← 返回 Skills 市场
Video Local
作者
linmillsd7
· GitHub ↗
· v1.0.0
· MIT-0
48
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-local
功能描述
Skip the learning curve of professional editing software. Describe what you want — trim the intro, add background music, and export for YouTube — and get edi...
安全使用建议
This skill claims to edit "local" videos but the runtime instructions upload your files to a remote API (mega-api-prod.nemovideo.ai) and may probe local paths (~/.clawhub/, ~/.cursor/skills/, ~/.config/nemovideo/) to set headers — so it is not offline/local-only. Before installing or using it: (1) assume your videos will be transmitted to the vendor's servers; do not send sensitive footage. (2) Ask the publisher how long uploads and derived data are retained, who operates the endpoint, and whether uploads are encrypted/isolated. (3) If you need true local-only editing, do not use this skill. (4) Consider testing with a non-sensitive short clip first and only provide a minimal-scoped token (or use the anonymous token flow) if you accept cloud processing. (5) Note the metadata inconsistency about config paths and ask the author to clarify why the skill needs to inspect local directories.
功能分析
Type: OpenClaw Skill
Name: video-local
Version: 1.0.0
The skill is a functional integration for a cloud-based video editing service (nemovideo.ai). It provides instructions for the agent to manage sessions, upload video files, and poll for rendering status. While it involves uploading local files to a remote API and managing an API token (NEMO_TOKEN), these actions are transparently documented and directly support the stated purpose of AI-assisted video editing. No evidence of malicious intent, data exfiltration of sensitive system files, or unauthorized execution was found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
The name/description emphasize "local" editing, but the SKILL.md describes uploading user video files to https://mega-api-prod.nemovideo.ai and doing all rendering server-side. That is a meaningful mismatch between user expectation (local-only) and actual behavior. Additionally, the SKILL.md metadata declares a required configPaths (~/.config/nemovideo/) and detection of install paths (~/.clawhub/, ~/.cursor/skills/), which are not reflected in the registry requirement summary — another inconsistency.
Instruction Scope
Runtime instructions tell the agent to: generate an anonymous token (POST /api/auth/anonymous-token), create sessions, upload local files via multipart POST (/api/upload-video/...), stream SSE (/run_sse), poll render status, and include many headers. They also instruct detecting local install paths to set X-Skill-Platform, which implies reading filesystem paths (~/.clawhub/, ~/.cursor/skills/) and potentially ~/.config/nemovideo/. These filesystem checks and uploads go beyond simple editing instructions and can reveal environment information and transmit user files to a third-party API — inconsistent with a strictly local editing claim.
Install Mechanism
Instruction-only skill with no install steps or downloaded code, so it does not write new binaries to disk or pull remote archives. This is the lowest install risk.
Credentials
The skill requests a single credential (NEMO_TOKEN) which is appropriate for a hosted service. However, SKILL.md metadata also references a config path (~/.config/nemovideo/) and requires detecting installation directories; that expands the scope of data the agent may read beyond just one token and is not justified by the registry metadata inconsistency.
Persistence & Privilege
The skill does not request always:true and has no install-time hooks. It instructs saving session_id and using tokens for API calls, which is normal for session-based APIs and does not indicate elevated platform privileges or modifications to other skills.
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-local - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-local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 Video Local — fast, simple AI-powered editing for local video files.
- Upload MP4, MOV, AVI, or WebM files up to 500MB and get AI-edited videos in 1–2 minutes.
- Edit by describing your needs (e.g., trim, add audio, export for YouTube) without using complex software.
- Automatic session and token management for quick onboarding; free token available at startup.
- Cloud GPU rendering with easy export/download, supporting various formats and quality settings.
- Simple commands for editing, status check, credits, and export, all managed via a streamlined chat workflow.
元数据
常见问题
Video Local 是什么？
Skip the learning curve of professional editing software. Describe what you want — trim the intro, add background music, and export for YouTube — and get edi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 48 次。
如何安装 Video Local？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-local」即可一键安装，无需额外配置。
Video Local 是免费的吗？
是的，Video Local 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Local 支持哪些平台？
Video Local 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 Local？
由 linmillsd7（@linmillsd7）开发并维护，当前版本 v1.0.0。
推荐 Skills