create-fusion-deliverables
Stage and verify Fusion exports, drawing PDFs, flat-pattern DXF, viewport images and local renders. Use for engineering deliverables, not automatic publication or release.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-11
- Stars
- ★ 20
- Forks
- 14
01 前言 Front Matter
- name
- create-fusion-deliverables
- description
- Stage and verify Fusion exports, drawing PDFs, flat-pattern DXF, viewport images and local renders. Use for engineering deliverables, not automatic publication or release.
02 资源文件 1
- 参考文档agents/openai.yaml221 B
03 SKILL.md 正文
Inspect source identity, configuration, references, units and output purpose. Discover the exact supported export variant and information-loss limits.
Use fusion_artifact_prepare with an approved root alias and filename, then execute the unchanged plan through fusion_artifact_generate. STL units/refinement are explicit; local F3D is not an external assembly package. Existing PDF export does not imply drawing-authoring support. Never pass raw paths, overwrite candidates or use an empty render destination.
Poll pending jobs with fusion_job_status. A partial file is not completion. Inspect artifact hashes, sizes, structural checks and limitations with fusion_artifact_inspect.
Approved STEP/F3D round trips use documents.import into a new document and numerical measurements. A new document is not a parser sandbox; hostile inputs need a separate qualified environment.
Return evidence actually obtained. Screenshots and signatures do not prove geometry. HTML setup sheets remain quarantined active content; do not automatically open, publish, send or release them. See qualification.
04 同仓库更多 Skills
recommend-review-reference-architecture
Recommend a conservative shadow-only review reference architecture from valid offline evidence. Use only when the user explicitly asks for a reference-architecture recommendation or uses the bundled synthetic fixture.
normalize-review-runs
Validate and normalize declared local review-run exports into a bounded canonical summary. Use only when the user explicitly asks to normalize review runs or use the bundled synthetic fixture.
benchmark-review-configs
Deterministically score comparable imported review-run lanes with root-cause metrics and uncertainty. Use only when the user explicitly asks to benchmark normalized local review runs or use the bundled synthetic fixture.
audit-review-eval-validity
Audit whether a declared local review evaluation can support fair quality claims. Use only when the user explicitly asks to audit review-eval validity or use the bundled synthetic fixture.
verify-swiftui-parity
Verify one approved SwiftUI feature slice against its behavioral parity contract with deterministic and conditional Apple-platform checks.
port-react-native-slice
Port one explicitly approved React Native or Expo feature slice into a declared SwiftUI target while preserving its parity contract.