Agent Skills

meshy-3d-printing

imagemeshy-dev1.3K installs

Generate or prepare models for physical 3D printing, including white or multicolor prints, Creative Lab products, sizing, and slicer handoff.

Install

npx skills add https://github.com/meshy-dev/meshy-3d-agent --skill meshy-3d-printing
SKILL.md

Meshy 3D Printing

Use Meshy CLI 0.4.0 to deliver the requested print files at the intended size, with analysis/repair results where applicable and a slicer handoff when requested. This skill is self-contained. Ordinary digital assets belong to meshy-3d-generation.

Need Reference
CLI runner, credentials, or output location Setup
Local preparation, cloud generation, or product workflow Printing recipes
Cost, waiting, preview, delivery, or finding a previous model Delivery
Failed or uncertain operation Troubleshooting

Read relevant sections as needed. Recipes illustrate valid commands; select only the stages needed for the user's output.

Choose local or cloud work

Request Route
Scale, orient or ground an existing OBJ Local mesh prepare-print; no auth or balance
Open an existing STL or 3MF Local slicer detect and slicer open; no auth or balance
White model from text or photo Generate geometry without textures; analyze/repair as needed; prepare the file
Multicolor model Generate/reuse geometry; analyze/repair as needed; texture; multi-color-print
Creative Lab lamp, keychain, fridge magnet or figure template Prototype → review → build → select product artifacts

A figurine does not by itself require Creative Lab. Infer the route from the intended product; ask about size, color or style only when the missing choice materially changes the result. For an existing model, distinguish local preparation from cloud printability analysis; a local dimension check cannot establish full printability.

Cloud authorization

Resolve the runner automatically using Setup (compatible meshy or npm exec --yes --package=meshy-cli@0.4.0 -- meshy …). Local-only work stops at runner setup. Cloud work reuses a verified session. If login is needed, keep auth login --device running, show its URL and user code in commentary/progress, never a final answer, and await the same tool session in this turn. After it exits, verify auth status and resume the print job. Do not ask for a "done" message or credentials in chat; Setup has the host wait procedure.

Printing-specific constraints

  • Repair changes geometry and drops textures. Use repaired geometry downstream and retexture before multicolor output. Use analysis when functional parts, thin features or other requirements make it relevant; its report does not establish material suitability.
  • Prepare a Y-up OBJ as a new Z-up file at the requested height, centered and grounded. Do not repeat the transform or apply it to STL, 3MF, or relief product output. A multicolor 3MF requires no OBJ conversion. Product ZIPs and optional lamp bases have distinct handling in Printing recipes.
  • API, downloads and geometry operations use the CLI. Local inputs have a 50 MiB limit. Business commands use --output-schema v1 --format json --no-update-check; writes carry the resolved --workspace WORKSPACE. Read returned paths and IDs rather than guessing.
  • Submit cloud tasks once with create --async, retain their resource and lineage, and wait on the same task. Keep the turn active during waits. Unknown submission and interrupted downloads are recovery cases, not permission to generate again.
  • Work within the approved scope and budget; propose additional paid stages before spending. Delivery describes applicable estimates. Local preparation and printability analysis are free.

Finish the handoff

Show an available rendered preview and deliver file paths, dimensions, analysis/repair status and reported charges. Launch a detected slicer only when requested or already authorized; launch_requested does not prove successful import or start a physical printer. If no suitable slicer is installed, still deliver the files. Explain relevant remaining checks, such as supports and wall thickness, without describing an untested model as guaranteed printable.

Related skills

ai-image-generationgenmedia-labs713KGenerate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-secoai-image-generation101-skills547KGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stnano-banana-2prime-skills424KGenerate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream insteimage-editprime-skills424KEdit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers