← 返回 Skills 市场

Imgae Convert Skill

Name: Imgae Convert Skill
Author: kanocifer

作者 LiuDeTao · GitHub ↗ · v0.1.2 · MIT-0

cross-platform ✓ 安全检测通过

154

总下载

当前安装

版本数

在 OpenClaw 中安装

/install image-convert-skill

功能描述

使用 Pillow 支持常见图像格式（PNG、JPEG、GIF、BMP、TIFF、WebP）之间的相互转换和格式不变的压缩，支持质量控制、尺寸缩放和无损压缩模式。

使用说明 (SKILL.md)

Image Converter Skill

支持常见图像格式相互转换或保留原格式压缩的自动化工具，使用前请确保已安装 Pillow 库：

pip install Pillow

# 或使用uv
uv add Pillow

目标格式优先级 (Target Format Precedence)

--to-format 标志（最高优先级）
明确的输出文件扩展名
默认行为：
- 默认：目录转换且未明确指定格式时转换为 WebP
- --compress 模式：保留输入格式

快速开始 / Usage Examples

Basic Format Conversion

Convert PNG to JPEG:

python scripts/convert.py input.png output.jpg

Convert WebP to PNG:

python scripts/convert.py input.webp output.png

Convert all images in a directory to PNG:

python scripts/convert.py ./input_dir ./output_dir --to-format png

Explicit Format Specification

Convert JPEG to WebP even if output has .jpg extension:

python scripts/convert.py input.jpg output.jpg --to-format webp

Compression

Compress PNG with quality 75 (preserves format):

python scripts/convert.py input.png output.png --compress --compress-quality 75

Batch Processing (Multiple Files)

Process multiple files using comma-separated list, glob patterns, or wildcard:

# Comma-separated files
python scripts/convert.py "img1.png,img2.jpg,img3.webp" output_dir/ --to-format png

# Glob pattern
python scripts/convert.py "*.jpg" output_dir/ --to-format webp

# Multiple patterns
python scripts/convert.py "*.png,*.jpg" output_dir/ --to-format webp

# Parallel processing (4 threads)
python scripts/convert.py "*.jpg" output_dir/ --threads 4

# Verbose output
python scripts/convert.py "*.jpg" output_dir/ -v

WebP Conversion (Legacy Usage Still Works)

Convert JPEG to WebP with quality 85:

python scripts/convert.py input.jpg output.webp --quality 85

Convert directory to WebP (keeps original files):

python scripts/convert.py ./images/ ./webp_output/

Lossless compression:

python scripts/convert.py input.png output.webp --lossless

Scale image (longest edge 1920px):

python scripts/convert.py input.jpg output.webp --max-size 1920

Batch compress directory (preserves format):

python scripts/convert.py ./images/ ./compressed/ --compress

功能列表

功能	说明
相互转换	支持常见图像格式之间的相互转换
批量转换	支持目录、文件列表、逗号分隔、通配符输入
并行处理	多线程批量转换加速
质量控制	有损压缩质量 1-100
无损模式	保持原始像素质量
尺寸缩放	按最长边等比缩放
色彩空间	自动转换 CMYK→RGB，调色板→RGBA
元数据	清除 EXIF，保留 ICC 配置文件
格式保留压缩	保留原格式进行压缩（PNG/JPEG/GIF/WebP/TIFF）

CLI 参数

转换参数 (Conversion Options)

参数	说明	默认值
`--to-format`	明确指定目标格式 (jpeg, png, webp, gif, bmp, tiff)，优先级高于输出扩展名	无
`--quality`	压缩质量 (1-100)	90
`--max-size`	最长边缩放像素	不缩放
`--lossless`	启用无损压缩	False

压缩参数（保留原格式）

参数	说明	默认值
`--compress`	启用压缩模式，保留原格式	False
`--compress-quality`	压缩质量 (1-100)	85
`--compress-level`	PNG/TIFF 压缩级别 (0-9)	6

批量处理参数

参数	说明	默认值
`--threads`	并行处理线程数	1
`--verbose`, `-v`	显示详细进度信息	False

参考

详细 WebP 参数配置请查看 webp_settings.md。

安全使用建议

This skill appears to do exactly what it says: convert and compress images using Pillow. Before installing or running it, consider: 1) install Pillow from the official PyPI (pip install Pillow) in a virtualenv to avoid contaminating system Python; ignore or verify the 'uv add' instruction if you don't know that tool; 2) inspect/track the included scripts (you already have them); run them on test images first and avoid giving it sensitive files — the script reads and writes local image files and can create output directories; 3) be aware that processing large or malformed images can consume CPU/memory (deny large uploads or limit --threads); 4) the skill source/homepage is unknown and the published name has a typo, which could indicate low maintenance — if you rely on this in production, prefer a package from a known repository or maintain your own copy. Overall the bundle is internally consistent and does not show signs of data exfiltration or unrelated access.

功能分析

Type: OpenClaw Skill Name: image-convert-skill Version: 0.1.2 The skill bundle is a legitimate image conversion utility using the Pillow library. The main script `scripts/convert.py` provides robust functionality for format conversion, resizing, and batch processing with no evidence of malicious behavior, data exfiltration, or suspicious instructions.

能力评估

✓ Purpose & Capability

The name/description (image conversion, compression, resizing) align with the included CLI script (scripts/convert.py) and the reference doc. Required capabilities are limited to Pillow; no unrelated credentials, binaries, or host services are requested. Minor notes: the published skill name has a typo ('Imgae') and the package source/homepage are unknown, but these are metadata issues, not functional mismatches.

✓ Instruction Scope

SKILL.md limits runtime actions to installing Pillow (pip) and running the provided convert script with local files/dirs and CLI flags. The instructions do not ask the agent to read unrelated system files, environment variables, or contact external endpoints. Note: the doc mentions 'uv add Pillow' (a nonstandard/unknown package manager invocation) — this is unusual but not harmful by itself.

✓ Install Mechanism

There is no automated install spec (instruction-only), so nothing is written to disk by an installer beyond running the included script. The README instructs the user to pip install Pillow (standard). Because there's no download/install step embedded in the skill bundle, install risk is low.

✓ Credentials

The skill declares no required environment variables or credentials and the script does not access env vars or external secret/config paths. The requested privileges are proportional to an image-conversion tool.

✓ Persistence & Privilege

always is false and model invocation is allowed (the platform default). The skill does not attempt to modify other skills or system-wide settings and does not request permanent presence or elevated privileges.

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 image-convert-skill
安装完成后，直接呼叫该 Skill 的名称或使用 /image-convert-skill 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

v0.1.2

GitHub: https://github.com/KanoCifer/image-convert-skill

v0.1.1

- Initial version supporting conversion and compression between common image formats (PNG, JPEG, GIF, BMP, TIFF, WebP). - Supports batch conversion, comma-separated/wildcard/directory input, with parallel processing for improved efficiency. - Offers lossy/lossless compression, quality control, and resizing capabilities. - Automatically handles color space conversion, removes EXIF data/preserves ICC profiles. - Comprehensive command-line arguments, compatible with old WebP usage, compression mode can preserve original format. - 初始版本，支持常见图像格式（PNG、JPEG、GIF、BMP、TIFF、WebP）之间互转与压缩。 - 支持批量转换、逗号分隔/通配符/目录输入，并行处理提升效率。 - 提供有损/无损压缩、质量控制、尺寸缩放等功能。 - 自动处理色彩空间转换，清除EXIF/保留ICC配置文件。 - 命令行参数全面，兼容旧的WebP用法，压缩模式可保留原格式。

元数据

Slug image-convert-skill

版本 0.1.2

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 2

常见问题