← Back to Skills Marketplace
468
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install cutmv-video-tool
Description
Perform video/audio cutting, format conversion, compression, frame/audio extraction, watermarking, and subtitle addition using FFmpeg.
README (SKILL.md)
SKILL.md - cutmv Video Tool
Skill Name
cutmv-video-tool
Description
A video processing skill for OpenClaw that leverages FFmpeg to perform video/audio cutting, format conversion, and compression. Perfect for handling video files for messaging apps with file size limits.
Capabilities
- Video Cutting: Split video/audio by time range
- Format Conversion: Convert between video/audio formats (mp4, avi, mp3, wav, etc.)
- Video Compression: Compress videos with adjustable bitrate
- Frame Extraction: Extract frames from videos at specified intervals
- Audio Extraction: Extract audio track from video
- Audio Replacement: Replace or mix audio in video
- Text Watermark: Add text overlay on video (requires freetype)
- Subtitle: Add .srt/.ass subtitle files to video
Use Cases
- Compress videos to send via WeChat/Lark/Telegram (16MB limit)
- Extract screenshots from videos for analysis
- Convert video formats for different platforms
- Cut specific segments from long videos
Requirements
System Requirements
- FFmpeg installed and available in PATH
- Python 3.7+
Python Dependencies
- None (uses subprocess to call ffmpeg)
Installation
-
Ensure FFmpeg is installed on your system:
- macOS:
brew install ffmpeg - Ubuntu:
sudo apt install ffmpeg - Windows: Download from ffmpeg.org or
winget install ffmpeg
- macOS:
-
Place the skill files in your workspace:
~/openclaw-workspace/skills/cutmv-video-tool/ ├── SKILL.md ├── skill.py ├── README.md └── README-CN.md
Usage
Python API
from skill import VideoTool
tool = VideoTool()
# Compress video for messaging
tool.compress("input.mp4", "output.mp4", bitrate="1000k")
# Cut video segment
tool.cut("input.mp4", "clip.mp4", start_time=30, end_time=90)
# Convert format
tool.convert("input.mp4", "output.avi", "avi")
# Extract frames every 10 seconds
tool.extract_frames("input.mp4", "./frames/", interval=10)
CLI Usage
# Compress video
python skill.py compress input.mp4 output.mp4 1000k
# Cut video
python skill.py cut input.mp4 clip.mp4 0 60
# Convert format
python skill.py convert input.mp4 output.mp3 mp3
Configuration
No additional configuration required. The skill uses system FFmpeg installation.
Testing
Run the built-in tests:
python skill.py test
License
MIT License
Author
- Isaac (@QiaoTuCodes)
Acknowledgments
- OpenClaw team for the platform
- FFmpeg team for media processing tools
Author Identity: yanyan@3c3d77679723a2fe95d3faf9d2c2e5a65559acbc97fef1ef37783514a80ae453
Usage Guidance
This skill appears to do only local video processing via your system ffmpeg and does not request secrets or network endpoints. Before installing: (1) ensure ffmpeg is from a trusted source (official builds) because the skill will execute it on files you provide; (2) be aware that running ffmpeg on untrusted media can expose ffmpeg vulnerabilities—avoid processing files from unknown sources; (3) if you want maximum assurance, inspect skill.py (particularly the eval() use for frame-rate parsing) and consider replacing eval with a safe parser; (4) note that the repository/source metadata and homepage are missing — if provenance is important, ask the author for a repository or signed release.
Capability Analysis
Type: OpenClaw Skill
Name: cutmv-video-tool
Version: 1.0.0
The `skill.py` file contains critical vulnerabilities. Most notably, the `get_video_info` method uses `eval()` on the `r_frame_rate` value obtained from `ffprobe` output. This creates a Remote Code Execution (RCE) vulnerability, as a specially crafted video file could embed malicious Python code in its metadata, which would then be executed. Additionally, the `add_subtitle` method directly inserts user-provided `subtitle_file` and `style` parameters into FFmpeg filter strings without proper escaping, leading to potential FFmpeg filter injection. Path traversal is also possible as input/output file paths are used directly without sanitization. These are severe vulnerabilities that could be exploited, classifying the skill as suspicious.
Capability Assessment
Purpose & Capability
Name/description (video cutting, conversion, compression, frame/audio extraction, watermarking, subtitles) align with the code and SKILL.md. The skill only requires FFmpeg on PATH and Python 3.7+, which is appropriate for the claimed functionality. The package does not request unrelated binaries, env vars, or config paths.
Instruction Scope
SKILL.md and skill.py direct the agent to run local ffmpeg/ffprobe subprocesses and operate on local files only, which matches the purpose. Minor note: skill.py uses eval(video_stream.get('r_frame_rate', '0/1')) to compute FPS from ffprobe output — this is convenient but introduces a small code-injection risk if ffprobe output is tampered with or maliciously crafted. Otherwise instructions do not read unrelated files or exfiltrate data.
Install Mechanism
No install spec; this is an instruction-only skill that expects a system ffmpeg. No remote downloads or extracted archives are executed by the skill, minimizing install-time risk.
Credentials
The skill requests no environment variables, credentials, or config paths. All operations are local filesystem and subprocess calls to ffmpeg/ffprobe, which is proportionate to video processing.
Persistence & Privilege
always is false and the skill does not request persistent system-wide changes or modify other skill configs. It does not declare autonomous elevation or special privileges beyond normal execution.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install cutmv-video-tool - After installation, invoke the skill by name or use
/cutmv-video-tool - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of cutmv-video-tool for OpenClaw.
- Provides video/audio cutting, format conversion, and compression using FFmpeg.
- Supports frame extraction, audio extraction and replacement, text watermarks, and subtitle embedding.
- Usable via Python API or command-line interface.
- No external Python dependencies required beyond FFmpeg in PATH.
- Suitable for preparing media files for messaging apps with size constraints.
Metadata
Frequently Asked Questions
What is cutmv Video Tool?
Perform video/audio cutting, format conversion, compression, frame/audio extraction, watermarking, and subtitle addition using FFmpeg. It is an AI Agent Skill for Claude Code / OpenClaw, with 468 downloads so far.
How do I install cutmv Video Tool?
Run "/install cutmv-video-tool" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is cutmv Video Tool free?
Yes, cutmv Video Tool is completely free (open-source). You can download, install and use it at no cost.
Which platforms does cutmv Video Tool support?
cutmv Video Tool is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created cutmv Video Tool?
It is built and maintained by 魏然 (@qiaotucodes); the current version is v1.0.0.
More Skills