Meshy 3D Agent skill
Three skills for the Meshy CLI: the agent makes 3D models from text and photos, textures them and prepares them for 3D printing
- 107 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Generation spends credits of a paid Meshy account
- Keeps the login session in `~/.config/meshy/credentials.json` and installs the CLI globally through npm
- Sends prompts and images to Meshy servers and can launch an installed slicer
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/meshy-3d-agentDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Generation spends credits of a paid Meshy account
- Keeps the login session in `~/.config/meshy/credentials.json` and installs the CLI globally through npm
- Sends prompts and images to Meshy servers and can launch an installed slicer
This is third-party code. Review the repository files before installing.
What it does
The repository holds three skills for the Meshy AI service. All of them drive the Meshy CLI version 0.7.3 or newer on Node.js 22.12+ and consist of instructions and references with no scripts of their own. The `meshy-3d-generation` skill creates models from text, images and photos, textures them, remeshes, builds LODs, unwraps UVs, converts between GLB, FBX, OBJ, USDZ, STL and 3MF, and rigs and animates. The `meshy-3d-printing` skill prepares white models and multi-color 3MF, analyzes and repairs meshes, rescales OBJ and opens the file in a slicer. The `meshy-openclaw` skill merges both workflows for OpenClaw. The user describes the result in their own words: "turn this photo into a textured GLB and save it to `./assets/chest.glb`". The agent installs the CLI itself with `npm install -g meshy-cli@0.7`, checks the login and, if needed, starts a browser login that shows a link and a code. No API key goes into the chat. The file lands at the given path with a preview and task IDs for follow-up requests, such as a 1500-face LOD or a conversion to FBX. The agent takes cost estimates from `meshy make --dry-run` or the published price list and not from the account balance. The real spend appears in the task's `consumed_credits` field. Local operations such as rescaling an OBJ run without a login or credits.
Who it is for. Game and app developers, designers and 3D printer owners who need models and assets without opening an editor by hand.
Good fit when
- You need a placeholder model for a scene from a text description, saved as `GLB`
- A photo of an object has to become a textured model, plus a low-poly version right away
- A model must go to print: check it, repair the mesh and open it in a slicer
- A set of models has to be converted from GLB to FBX or USDZ
- A character needs rigging and animation with generated motion
Not a fit when
- You work inside Blender or Maya, since the skills drive the cloud Meshy and do not control editors
- You cannot spend credits, because generation uses Meshy credits
- You have no Node.js 22.12 or newer and cannot install global npm packages
- You need offline generation, as requests go to Meshy servers
Example request
Turn this photo into a textured GLB, save it to ./assets/chest.glb and make a 1500-face versionLimitations
- Needs Node.js 22.12 or newer and Meshy CLI 0.7.3 or newer. Generation needs a Meshy account, and requests spend credits.
- Prompts, images and task parameters go to Meshy servers (`api.meshy.ai` or `api.meshy.cn`). Local print preparation works without a login.
- The `MESHY_API_KEY` variable overrides a saved browser session. Check the login source with `meshy auth status`.
- The skills were not verified on every host and system: the author notes that local tests do not replace a check in the agent itself.
How to disable. Delete the three skill folders from the agent's skills directory in full. `npm uninstall -g meshy-cli` removes the CLI and `meshy auth logout` signs out.
FAQ
How do I install the Meshy skills in Claude Code?
Give the agent the link to `INSTALL.md` from the repository or copy the skill folders whole into `.claude/skills/`. The agent installs the CLI itself with `npm install -g meshy-cli@0.7`.
Is a Meshy API key required?
No, a browser login is enough: `meshy auth login` shows a link and a code. If `MESHY_API_KEY` is set, it takes priority over the saved login.
How much does generation cost?
`meshy make --dry-run` gives an estimate before the run, and the real spend shows in `consumed_credits` on the finished task. The account balance is not used for estimates.
How does meshy-3d-printing differ from meshy-3d-generation?
The printing skill prepares white and multi-color 3MF models, repairs meshes and opens a slicer, while the generation skill handles creation, textures, rigging and animation. The printing skill installs independently of the other.
Which formats does conversion support?
GLB, FBX, OBJ, USDZ, STL, 3MF and Blender formats. The `meshy-3d-generation` skill handles conversion, scale and UV unwrapping.
Discussion
No questions or reviews yet.
Related
SkillsA skill collection guides AI agents through Blender modeling, materials, animation and asset checks using supplied Python scripts.
A coding agent turns one illustration into an animated 2D avatar that blinks and talks, and you fine-tune it in a local editor
Clipmivo Video
clipmivo-video
A skill for ClipmivoAI: the agent quotes a video task in credits, starts generation, follows it and downloads the result.
A local MCP server and CLI: the agent writes JavaScript for a 3D model, checks it on renders and exports a GLB with source
Scenario Agent Skills
scenario-labs-skills
Skills for the paid Scenario service: images, video, audio and 3D from an agent, model and price selection before spending, sets for game assets and brands
The official SpicyAPI skill: an agent runs image, video and audio generation tasks through the MCP server, CLI or SDK
README in short
The README starts with a one-sentence install for the agent, then covers manual CLI installation and a table of the three skills. It goes on with installing into OpenClaw and Hermes Agent, notes on data and local effects, validation and rules for upgrade and rollback.
README badge
Original SKILL.md
--- name: meshy-3d-generation description: "Generates and edits digital 3D assets with the Meshy CLI: text-to-3D and image-to-3D models, texturing, remeshing and LODs, UV unwrapping, format conversion (GLB, FBX, OBJ, USDZ, STL, 3MF, Blender), rigging, animation, motion clips from text and reference images. Use when the user asks to make, texture, rig, animate or convert a 3D model or game asset. For physical 3D printing use meshy-3d-printing." license: MIT compatibility: "Needs Node.js 22.12+ and the Meshy CLI 0.7.x, 0.7.3 or later (npm install -g meshy-cli@0.7); network access to the Meshy API." --- # Meshy 3D Generation Use Meshy CLI **0.7** (0.7.3 or later) 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 | Need | Reference | |---|---| | CLI runner, credentials, or output location | [Setup](references/setup.md) | | Generation, texturing, remeshing, conversion, scale, or 2D images | [Pipelines](references/pipelines.md) | | Rigging, animation, or generated motion | [Animation](references/animation.md) | | Cost, waiting, preview, delivery, or finding a previous model | [Delivery](references/delivery.md) | | Failed or uncertain operation | [Troubleshooting](references/troubleshooting.md) | 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 Before the first command run `meshy --version`; no need to ask. When `meshy` is missing or older than 0.7.3, install the newest 0.7.x with `npm install -g meshy-cli@0.7` and say so in one line; Setup covers a refused install and a CLI of 0.8 or newer. Reuse a verified session. If login is needed, follow Setup and run `auth login --device` (adding `--region cn` for a user in mainland China) 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, except in Setup's two-step sign-in for a user on a remote chat (a phone through a chat bot). 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, UV unwrap and multicolor: GLB); use the supported