --json

Inspect the exact model's input/media schema before creating a job. A display name, fal endpoint and Higgsfield job type are different identifiers. Model IDs and supported flags can change; use the current CLI help and catalog. Do not replace the user's chosen provider or model with a skill's historical default.

For a requested generation, use the current generate create syntax, with the chosen job type and required inputs. Save the returned job ID immediately. Resume a slow job using generate get or generate wait; a waiting timeout does not justify submitting it again. Inspect a terminal error before retrying. Keep estimated credits separate from observed billing.

Download outputs and inspect them. For Blender integration, verify that the asset was imported and the scene saved, not merely that the remote job finished. Do not replay numbered project scripts that can submit jobs or depend on old checkpoints. They are not necessarily safe to run twice.

Example: request one prop from a supplied reference, save its job ID, download the model and verify materials in a disposable Blender scene. Do not claim a rigged or game-ready result from successful mesh generation alone.

Dependencies: official CLI, vendor skills, an account, and the Blender companion only when that route is used. Vendor tools are not copied here.

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.