← 返回 Skills 市场
57
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-to-audio
功能描述
Skip the learning curve of professional editing software. Describe what you want — extract the audio track from my video as an MP3 file — and get extracted a...
安全使用建议
This skill uploads your video files to an external backend (mega-api-prod.nemovideo.ai) for processing and requires a NEMO_TOKEN (or will request an anonymous token on first use). Before installing: (1) confirm you trust the remote service and are comfortable with your media being uploaded to that domain; (2) verify the token scope and retention policy (anonymous tokens are described as 7-day, 100 free credits); (3) note the small metadata mismatch (SKILL.md lists a config path ~/.config/nemovideo/ while registry metadata did not) — ask the author which is authoritative; (4) if you need stronger privacy, avoid using the skill or only upload non-sensitive clips; (5) prefer skills with a known homepage or owner for accountability. If you want higher assurance, ask the publisher for a privacy/security statement and a canonical endpoint and compare that to the endpoints in SKILL.md.
功能分析
Type: OpenClaw Skill
Name: video-to-audio
Version: 1.0.0
The skill is a legitimate integration for a cloud-based video processing service (nemovideo.ai). It defines standard API workflows for authentication, file uploading, and audio extraction via remote GPU nodes. No evidence of data exfiltration, malicious command execution, or harmful prompt injection was found; the instructions in SKILL.md are strictly focused on managing the API lifecycle and session state.
能力评估
Purpose & Capability
The skill claims to upload video files and run a cloud render pipeline; requesting an API token (NEMO_TOKEN) and calling the listed nemo API endpoints is coherent with that purpose. The attribution headers and session flow described match a remote-processing design.
Instruction Scope
Instructions explicitly tell the agent to upload user media, create sessions, read/maintain a session_id, and stream SSE responses — all expected for a cloud render workflow. They also instruct generating an anonymous token when NEMO_TOKEN is absent and to auto-detect an install platform from an install path; the latter implies the agent may inspect its environment/install path. This is expected for header population but is broader than a purely local-only tool and should be understood before use.
Install Mechanism
No install spec or downloads are present (instruction-only). Nothing is written to disk by an installer in the skill bundle itself, which is the lowest install risk.
Credentials
The skill requests a single credential (NEMO_TOKEN) which is proportional to a remote processing service. Two small discrepancies: (1) the registry metadata you provided lists no required config paths, but the SKILL.md frontmatter's metadata lists a config path (~/.config/nemovideo/), and (2) the SKILL.md also describes generating an anonymous token when NEMO_TOKEN is absent — meaning the skill can obtain a transient token itself. Both are explainable but worth noting before trusting the skill.
Persistence & Privilege
The skill is not always-on and does not request elevated platform privileges. It uses short-lived session tokens for cloud jobs; nothing in the skill attempts to modify other skills or system-wide settings.
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-to-audio - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-to-audio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 the Video to Audio skill — extract audio from video files easily.
- Upload MP4, MOV, AVI, or WebM files (up to 500MB) and extract audio tracks as MP3 in seconds.
- No installation or complex setup required; automatic backend session and token management.
- Clear user commands for uploading files, checking credits, export, and status tracking.
- Real-time cloud processing: audio extraction via remote GPU with timely feedback.
- Supports multiple workflows: quick single file, batch, and iterative editing sessions.
- Helpful prompts, clear status updates, and error handling for smooth user experience.
元数据
常见问题
Video To Audio 是什么？
Skip the learning curve of professional editing software. Describe what you want — extract the audio track from my video as an MP3 file — and get extracted a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 57 次。
如何安装 Video To Audio？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-to-audio」即可一键安装，无需额外配置。
Video To Audio 是免费的吗？
是的，Video To Audio 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video To Audio 支持哪些平台？
Video To Audio 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 To Audio？
由 mory128（@mory128）开发并维护，当前版本 v1.0.0。
推荐 Skills