Skip to content
Back to skills

Models

ASecurity

Make coherent 3D assets through the official fal MCP, then optimize, register and check them in the studio.

  • 1,531 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
ai-agentsnodeperformance

Works with

  • cli
  • mcp

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned November 7, 2026

npx -y skills add hashgraph-online/awesome-codex-plugins --skill models --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Models?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Models
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hashgraph-online-models/badge)](https://www.skillsdirectory.com/skills/hashgraph-online-models)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: models
description: "Make coherent 3D assets through the official fal MCP, then optimize, register and check them in the studio."
compatibility: Node 22 and Tripo models through the official fal plugin in the AI client. Local media processing uses ffmpeg and Chrome where needed.
metadata:
  providers: fal tripo
---

# Models that fit the game

Start with Homie's CC0 starter library (`homie-studio assets`) when it fits. Read the
locked style, character proportions, scale and performance budgets before generating.
For a new prop, generate and inspect one clean concept first, then a mesh. For a
character, specify a full body A-pose, readable silhouette and the required skeleton.
Use a coherent family; avoid mixing unrelated material styles and proportions.

Use fal's `recommend_model`/`search_models`, `get_model_schema` and `get_pricing` for
each image, mesh and rig step. No model or price is permanently pinned in Homie.
Use `run_model` for the concept and `submit_job`, `check_job`, `get_job_result` for 3D.
Inspect the concept before paying for a mesh. Request only schema-supported rig fields.

Import a completed GLB with `homie-studio assets add`; use its current `--help` for
scale, rig and clip options. Retain original generation receipts and register the
optimized result's licence and provenance. `scripts/models.mjs import` also accepts
an already completed connector receipt and local GLB; it never runs a provider.
For a completed connector job, the local import command is:

```sh
node <path-to-models.mjs> import <id> <asset> --receipt <job.json> --file <model.glb>
```

If a registered asset is deliberately not placed, mark it accurately with
`homie-studio assets use <id> <asset> unused`. Never report an unused model as visible.

Inspect bounds, normals, textures, silhouettes and pivot; run `assets check`, check
triangles/draw calls/texture memory on a phone, and test animation in the actual scene.
A generated rig is not proof that Homie's clips retarget correctly.

## Official generation workflow

The owner's AI uses the provider's official plugin/MCP in its own client. Homie never
asks for, stores, reads or prints provider credentials. Read the current provider
skill and discover its available tools and input schemas; host prefixes vary.
Connection instructions and verified sources: [official integrations](../studio-setup/references/OFFICIAL-MEDIA.md).
If tools are missing, connect that official plugin once in the client's browser flow.
Do not fall back to a Homie client, key file, environment key or CLI generation wrapper.

Before spending, state the model, count/duration, estimated cost and remaining approved
budget. Use the owner's existing authorization; ask only if the spend is outside it.
Record the request ID as soon as accepted. Poll that same request; never resubmit to
retry a slow job. Unknown cost is unknown, never zero. Provider billing is authoritative;
Homie's local receipt cannot enforce spending in another client.

## Place and prove the result

Download the completed tool's output using the AI client's file/download facilities.
Keep temporary signed URLs out of committed records. Keep the original in the studio's
art/job folder; put the optimized delivered asset beside its game/app, or in music/ or
videos/ for a published work. Record a receipt with these fields:

```json
{
  "provider": "fal",
  "tool": "run_model",
  "model": "exact endpoint returned by the provider",
  "requestId": "actual request ID",
  "prompt": "the actual prompt, including style constraints",
  "styleRevision": "revision from the studio's style",
  "rights": {"source": "provider/model terms URL", "checkedAt": "YYYY-MM-DD", "commercial": false, "note": "record the actual plan and permitted use"},
  "cost": {"status": "unknown"}
}
```

For ElevenLabs use its actual discovered tool and model, and its flow/session or request
identifier. A measured cost uses `{"status":"actual","amount":1,"unit":"credits"}`;
a quote uses `estimate`. Never claim commercial rights from the fact that generation
succeeded. Read the provider and model terms for the account's plan; record attribution,
reference-image permissions and any restrictions. Mark test fixtures `"fixture": true`.

Wire the delivered path into the scene or manifest, then run:

```sh
npx --no-install homie-studio media import --file <downloaded-file> --receipt <receipt.json> --out games/<id>/assets/<name> --used-by games/<id>/view.ts
```

This copies bytes, verifies a static reference, hashes the asset and records allowlisted
provenance in `media/provenance.json`. Reimporting the same output is idempotent; it
never generates or charges. Include each generation step's receipt for derived assets.
Run the scene and look/listen: a file and static reference are not proof that it renders
or plays. Report the placed path, usage evidence, rights and actual/estimated cost.

The toolkit’s `lib/media-workflows.mjs` declares this skill’s verified tool references.
Validate them against the host’s current tool inventory before execution; tool discovery
is required for generation capabilities that have no stable documented name.

Files in this skill

  • SKILL.md5 KB
  • agents/openai.yaml531 B
  • references/RIGHTS.md3.2 KB
  • scripts/models.mjs15.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.