automated-3d-model-splitting SKILL.md skillA
automated-3d-model-splitting from bensonzeng00/automated-3d-model-splitting is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add bensonzeng00/automated-3d-model-splitting/automated-3d-model-splitting@git:20261027.990797ePins git:20261027.990797e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- bensonzeng00/automated-3d-model-splitting
- Path
skills/automated-3d-model-splitting/SKILL.md- Versions recorded
- 10
- Latest version
- git:20261027.990797e, committed Oct 27, 2026
- First version recorded
- Oct 12, 2026
- Size
- 18,361 bytes
- Repository stars
- 21
- License
- a license file GitHub does not identify
Split externally painted 3MF source regions into an assembled multi-part 3MF by planning shared seams and interfaces without repairing or merging source defects.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 自动化 3D 模型拆件 Current release: `3.0.0`, positioned as automated painted-3MF model-part splitting. ## 尽力拆件与质量告警 CLI 默认采用 best-effort：保留原几何阈值并执行检查，质量超限记录告警，继续构造其他接口和零件。正常模型沿用原构造路径；接口无法生成时跳过并标记缺少榫/卯；零件拼接失败时保留原区域参考网格。用户检查最终模型并判断是否可打印，输出成功不代表验证通过。`--strict-quality` 恢复几何检查阻断；底层 Python 服务在未进入报告作用域时仍保持严格行为。 每次运行生成 `*_split_report.md`、同名 JSON 和 `*_partial_parts/` 内的 PLY 保留网格。报告记录阶段、零件/接口、实测值、原阈值、处理结果及未执行检查。读取 CLI 摘要的 `split_report` 定位报告。未构造的接口、参考网格、未检查的视觉一致性均不得标记通过。 文件不可读、依赖不可用、没有可导出网格、写入失败或导出包无法重新解析仍停止并保留已有网格与报告。模型选择、源 SHA256/工件指纹、资源预算、语义及装配人工确认门槛仍有效；不得猜测身份、绕过确认或临时修改代码来放行模型。详见 [执行与日志策略](references/execution-policy.md)。 ## 安装与入口定位 用户只需提出“从 GitHub 仓库安装此 Skill 和所需依赖”即可启动安装流程，不需要提供脚本名、Python 路径或把确认规则写入请求。助手应读取仓库安装说明，选择环境、取得下述确认并执行安装，不能仅返回手动命令就视为完成。普通安装请求本身仍不构成消耗确认。 从仓库安装时使用仓库根目录下的 `tools/install_skill.py`，详细流程见仓库 `tools/INSTALL.md`。无交互终端时先在对话中展示以下原句并取得明确同意，再传入 `--accept-usage`；不得自行填写确认，也不得手动复制或单独执行 pip 绕过安装器。安装脚本属于仓库工具，不应假设它存在于已安装技能的 `tools/` 中。 > 拆件可能消耗较多 token，复杂模型有可能失败；如果没有 Coding Plan，请谨慎使用，并对 token 消耗做好预期。明确确认后才安装 安装成功后再次显示上述原句，不再要求确认。不单独询问套餐情况。首次安装请求、空回复不构成同意；同一次安装会话已有明确确认则复用。示例拆件需另行征求用户意愿；开发修改和隔离打包测试不触发安装确认。 …
Read the whole file at its exact version.
How to install
mdr add bensonzeng00/automated-3d-model-splitting/automated-3d-model-splitting@sha256:824a689ab10cc504The line at the top of this page pins the label git:20261027.990797e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_22tpzvbhh7rauoyh)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Oct 12, 2026 and Oct 27, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.990797e latest | 2026-10-27 | 990797e | 18,361 B | A | view · diff |
| git:20261025.0fce08e | 2026-10-25 | 0fce08e | 18,806 B | A | view · diff |
| git:20261025.a173f32 | 2026-10-25 | a173f32 | 19,299 B | A | view · diff |
| git:20261025.ff6a97e | 2026-10-25 | ff6a97e | 19,146 B | A | view · diff |
| git:20261025.206493f | 2026-10-25 | 206493f | 18,298 B | A | view · diff |
| git:20261020.6180f11 | 2026-10-20 | 6180f11 | 15,708 B | A | view · diff |
| git:20261014.3815494 | 2026-10-14 | 3815494 | 15,035 B | A | view · diff |
| git:20261014.110c3a9 | 2026-10-14 | 110c3a9 | 14,637 B | A | view · diff |
| git:20261013.5aaa21c | 2026-10-13 | 5aaa21c | 14,040 B | A | view · diff |
| git:20261012.a87c753 | 2026-10-12 | a87c753 | 13,642 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (18361 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
bensonzeng00/automated-3d-model-splitting · 21 stars · license a license file GitHub does not identify · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_22tpzvbhh7rauoyh GET https://markdownregistry.com/api/v1/resolve?ref=bensonzeng00/automated-3d-model-splitting/automated-3d-model-splitting GET https://markdownregistry.com/api/v1/blob/824a689ab10cc5045f59627833526d1de31c3a8fe9b094577e02c539630dc89d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.