← 返回 Skills 市场
112
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-news
功能描述
Get broadcast-ready segments ready to post, without touching a single slider. Upload your raw news footage (MP4, MOV, MXF, AVI, up to 500MB), say something l...
安全使用建议
This skill appears to be a legitimate cloud video editor that uploads your footage to a third‑party API and needs a NEMO_TOKEN. Before installing or using it: (1) Confirm you are comfortable uploading potentially sensitive video to https://mega-api-prod.nemovideo.ai and ask for the provider's privacy/retention policy; (2) Prefer using an ephemeral / limited-scope token rather than a long-lived high-privilege secret; (3) Ask the publisher to explain the apparent metadata inconsistency (the SKILL.md frontmatter lists ~/.config/nemovideo/ while registry metadata lists no config paths) and to clarify why the skill needs to detect install paths; (4) Request clarification of the truncated/incoherent instruction fragment (the 'click [button]' → 'Execute vi…' line) — incomplete or incorrect runtime instructions could cause unexpected behavior; (5) If you require transparency, ask the publisher to remove the 'keep technical details out of the chat' requirement or to provide an explicit, user-visible upload/authorization confirmation step; (6) Avoid using this skill for highly sensitive footage until the above are resolved. If the publisher cannot clarify these items, treat the skill as higher risk and do not install or grant your real credentials.
功能分析
Type: OpenClaw Skill
Name: video-news
Version: 1.0.0
The 'video-news' skill is a legitimate integration for an AI-driven video editing service hosted at nemovideo.ai. It provides structured instructions for the agent to manage sessions, upload media, and trigger cloud-based video rendering via a series of API endpoints. While it requests access to a specific environment variable (NEMO_TOKEN) and a configuration directory (~/.config/nemovideo/), these are standard requirements for its stated functionality, and no evidence of malicious intent, data exfiltration, or unauthorized execution was found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name/description (video editing) aligns with required credential NEMO_TOKEN and the documented API endpoints for uploads and renders. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) that is not present in the registry metadata, and the instructions ask the agent to detect an install path (to set X-Skill-Platform). These filesystem checks are not obviously required for editing and introduce a small mismatch between claimed requirements and runtime behavior.
Instruction Scope
The instructions tell the agent to read NEMO_TOKEN (expected) or obtain an anonymous token via an external POST (reasonable). They further instruct streaming SSE handling, polling, and uploading user media to https://mega-api-prod.nemovideo.ai — all expected for a cloud editor. Concerns: (1) SKILL.md says to 'keep the technical details out of the chat' which hides transmission/authorization steps from users; (2) the doc instructs the agent to detect install paths and include derived headers (requires filesystem awareness); (3) there's an odd truncated mapping ('click [button]' → 'Execute vi…') which looks incoherent and may indicate incomplete or incorrect instructions. The skill will upload user media to a third party — that is central to its function but requires explicit user consent and clear privacy/retention terms.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest filesystem/write risk. Nothing is downloaded or written by an installer according to the manifest.
Credentials
Only one credential is required (NEMO_TOKEN), which is appropriate for a cloud API. The SKILL.md also includes a mechanism to mint anonymous tokens if none are present. The frontmatter's configPaths entry (~/.config/nemovideo/) is declared in the skill file but not in registry metadata — this inconsistency suggests the skill may attempt to read a local config path even though the registry reported none.
Persistence & Privilege
always:false and no install operations. The skill does not request permanent presence or modifications to other skills. Note: the skill can be invoked autonomously by the agent (platform default) — combine that with the opaque 'keep technical details out of the chat' instruction and automated uploads to an external service, and you should consider whether you want the agent to run this skill without explicit per-use confirmation.
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-news - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-news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 News — Edit News Clips for Broadcast.
- Instantly edit raw news footage into 1080p MP4 broadcast-ready segments with AI-powered cloud rendering.
- Upload video files (MP4, MOV, MXF, AVI up to 500MB) and use natural language to trim, caption, and edit.
- Connects automatically to the backend; obtains a free token if needed for easy first-time setup.
- Supports essential workflows: quick edits, iterative changes, and batch processing.
- Handles video uploads, editing commands, export, credits checking, and timeline status.
- Fast cloud GPU processing returns downloadable news clips, with clear feedback throughout.
元数据
常见问题
Video News 是什么？
Get broadcast-ready segments ready to post, without touching a single slider. Upload your raw news footage (MP4, MOV, MXF, AVI, up to 500MB), say something l... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 112 次。
如何安装 Video News？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-news」即可一键安装，无需额外配置。
Video News 是免费的吗？
是的，Video News 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video News 支持哪些平台？
Video News 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 News？
由 tk8544-b（@tk8544-b）开发并维护，当前版本 v1.0.0。
推荐 Skills