效率需要联网clawhub未标认证来源可访问clear审计通过

media-compress（媒体压缩）

Agent Skill

media-compress 用于处理图像、截图、视觉识别或图片素材相关工作，适合在 OpenClaw 中需要让 Agent 分析图片、整理视觉素材或辅助图像流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

总安装

5,484

周安装

224

GitHub Stars

公开资料未说明

下载量

1,774

OpenClaw

安装说明

本站只整理中文说明和来源信息，不托管安装包，也不代用户安装。

GitHub

来源数

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手，先确认命令和权限，再让它执行。

请帮我安装这个 Agent Skill：media-compress（媒体压缩）
来源仓库：https://github.com/1987566643/media-compress
安装命令：
openclaw skills install media-compress
安装前请先检查当前环境是否支持对应 CLI，并向我确认将要执行的命令、安装目录、联网范围和文件读写权限；确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill；本站只展示命令，不托管安装包，也不自动执行。

ClawHubOpenClaw

openclaw skills install media-compress

简介

使用 ffmpeg 压缩与转换图像、音频及视频文件格式。

适用于存储空间优化、传输加速或格式统一化处理场景。
支持批量处理与质量调节，平衡文件大小与画质损失。media-compress 属于效率类 Skill，可作为该场景下的辅助能力补充。
使用前需指定输入输出路径与编码参数，避免误删原文件。
注意：极端压缩可能导致音画失真，建议根据用途选择合适码率。

SKILL.md

name: media-compress
description: Compress and convert images and videos using ffmpeg. Use when the user wants to reduce file size, change format, resize, or optimize media files. Handles common formats like JPG, PNG, WebP, MP4, MOV, WebM. Triggers on phrases like "compress image", "compress video", "reduce file size", "convert to webp/mp4", "resize image", "make image smaller", "batch compress", "optimize media".

Media Compression Skill

Compress and convert images and videos with intelligent defaults. Supports single files and batch processing.

Supported Formats

Images: JPG, PNG, WebP, BMP, TIFF, GIF → JPG, PNG, WebP Videos: MP4, MOV, AVI, MKV, WebM, FLV, WMV, M4V → MP4

Prerequisites

ffmpeg must be installed:

Ubuntu/Debian: sudo apt update && sudo apt install ffmpeg
macOS: brew install ffmpeg
Windows: Download from https://ffmpeg.org/download.html and add to PATH

Verify installation: ffmpeg -version

Quick Start

Image Compression

# Compress to target size (auto-adjusts quality)
python scripts/compress_image.py photo.jpg --max-size 200kb

# Resize + compress
python scripts/compress_image.py photo.png --width 800 --output photo_small.jpg

# Convert to WebP (better compression)
python scripts/compress_image.py photo.jpg --format webp

# Batch compress entire folder
python scripts/compress_image.py ./photos --output ./compressed --quality 80

# Preview mode - see what will happen without compressing
python scripts/compress_image.py photo.jpg --max-size 500kb --preview

# Keep backup of original file
python scripts/compress_image.py photo.jpg --max-size 500kb --backup

Video Compression

# Compress with default settings (good balance)
python scripts/compress_video.py video.mp4 --output video_small.mp4

# Resize to 720p
python scripts/compress_video.py video.mp4 --height 720

# Target specific file size (approximate)
python scripts/compress_video.py video.mp4 --target-size 50mb

# Lower quality for smaller file
python scripts/compress_video.py video.mp4 --crf 28

# Batch process all videos in folder
python scripts/compress_video.py ./videos --output ./compressed --height 480

# Preview mode - see what will happen without compressing
python scripts/compress_video.py video.mp4 --height 720 --preview

# Keep backup of original file
python scripts/compress_video.py video.mp4 --height 720 --backup

Common Use Cases

1. Upload to Website (Image)

Most websites need images under 500KB:

python scripts/compress_image.py photo.jpg --max-size 500kb --format webp

2. Email Attachment (Image)

Email often has 25MB limit:

python scripts/compress_image.py scan.pdf.jpg --max-size 5mb --quality 90

3. Social Media Video

Platforms prefer 720p, smaller files:

python scripts/compress_video.py clip.mov --height 720 --crf 23 --preset fast

4. Archive Old Videos

Maximum compression for storage:

python scripts/compress_video.py old_video.avi --crf 28 --preset slow --height 480

5. Convert Format Only

Keep quality, just change format:

# Image
python scripts/compress_image.py image.png --format jpg --quality 95

# Video
python scripts/compress_video.py video.mov --output video.mp4 --crf 18

Parameters Reference

Image (`compress_image.py`)

Parameter	Description	Default
`input`	Input file or directory (required)	-
`--output, -o`	Output file or directory	Auto-generated
`--max-size`	Target max file size (e.g., 500kb, 2mb)	None
`--quality, -q`	JPEG/WebP quality (1-100)	85
`--width, -w`	Max width in pixels	Original
`--height`	Max height in pixels	Original
`--format, -f`	Output format: jpg, png, webp	Original format
`--no-strip`	Keep metadata (default: remove)	False
`--preview, -p`	Preview mode: show settings without compressing	False
`--backup, -b`	Keep backup of original file	False

Video (`compress_video.py`)

Parameter	Description	Default
`input`	Input file or directory (required)	-
`--output, -o`	Output file or directory	Auto-generated
`--crf`	Quality 0-51 (lower=better). 18=visually lossless, 23=default, 28=smaller	23
`--preset`	Encoding speed: ultrafast, superfast, veryfast, faster, fast, medium, slow, slower, veryslow	medium
`--height`	Max height (480, 720, 1080)	Original
`--target-size`	Approximate target size (e.g., 50mb, 1gb)	None
`--fps`	Limit frame rate (e.g., 30, 24)	Original
`--audio-bitrate`	Audio quality (e.g., 128k, 192k)	128k
`--preview, -p`	Preview mode: show settings without compressing	False
`--backup, -b`	Keep backup of original file	False

Quality Guidelines

Images

90-95: High quality, minimal compression artifacts
85: Sweet spot (default) - good quality, significant size reduction
70-80: Acceptable for web, smaller files
50-60: Low quality, visible artifacts

Videos (CRF)

17-18: Visually lossless, archival quality
20-22: High quality, professional use
23: Default, good balance (recommended)
28: Smaller files, acceptable quality
35+: Low quality, preview/draft only

Presets

ultrafast: Fastest encoding, largest files
fast: Quick results, slightly larger
medium: Default balance
slow: Better compression, smaller files
veryslow: Maximum compression, smallest files

Batch Processing

When input is a directory:

All supported files are processed
Output directory structure mirrors input
Progress shown for each file
Original and compressed sizes displayed

Example:

$ python scripts/compress_image.py ./vacation_photos --output ./compressed --max-size 500kb
找到 24 个图像文件
[1/24] 处理: IMG_001.jpg
  ✓ 2847.3KB → 456.2KB (84.0% 减少)
[2/24] 处理: IMG_002.png
  ✓ 1532.1KB → 298.5KB (80.5% 减少)
...

Troubleshooting

"ffmpeg not found"

Install ffmpeg first:

# Ubuntu/Debian
sudo apt update && sudo apt install ffmpeg

# macOS
brew install ffmpeg

"Permission denied"

Make scripts executable:

chmod +x scripts/*.py

Quality too low

Increase quality setting:

# Image
python scripts/compress_image.py photo.jpg --quality 90

# Video
python scripts/compress_video.py video.mp4 --crf 20

File not smaller

Try lower quality or smaller dimensions
Some files are already optimally compressed
Use --max-size to force target size

Batch processing stops

Check that all files in directory are valid images/videos. Corrupt files may cause errors.

Advanced Tips

Strip metadata for privacy (default behavior)
Use WebP for best web compression
720p height is usually enough for mobile viewing
CRF 23 + preset slow gives great results for archiving
Test with one file before batch processing

References

FFmpeg Guide - Detailed ffmpeg commands and parameters

适合场景

OpenClaw 用户查找和安装 Skill 时

用户想查找某类 Agent Skill 时

需要根据任务场景推荐可安装能力包时

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明，方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用；具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

91.71%

按下载量换算1,627

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API；具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息，不托管安装包，不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源，正式发布前建议补源仓库或其他目录站核验。

来源信息

GitHub 仓库

github.com

/1987566643/media-compress

SKILL.md 来源

clawhub.ai