Yolo Utilities

基于 yoloutils 的命令级技能。用户需要执行 yoloutils 的 label、merge、copy、remove、change、crop、labelimg、resize、classify、test 任一子命令时使用。以源码真实行为为准，提供每个子命令的参数定义、执行逻辑、副作用、限制和示例。

This is documentation for a local yoloutils tool rather than code to be installed. Before using: (1) back up your datasets; test commands on a small sample directory first; (2) be careful with flags like --clean and in-place operations (they can delete or overwrite images and labels); (3) ensure the declared Python deps (opencv-python, pillow, ultralytics, etc.) and any model files (e.g., best.pt) are from trusted sources; (4) note the SKILL.md refers to src/netkiller/yoloutils.py but the package/source code is not included here — if you need to execute code, prefer installing/reviewing the original project from a trusted repository or author to verify behavior.

Type: OpenClaw Skill Name: yoloutils Version: 1.0.0 The `yoloutils` skill bundle describes a utility for YOLO dataset management with extensive file system capabilities, including recursive scanning, in-place modification of label files, and directory deletion via a `--clean` flag as detailed in `SKILL.md`. While these actions are aligned with the stated purpose, they represent high-risk behaviors for an automated agent. Additionally, the instructions explicitly direct the agent to prioritize the logic of an external script (`src/netkiller/yoloutils.py`) that is not included in the provided files, preventing a full verification of the actual execution logic.