← 返回 Skills 市场
127
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install unified-video
功能描述
Skip the learning curve of professional editing software. Describe what you want — combine all clips into one seamless video with smooth transitions — and ge...
安全使用建议
This skill appears to implement a remote video-merge service and will upload files to mega-api-prod.nemovideo.ai; that behavior is expected for this purpose. Before installing or using it: (1) Confirm the source/owner and ask for a privacy policy and data retention policy — do not upload sensitive or private videos until you know where they are stored and for how long. (2) Ask whether the skill will write anything to ~/.config/nemovideo/ or persist the anonymous token; prefer ephemeral tokens and explicit user consent for persistent storage. (3) Note the skill can auto-create an anonymous NEMO_TOKEN if none is provided — this is convenient but means uploads can proceed without you supplying a token. (4) If you need stronger guarantees, request a documented API endpoint list, TLS/CA expectations, and whether media is encrypted at rest. The metadata inconsistency (declared configPath in SKILL.md vs. registry showing none) is why I marked this suspicious rather than benign; if the developer confirms no local config access and provides a privacy policy, confidence could be raised.
功能分析
Type: OpenClaw Skill
Name: unified-video
Version: 1.0.0
The unified-video skill is a functional integration for the nemovideo.ai cloud video editing service. The SKILL.md file provides detailed instructions for an AI agent to manage authentication, handle file uploads, and interact with a remote rendering pipeline via API endpoints (mega-api-prod.nemovideo.ai). The behavior is entirely consistent with the stated purpose of merging video clips, and the instructions include security-conscious directives such as not exposing tokens or raw API output to the user.
能力评估
Purpose & Capability
The skill is described as a cloud video merging service and its runtime instructions call a remote rendering API and upload media — that is coherent. However the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) that the registry metadata did not list; this mismatch is unexplained.
Instruction Scope
Instructions are explicit about uploading files, creating sessions, streaming SSE, polling render status, and attaching attribution headers. The agent is told to read this skill's YAML frontmatter and detect install path to set X-Skill-Platform — which requires filesystem access. No other unrelated files or secrets are requested, but the skill will send user-uploaded media to an external API (mega-api-prod.nemovideo.ai).
Install Mechanism
No install spec or code is included (instruction-only). Nothing is written to disk by an installer, which minimizes supply-chain risk.
Credentials
The skill declares NEMO_TOKEN as the primary credential (expected for a cloud API). But the SKILL.md also instructs the agent to request an anonymous token from the same API if NEMO_TOKEN is absent — and the frontmatter lists a config path (~/.config/nemovideo/) that could imply reading/writing local config. The registry metadata earlier listed no config paths, creating an inconsistency. The required credential and anonymous-token flow are plausible but you should confirm whether the skill will persist tokens or write config files locally and whether the config path is actually used.
Persistence & Privilege
The skill does not request always:true, has no install hooks, and uses ephemeral session tokens. It keeps session_id for ongoing jobs but does not request system-wide privileges.
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 unified-video - 安装完成后，直接呼叫该 Skill 的名称或使用
/unified-video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
Unified Video skill initial release.
- Seamlessly merges multiple video clips (MP4, MOV, AVI, WebM) up to 500MB into one MP4 with AI-powered transitions and optional silence trimming.
- No editing software required; handles session creation, cloud rendering, and file management automatically.
- Supports quick combining, batch processing, and iterative editing within one chat session.
- Cloud-based processing; standard export completes in 1–2 minutes for typical clips.
- Includes user-friendly commands for upload, download, credits, and status tracking.
- Built-in error handling for file types, sizes, and common authentication issues.
元数据
常见问题
Unified Video 是什么？
Skip the learning curve of professional editing software. Describe what you want — combine all clips into one seamless video with smooth transitions — and ge... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 127 次。
如何安装 Unified Video？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install unified-video」即可一键安装，无需额外配置。
Unified Video 是免费的吗？
是的，Unified Video 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Unified Video 支持哪些平台？
Unified Video 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 Unified Video？
由 tk8544-b（@tk8544-b）开发并维护，当前版本 v1.0.0。
推荐 Skills