← 返回 Skills 市场
Video Open Ai
作者
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
75
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-open-ai
功能描述
Get AI-edited videos ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "trim th...
安全使用建议
This skill's runtime behavior (uploading clips to https://mega-api-prod.nemovideo.ai and using a NEMO_TOKEN) is consistent with a cloud video-editing tool, but take these precautions before installing or using it:
- Provenance: There is no homepage or clear publisher; if you don't trust the owner, avoid installing or uploading private/sensitive videos.
- Token scope: NEMO_TOKEN grants the skill API access to your account or anonymous credits. Prefer short-lived anonymous tokens if available and revoke tokens you didn't intend to keep.
- Data exposure: Uploaded videos will be sent to an external service; review the service's privacy and retention policies (not provided). Do not upload sensitive PII or private footage until you verify the vendor.
- Metadata mismatch: The SKILL.md frontend lists a local config path (~/.config/nemovideo/) even though registry metadata omitted it — ask the publisher to clarify whether the skill will read or write local config files.
- Persistence: Ask where the agent stores session_id and token data and how to remove them; if you cannot confirm safe storage/revocation, avoid long-term installation.
If you decide to proceed, prefer using an anonymous token flow (documented in SKILL.md), monitor network activity, and revoke the token after testing. If the publisher cannot be identified or their domain looks unfamiliar, treat the skill as untrusted.
功能分析
Type: OpenClaw Skill
Name: video-open-ai
Version: 1.0.0
The video-open-ai skill is a functional wrapper for a third-party video processing service (nemovideo.ai). It manages authentication via environment variables or anonymous token generation, handles file uploads, and coordinates cloud-based video rendering. All identified behaviors, including network requests to mega-api-prod.nemovideo.ai and access to ~/.config/nemovideo/, are directly aligned with the stated purpose of AI video editing and lack indicators of malicious intent or data exfiltration.
能力评估
Purpose & Capability
Name/description describe cloud video editing and the skill only requires a single API token (NEMO_TOKEN) and makes calls to a nemovideo.ai API — this is coherent. However, the package registry metadata said no required config paths while the SKILL.md frontmatter lists a config path (~/.config/nemovideo/). Also the skill has no listed homepage or accountable publisher, which lowers trust in provenance.
Instruction Scope
SKILL.md instructions are specific to creating sessions, uploading media, streaming SSE for edits, polling render status, and returning download URLs — all within the claimed video-editing scope. It does not instruct the agent to read unrelated files or other environment variables. It does instruct the agent to 'save session_id' but does not specify where; that is expected for session management but worth noting for persistence.
Install Mechanism
There is no install spec and no code files; this is instruction-only so nothing is written to disk by an installer. That's the lowest-risk install mechanism.
Credentials
Only a single credential (NEMO_TOKEN) is required and is appropriate for calling the external API. The skill also documents a way to obtain a short-lived anonymous token via the API. The frontmatter's configPaths entry suggests possible access to a local config directory, but SKILL.md does not instruct reading it — this mismatch should be clarified.
Persistence & Privilege
always is false (no forced inclusion). The skill expects to manage session tokens (session_id) and the NEMO_TOKEN; the SKILL.md says to 'save session_id' and to use/skip NEMO_TOKEN if env var present. Persisting tokens or session IDs in agent storage is expected for functionality, but you should confirm where/if the agent persists them and how to revoke them.
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-open-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-open-ai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: Quickly generate and edit AI-powered videos in the cloud, tailored for content creators.
- Upload video clips (MP4, MOV, AVI, WebM up to 500MB) and give natural-language instructions for editing.
- Automatically trims, adds captions, adjusts aspect ratio, overlays text, and exports 1080p MP4 files—no manual timeline work.
- Handles session, token, and cloud processing setup behind the scenes; credits/free usage supported for quick start.
- All video edits, exports, credits checks, and state/status requests routed by simple commands or file uploads.
- Designed for rapid, instruction-based workflow with easy status feedback and error handling.
元数据
常见问题
Video Open Ai 是什么？
Get AI-edited videos ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "trim th... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 75 次。
如何安装 Video Open Ai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-open-ai」即可一键安装，无需额外配置。
Video Open Ai 是免费的吗？
是的，Video Open Ai 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Open Ai 支持哪些平台？
Video Open Ai 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 Open Ai？
由 whitejohnk-26（@whitejohnk-26）开发并维护，当前版本 v1.0.0。
推荐 Skills