mcpField
M
meshy-3d-generation

meshy-3d-generation

github.com/meshy-devCreative & media1062.4k installsUpdated 2w ago
Repository

About meshy-3d-generation

meshy-3d-generation is an agent skill that uses Meshy CLI 0.4.3 to generate and deliver 3D assets. It is for requests involving generation or follow-up work on models, and emphasizes completing file delivery, preview inspection when available, and requested project integration.

Key features

  1. 01Generates assets through Meshy CLI
  2. 02Supports texturing, rigging, and animation
  3. 03Converts supported model formats
  4. 04Downloads requested output files
  5. 05Checks available previews and project integration

Use cases

  1. 01Creating a 3D model from a request
  2. 02Texturing or rigging an existing model
  3. 03Delivering generated assets into a project

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/meshy-dev/meshy-3d-agent --skill meshy-3d-generation

After installing, type/meshy-3d-generationin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
delivery.md
pipelines.md
setup.md
troubleshooting.md

Details

From the project README

Meshy 3D Generation

Use Meshy CLI 0.4.3 to turn the user's request into a delivered asset. Completion means saving the requested files in the requested location, inspecting an available preview, and finishing any project integration the user requested. Login or task submission alone is not completion. Choose the shortest suitable pipeline and reuse existing assets for follow-ups.

Read what this request needs

NeedReference
CLI runner, credentials, or output locationSetup
Generation, texturing, rigging, animation, or conversionPipelines
Cost, waiting, preview, delivery, or finding a previous modelDelivery
Failed or uncertain operationTroubleshooting

Read the relevant section when needed; recipes are examples to adapt to the requested result, not a requirement to execute every stage. An untextured model skips texture generation; an existing GLB needs no extra format conversion. Use command help when parameters are uncertain.

First use and authorization

Resolve the runner automatically: use compatible meshy, otherwise npm exec --yes [email protected] -- meshy …. Reuse a verified session. If login is needed, follow Setup and run auth login --device in a persistent tool session. Show its verification URL and user code in commentary/progress, not a final answer. Await that same session in this turn until it exits, verify auth status, then continue the original request. A background process cannot resume a finished turn; do not require a "done" chat message. Browser approval stays with the user; credentials never belong in chat.

Execution boundaries

  • Run API, upload, download and mesh operations through the CLI. Local inputs have a 50 MiB limit, and a local model must be GLB or glTF (rigging and multicolor: GLB); use the supported URL input route for anything else.
  • Use --output-schema v1 --format json --no-update-check for business commands; auth has its own JSON shape. Resolve WORKSPACE from the user's output path and pass it to writes.
  • Submit once with create --async, retain the owning resource and ID, then wait on that task. Keep the agent turn active while awaiting a running command. Follow Troubleshooting on timeout or unknown submission; these do not authorize another paid create.
  • Continue work within the user's approved scope and budget. Propose additional paid stages or reruns before spending; Delivery specifies estimates and balance checks.

Deliver

Download only needed assets. Inspect and show a preview when available; a missing preview must not prevent delivery or be described as inspected. Delivery covers earlier-stage preview lookup, actual charges, and existing-project integration. Report the result and any concrete limitation; a rendered image does not establish topology quality or provide a 3D viewer.

Comments

Markdown supported