← 返回 Skills 市场

Annotation Visualizer

Name: Annotation Visualizer
Author: mingo-318

作者 Mingo_318 · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

302

总下载

当前安装

版本数

在 OpenClaw 中安装

/install annotation-visualizer

功能描述

Visualize bounding boxes and class labels on images with support for COCO, YOLO, VOC, and LabelMe annotation formats.

使用说明 (SKILL.md)

Annotation Visualizer

Visualize bounding boxes and labels on images. Supports COCO, YOLO, VOC, and LabelMe formats. Use when user wants to visualize annotations on images for quality checking or debugging.

Features

Multi-format Support: COCO, YOLO, VOC, LabelMe
Customizable Colors: Per-class colors or auto-generated
Label Display: Show class names and confidence
Box Styles: Filled or outline boxes
Batch Processing: Visualize entire dataset

Usage

# Visualize YOLO annotations
python scripts/visualize.py yolo images/ labels/ output/

# Visualize COCO annotations
python scripts/visualize.py coco annotations.json images/ output/

# Custom colors and styles
python scripts/visualize.py yolo images/ labels/ output/ \
  --colors red,green,blue \
  --thickness 2 \
  --fill

Examples

$ python scripts/visualize.py yolo ./images ./labels ./output

Processing 100 images...
✓ Saved visualization for image1.jpg -> output/image1.jpg
✓ Saved visualization for image2.jpg -> output/image2.jpg
...

Supported Formats

Format	Input	Description
YOLO	.txt	YOLO darknet format
COCO	.json	COCO JSON annotation
VOC	.xml	Pascal VOC XML
LabelMe	.json	LabelMe JSON

Installation

pip install pillow

Options

--colors: Comma-separated colors for each class
--thickness: Box line thickness (default: 2)
--fill: Fill boxes with semi-transparent color
--show-label: Show class labels on boxes
--font-size: Label font size (default: 16)

安全使用建议

This skill appears coherent and limited to local image/annotation visualization. Before installing or running: 1) review the included script if you want to confirm behavior (it only reads files you point it at and writes output images); 2) run it in a sandbox or with non-sensitive images if you have policy concerns; 3) ensure pillow is installed (pip install pillow) and that input paths are correct. Minor notes: the script swallows some exceptions silently and defaults class names/IDs in simple ways, so check output for correctness on your datasets.

功能分析

Type: OpenClaw Skill Name: annotation-visualizer Version: 1.0.0 The skill is a standard utility for visualizing bounding box annotations on images across multiple formats (YOLO, COCO, VOC, LabelMe). The implementation in `scripts/visualize.py` uses the Pillow library for image processing and contains no evidence of malicious intent, network activity, or unauthorized file access. The instructions in `SKILL.md` are consistent with the tool's purpose and do not contain any prompt injection attempts.

能力评估

✓ Purpose & Capability

Name/description (annotation visualization) matches the files and declared behavior. The included script implements YOLO/COCO/VOC/LabelMe parsing and image drawing, which is appropriate for the stated purpose.

✓ Instruction Scope

SKILL.md instructs running the included script with local image/annotation paths and options. The runtime instructions and the script only read specified image/annotation directories and write output images; they do not request unrelated files, environment variables, or network endpoints.

✓ Install Mechanism

No install spec; SKILL.md suggests installing pillow via pip which is proportional to drawing images. There are no downloads from external URLs or archive extraction steps.

✓ Credentials

The skill declares no required environment variables, credentials, or config paths. The code does not read environment variables or secret files; requested resources are local image/annotation files as expected.

✓ Persistence & Privilege

The skill is not always-enabled and does not request persistent platform privileges. It does not modify other skills or system-wide configurations.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install annotation-visualizer
安装完成后，直接呼叫该 Skill 的名称或使用 /annotation-visualizer 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of Annotation Visualizer. - Visualize bounding boxes and labels on images for COCO, YOLO, VOC, and LabelMe annotation formats. - Supports customizable colors per class, label display (class names & confidence), and adjustable box styles (filled or outline). - Enables batch processing to visualize entire datasets. - Command-line interface with options for color, box thickness, fill, label display, and font size.

元数据

Slug annotation-visualizer

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题