home/categories/documents/charleswiltgen-axiom-claude-plugin-plugins-axiom-skills-axiom-vision-ref-skill-md
documentscontent-media
axiom-vision-ref
Use when needing Vision framework API details for hand/body pose, segmentation, text recognition, barcode detection, document scanning, or Visual Intelligence integration. Covers VNRequest types, coordinate conversion, DataScannerViewController, RecognizeDocumentsRequest, SemanticContentDescriptor, IntentValueQuery.
maintainer
CharlesWiltgen
更新于 2/27/2026
星标
807
分支
66
quick start
Installation and usage
Use when needing Vision framework API details for hand/body pose, segmentation, text recognition, barcode detection, document scanning, or Visual Intelligence integration. Covers VNRequest types, coordinate conversion, DataScannerViewController, RecognizeDocumentsRequest, SemanticContentDescriptor, IntentValueQuery.
安装
$ install --globalskills.sh
使用
安装后，您可以通过在终端运行以下命令来使用此技能：
skills use axiom-vision-ref