← 返回 Skills 市场
Objectremover Video
作者
mhogan2013-9
· GitHub ↗
· v1.0.0
· MIT-0
61
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install objectremover-video
功能描述
Skip the learning curve of professional editing software. Describe what you want — remove the car parked in the background from the entire video — and get cl...
安全使用建议
This skill will upload your videos to an external service (mega-api-prod.nemovideo.ai) for processing and will use or create a NEMO_TOKEN for API access. Before installing: 1) Confirm the service/operator and privacy policy for uploaded media (sensitive videos will leave your device). 2) Prefer supplying your own NEMO_TOKEN if you want control over identity/credentials rather than letting the skill obtain an anonymous token. 3) Ask the publisher to clarify the config path behavior: will the skill read/write ~/.config/nemovideo/ or other local files? Where are generated tokens/client IDs stored and for how long? 4) If you are uncomfortable with automatic uploads or persistent tokens, do not install or set disable-model-invocation/autonomous usage to restrict automatic runs. 5) Because this is instruction-only (no code to audit), treat network calls and credential creation as the primary risk surface.
功能分析
Type: OpenClaw Skill
Name: objectremover-video
Version: 1.0.0
The objectremover-video skill is a legitimate integration for the NemoVideo AI service, designed to automate video object removal via a cloud API. The SKILL.md file provides clear instructions for authentication (using NEMO_TOKEN or an anonymous token flow), file uploading, and session management with the backend at mega-api-prod.nemovideo.ai. There is no evidence of data exfiltration, unauthorized command execution, or malicious prompt injection; the requested environment and file access are strictly aligned with the stated purpose of video processing.
能力评估
Purpose & Capability
The skill's name/description (remote AI object removal) aligns with the actions described (upload, render, export). Requested primary credential (NEMO_TOKEN) is appropriate for a cloud API. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata earlier reported no required config paths — this mismatch should be clarified (will the skill read/write local config?).
Instruction Scope
Instructions direct the agent to perform network operations (anonymous token generation, session creation, SSE streaming, file uploads) which are expected for a cloud-render service. They also instruct 'auto-detect' platform from the install path and reference a local config path — that implies the agent may read filesystem locations beyond just environment variables. The skill also auto-generates and uses anonymous tokens if NEMO_TOKEN is not present; this behavior should be explicit to the user and the storage location for created tokens should be confirmed.
Install Mechanism
No install spec or code files are present (instruction-only). That minimizes disk-write risk; the skill does not download or install arbitrary third-party code.
Credentials
Only NEMO_TOKEN is declared (primary credential), which is proportionate. But the SKILL.md will create/use an anonymous NEMO_TOKEN if none is provided and may expect or write config under ~/.config/nemovideo/ (frontmatter). The registry said no config paths, so it's unclear whether the skill will persist tokens or client IDs locally. Automatic token creation and implicit storage increases privacy/credential risk if not made explicit.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. Still, its runtime behavior includes creating tokens and long-lived sessions/SSE connections and may persist a client id or token to a config path (per frontmatter). Confirm whether the skill will persist credentials or other state and where.
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 objectremover-video - 安装完成后，直接呼叫该 Skill 的名称或使用
/objectremover-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
- Initial release of objectremover-video skill for automatic object removal from video clips.
- Supports uploads up to 500MB in MP4, MOV, AVI, and WebM formats.
- Cloud-based processing—describe editing requests and get results in 1-2 minutes.
- Automatic setup: handles token, session, and backend connection for you.
- Covers export, credits, upload, and session management with clear error handling.
- Ideal for creators wanting distraction-free videos without manual editing.
元数据
常见问题
Objectremover Video 是什么？
Skip the learning curve of professional editing software. Describe what you want — remove the car parked in the background from the entire video — and get cl... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 61 次。
如何安装 Objectremover Video？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install objectremover-video」即可一键安装，无需额外配置。
Objectremover Video 是免费的吗？
是的，Objectremover Video 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Objectremover Video 支持哪些平台？
Objectremover 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 Objectremover Video？
由 mhogan2013-9（@mhogan2013-9）开发并维护，当前版本 v1.0.0。
推荐 Skills