agentleFS
meshy-devmeshy-dev/meshy-3d-agent/skills/meshy-3d-printing/SKILL.md

meshy-3d-printing

Skill107 starsChanged 9 days agoMITView on GitHub

Generates and prepares models for physical 3D printing with the Meshy CLI: white and multicolor prints (3MF, STL, OBJ), printability analysis and repair, splitting into parts, Creative Lab products such as figures, lamps and keychains, sizing, and slicer handoff (Bambu Studio, OrcaSlicer, PrusaSlicer, Cura). Use when the user wants something 3D-printed or asks for print or slicer files.

  • Reads credentials
  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Laic-parsiism709/meshy-3d-agent★ 5same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Meshy CLI 0.8 (0.8.3 or later) to deliver the requested print files at the intended size, with analysis/repair results where applicable …

    line 10
  2. Distinctive:

    Read relevant sections as needed.

    line 22
  3. Very specific:

    Before the first command run meshy --version.

    line 56
  4. Distinctive:

    Never ask for credentials in chat, nor for a "done" message except in Setup's two-step sign-in for a user on a remote chat (a phone through …

    line 63
  5. Very specific:

    Only the CLI touches its config directory (~/.config/meshy by default): never read, copy, edit or delete a file there (an old …

    line 66
  6. Very specific:

    Every command uses --format json --no-update-check and prints one meshy.cli/v1 envelope.

    line 86

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Meshy 3D Printing

Use Meshy CLI 0.8 (0.8.3 or later) 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.

NeedReference
CLI runner, credentials, or output locationSetup
Local preparation, white or multicolor prints, analysis/repair, or splitting into partsPrinting recipes
Creative Lab products (figures, lamps, keychains, magnets, keycaps, fidgets)Creative Lab
Cost, waiting, preview, delivery, or finding a previous modelDelivery
Failed or uncertain operationTroubleshooting

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

Choose local or cloud work

RequestRoute
Scale, orient or ground an existing OBJLocal mesh prepare-print; no auth or balance
Open an existing STL or 3MFLocal slicer detect and slicer open; no auth or balance
White model from text or photoGenerate geometry without textures; analyze/repair as needed; prepare the file
Multicolor modelGenerate/reuse geometry; analyze/repair as needed; texture; multi-color-print
Print in separate parts (build plate, colours per part, fewer supports)Generate/reuse geometry; auto-split; slice the parts
Check or fix an existing model (holes, thin walls), any formatFree analyze-printability by task ID or --model-url; repair only if needed
Resize an existing STL, 3MF or GLBScale it in the slicer; only an OBJ is resized locally
Creative Lab figure (a stylized collectible from a photo), vinyl figure, brick figure, lamp, keychain, fridge magnet, keycap or pixel fidget boardPrototype → review → build → select product artifacts
Creative Lab collapsible fidgetOne create from the photo → STL

Colour routes differ: multicolor paints one object's surface for a multi-material printer; a split cuts it into parts, one filament each, and drops the texture (split before any repair; the two do not chain); the pixel fidget board is a product of its own.

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

DeepSeek Harness with the Meshy plugin (DSH_MESHY_CLI is set; check with test -n "$DSH_MESHY_CLI"): the plugin ships the CLI and keeps the sign-in. Run every command as "$DSH_MESHY_NODE" "$DSH_MESHY_CLI" … in place of meshy … — never a meshy on PATH, which cannot see that sign-in — install nothing, and when a command reports that nobody is signed in, call the meshy_sign_in tool instead of auth login (Setup, section 1). Everywhere else:

Before the first command run meshy --version; no need to ask. When meshy is missing or older than 0.8.3, install the newest 0.8.x with npm install -g meshy-cli@0.8 and say so in one line; Setup covers a refused install and a CLI of 0.9 or newer. Local-only work stops at runner setup. Cloud work reuses a verified session. If login is needed, keep auth login --device running (with --region cn for a user in mainland China: the same account and credits as the global site), 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. Never ask for credentials in chat, nor for a "done" message except in Setup's two-step sign-in for a user on a remote chat (a phone through a chat bot); Setup has the host wait procedure.

Only the CLI touches its config directory (~/.config/meshy by default): never read, copy, edit or delete a file there (an old credentials.json included), and never look for credentials anywhere else. When a sandboxed shell blocks the network (auth login fails with oauth_network or fetch failed), run the same command again with network access or outside the sandbox, asking the user to allow it if the host requires. Do not probe with curl or switch to --with-key (Setup, section 3).

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, with the printer type and print size when known so wall thickness is checked too; 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; cloud print files are scaled in the slicer (Printing recipes, Print size). 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, and a local model must be GLB or glTF (multicolor: GLB); an STL, OBJ or FBX goes to Meshy only as an http(s) URL. Every command uses --format json --no-update-check and prints one meshy.cli/v1 envelope; 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.

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.