What makes 3d Print Model Splitting notable?

1K downloads. Trust evidence available

How should 3d Print Model Splitting be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

3d Print Model Splitting

Use when splitting a single complex STL / figurine / statue model into multiple 3D-printable and physically assemblable parts, especially with Blender face/m... Skill: 3d Print Model Splitting Owner: lzyling Summary: Use when splitting a single complex STL / figurine / statue model into multiple 3D-printable and physically assemblable parts, especially with Blender face/m... Tags: 3d-printing:1.0.1, bambu:1.0.1, blender:1.0.1, latest:1.0.1, stl:1.0.1 Version history: v1.0.1 | 2026-05-12T11:29:11.460Z | user Add mandatory preview gates; require capped split baselines with bou

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.1release · observed May 12, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17b20pjwm3e6gpzdhjbtfr3es84rtrw:3d-print-model-splitting

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-lzyling-3d-print-model-splitting/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

53,171 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: 3d-print-model-splitting
description: Use when splitting a single complex STL / figurine / statue model into multiple 3D-printable and physically assemblable parts, especially with Blender face/material annotation, Bambu Studio, MeshFix, manifold Boolean, interface clearance/allowance, 3MF object validation, or assembly interference checks. Trigger for requests about STL hand-model splitting, Bambu-ready 3MF delivery, print-fit failures, or fixing part interfaces that print but do not assemble.
---

# 3D Print Model Splitting

This skill turns a single complex sculpted STL into multiple Bambu-ready, physically assemblable parts.

## Core rule

Do not confuse printable with assemblable.

Also do not confuse a material-selection preview with a split part.

- MeshFix/slicers can make parts watertight and printable.
- They do not guarantee that interfaces have clearance.
- The validated workflow succeeds because it treats part interfaces as the core problem.
- A face-selection preview is only a semantic preview. It is not a valid part preview until every split part has its open contact boundary capped/filled.

## Mandatory preview gates

For interactive demos or human-guided annotation, proactively generate previews; do not wait for the user to ask.

- After preparing the annotation `.blend`: render a quick source/annotation preview so the user can confirm scale, orientation, and material slots.
- After the user saves material-face annotation: render an annotation preview/contact sheet with clear part colors and face counts.
- Before claiming “拆件完成” / “split complete”: generate a **capped split preview**, not just a face-selection preview.
- In previews, label colors explicitly. If possible, show cap/interface faces in a distinct color.
- If any part is still open at the cut/contact surface, say so clearly and call it “annotation preview only”, not “split preview”.

## Split-surface capping hard rules

Every part created by material splitting must have its cut/contact surfaces filled before baseline export.

- Deleting the other material groups leaves shell openings at the interface. This is expected but not acceptable as a split baseline.
- Cap/fill all boundary loops introduced by the split before exporting baseline STLs.
- Validate capping with boundary-edge counts per part. Target: `boundary_edges = 0` for each baseline part, unless a known intentional opening is documented.
- If automatic hole filling leaves residual boundaries, retry with a more robust method or explicitly report the residual count; do not present it as final.
- Lock the first accepted baseline only after it is “split + capped”; never lock a raw material-isolated shell as baseline.

## Scope boundaries

Good fit:

- figurines, statues, toys, decorative sculpts, and similar triangle-mesh STL files;
- human-guided semantic part boundaries;
- glue-fit or lightly finished assemblies;
- Bambu-ready 3MF/STL handoffs.

Poor fit unless explicitly requested:

- fully automatic

README.md

# 3D Print Model Splitting Skill

OpenClaw AgentSkill for splitting a single complex STL figurine/statue into multiple 3D-printable and physically assemblable parts.

The core lesson encoded here is:

> Printable is not the same as assemblable. Mesh repair and slicer import can make parts printable, but interface clearance is what makes them fit.

## What it covers

- Blender face/material annotation for human-guided semantic splitting
- STL split/cap baseline workflow
- Pre-clearance MeshFix repair guidance
- Manifold Boolean interface clearance using expanded cutters
- Post-clearance simplify without filling intentional cavities
- 3MF object validation and pairwise interference checks
- Bambu Studio handoff guidance

## Skill contents

```text
SKILL.md                 OpenClaw skill entrypoint
references/             SOP, clearance lessons, versioning, case study
scripts/                Reusable helper scripts
.clawhubignore          Files to exclude from ClawHub packaging
.skillignore            Legacy/local ignore mirror
```

## Dependencies

Depending on which scripts you use:

- Blender (`bpy`, `bmesh`, `mathutils`) for annotation, splitting, and Blender-based checks
- Python packages: `trimesh`, `numpy`, `manifold3d`, `pymeshfix`, `Pillow`
- Bambu Studio or another slicer for final print preparation

Install Python dependencies in your project environment, not inside the skill package.

## Public release note

This repository is intended for public distribution of the skill. Generated model files (`.stl`, `.3mf`, `.blend`, preview images, caches, and virtual environments) are intentionally excluded.

_meta.json

{
  "ownerId": "kn73gt88jsjv66v89gzkwxcfrn84swtx",
  "slug": "3d-print-model-splitting",
  "version": "1.0.1",
  "publishedAt": 1778585351460
}

references/blender-material-annotation.md

# Blender material-face annotation

## Table of contents

1. Why this workflow exists
2. Agent setup
3. Human annotation steps
4. Quality checks
5. What not to do

## 1. Why this workflow exists

Complex sculpted STL files rarely contain semantic part information. A model may visually contain a hat, head, torso, pants, arms, or legs, but the STL is usually just triangles.

The reliable compromise is:

```text
human sees semantic boundaries
agent reads polygon material indices
```

This avoids unreliable automatic cutter guesses while keeping downstream splitting deterministic.

## 2. Agent setup

Prepare a Blender file with:

- the imported source STL;
- one material slot per intended part;
- one unassigned/base material;
- optionally one check/uncertain material;
- a text note inside the `.blend` explaining how to annotate.

Material naming pattern:

```text
BASE_UNASSIGNED
PART_01_<name>
PART_02_<name>
CHECK_UNCERTAIN
```

Use stable prefixes such as `PART_01_` so scripts can preserve part order.

## 3. Human annotation steps

In Blender:

1. Select the source mesh.
2. Press `Tab` for Edit Mode.
3. Press `3` for Face Select.
4. Select triangle faces belonging to a part.
5. In Material Properties, choose the target part material.
6. Click `Assign`.
7. Repeat for all parts.
8. Save the `.blend`.

Useful selection tools:

- `C` Circle Select for painting broad regions;
- `B` Box Select for rectangular areas;
- Shift-click for incremental edits;
- assign uncertain boundary faces to a check material if needed.

## 4. Quality checks

Before running automated splitting:

- every intended part has nonzero face count;
- obvious semantic regions are not left unassigned;
- boundary rings are visually continuous enough to cap;
- uncertain faces have been resolved or intentionally documented;
- tiny accidental islands are expected but should be cleaned conservatively.

## 5. What not to do

- Do not use Texture Paint; it creates image/color data, not reliable per-face part metadata.
- Do not actually cut the model manually unless the workflow explicitly asks for it.
- Do not expect the agent to infer all semantic boundaries from geometry alone.
- Do not mix left/right naming conventions; define whether left/right means character-left or screen-left.

references/case-study-v13.md

# Case study: validated 5-part figurine workflow

## Table of contents

1. Why this case matters
2. Failed earlier route
3. Final part plan
4. Interface responsibility table
5. Cleanup and validation
6. Transferable lessons

## 1. Why this case matters

This case closed the loop from a single complex figurine STL to parts that passed:

- geometry validation;
- 3MF object validation;
- pairwise assembly interference checks;
- physical print and assembly testing.

The important lesson is not the specific character or filenames. The transferable lesson is that the final version succeeded because it explicitly solved interface clearance.

## 2. Failed earlier route

An earlier route did this:

```text
split by material
→ cap / close parts
→ MeshFix each part
→ create slicer-ready 3MF
→ print test
```

The print could complete, but the parts could not assemble. This proved:

```text
watertight + printable ≠ assemblable
```

The missing step was real clearance at the part interfaces.

## 3. Final part plan

The final successful version used 5 parts:

```text
01_hat_head = hat + head
02_body_arms = body + left arm + right arm
03_pants
04_left_leg
05_right_leg
```

A prior 7-part clearance candidate already had clearance cut between some parts. The 5-part version was **not** made by directly merging that already-clearanced version, because that would leave internal seams/cavities.

Correct approach:

```text
return to un-clearanced baseline
→ rebuild merged parts
→ apply clearance only to remaining real assembly interfaces
```

## 4. Interface responsibility table

The successful responsibility table was:

```text
body_arms subtract expanded hat_head
body_arms subtract expanded pants
pants subtract expanded left_leg
pants subtract expanded right_leg
```

Meaning:

- `body_arms` makes room for `hat_head` and `pants`;
- `pants` makes room for the legs;
- cutters are expanded versions of the neighboring parts;
- expansion depends on correct outward winding.

The target clearance in this case was 0.5 mm.

## 5. Cleanup and validation

Final cleanup used manifold simplify, not MeshFix-after-clearance.

Validation gates:

```text
3MF object validation: PASS
pairwise interference: no meaningful intersections
physical print/assembly: PASS
```

3MF object checks included:

```text
boundary_edges = 0
edges_more_than_2_faces = 0
non_2_face_edges = 0
watertight = true
winding_consistent = true
```

## 6. Transferable lessons

- If the part plan changes, rebuild from baseline before cutting clearance.
- Do not merge parts that have already had clearance cut between them.
- MeshFix is useful before clearance, dangerous after clearance.
- Slicer overlap warnings are not assembly validation.
- The deliverable 3MF must be re-read and validated object by object.
- Physical assembly remains the final acceptance gate.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.