← 返回 Skills 市场
Video Frames
作者
utromaya-code
· GitHub ↗
· v1.0.1
· MIT-0
797
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install video-clip-extractor
功能描述
Extract frames or short clips from videos using ffmpeg.
使用说明 (SKILL.md)
Video Frames (ffmpeg)
Extract a single frame from a video, or create quick thumbnails for inspection.
Quick start
First frame:
{baseDir}/scripts/frame.sh /path/to/video.mp4 --out /tmp/frame.jpg
At a timestamp:
{baseDir}/scripts/frame.sh /path/to/video.mp4 --time 00:00:10 --out /tmp/frame-10s.jpg
Notes
- Prefer
--timefor “what is happening around here?”. - Use a
.jpgfor quick share; use.pngfor crisp UI frames.
安全使用建议
This skill is straightforward: it runs a small bash wrapper around ffmpeg to extract frames and will install ffmpeg via Homebrew if needed. Before installing: ensure you are comfortable allowing brew to install ffmpeg; use the official ffmpeg package source; and be aware that processing untrusted video files can be risky because vulnerabilities have existed in ffmpeg in the past — consider running on trusted inputs or in a sandbox if the videos come from unknown sources. No credentials are requested and the skill does not transmit data off your machine.
功能分析
Type: OpenClaw Skill
Name: video-clip-extractor
Version: 1.0.1
The skill bundle is a straightforward utility for extracting video frames using ffmpeg. The shell script 'scripts/frame.sh' implements basic argument parsing and executes ffmpeg commands with proper variable quoting to mitigate common injection risks. No evidence of malicious intent, data exfiltration, or prompt injection was found.
能力评估
Purpose & Capability
Name/description match the included files and runtime instructions. The only runtime dependency is ffmpeg (declared) and the script operates on a user-supplied video file to produce a local output image.
Instruction Scope
SKILL.md and scripts/frame.sh only read the provided input video and write the specified output path. No reading of unrelated files, no network endpoints, no collection or transmission of extra data, and no vague 'gather whatever context you need' instructions.
Install Mechanism
Install is limited to a homebrew formula (ffmpeg) which is a standard, well-known package source; no arbitrary downloads or archive extraction are used.
Credentials
No environment variables, credentials, or config paths are required. The requested resources are proportional to the stated purpose.
Persistence & Privilege
Skill is not always-enabled and does not request persistent system-wide changes or access to other skills' configurations. Default autonomous invocation is unchanged (normal).
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 video-clip-extractor - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-clip-extractor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
v1.0.1
- Updated SKILL.md to rename the skill to "video-frames" and clarify its purpose as extracting frames or short clips from videos using ffmpeg.
- Added clear quick start instructions for extracting frames at default or specific timestamps.
- Included installation guidance for ffmpeg via Homebrew.
- Provided practical notes for choosing output formats and times.
元数据
常见问题
Video Frames 是什么？
Extract frames or short clips from videos using ffmpeg. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 797 次。
如何安装 Video Frames？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-clip-extractor」即可一键安装，无需额外配置。
Video Frames 是免费的吗？
是的，Video Frames 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Frames 支持哪些平台？
Video Frames 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Video Frames？
由 utromaya-code（@utromaya-code）开发并维护，当前版本 v1.0.1。
推荐 Skills