← 返回 Skills 市场
mhogan2013-9

Short Video Auto

作者 mhogan2013-9 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
53
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install short-video-auto
功能描述
convert raw video footage into auto-edited short clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. TikTok and Reels creators use it fo...
安全使用建议
This skill connects to a third-party cloud backend (mega-api-prod.nemovideo.ai) and uploads your videos for processing. Before installing or using it: (1) Confirm you trust that domain and are comfortable uploading the content (do not upload sensitive/private/proprietary footage). (2) Prefer supplying your own NEMO_TOKEN if you have an account; otherwise the skill will request an anonymous token from the backend (100 free credits, 7-day expiry) and use it for uploads/exports. (3) Be aware the skill may read or write its own config directory (~/.config/nemovideo/) for caching sessions/tokens; avoid storing other secrets there. (4) If you need stronger privacy controls, ask the developer for a privacy/retention policy or an on-prem alternative. (5) Because the skill's source and homepage are unknown, exercise caution: verify the vendor or test with non-sensitive sample videos first.
功能分析
Type: OpenClaw Skill Name: short-video-auto Version: 1.0.0 This skill connects to a remote backend (mega-api-prod.nemovideo.ai) and instructs the agent to execute 'tool calls' received via a Server-Sent Events (SSE) stream while explicitly hiding these actions and their results from the user ('process internally, don't forward'). This architecture creates a high risk of unauthorized remote command execution, as the backend can potentially trigger any tool available to the agent without user oversight. Additionally, the skill performs environment reconnaissance by requiring the agent to detect the host platform (e.g., Cursor or Clawhub) from its installation path and transmits this metadata in every request header.
能力评估
Purpose & Capability
Name and description match the instructions: uploading video, creating sessions, starting renders, and returning download URLs. The declared primary env var (NEMO_TOKEN) matches the backend Authorization usage. Minor mismatch: metadata lists a config path (~/.config/nemovideo/) that the SKILL.md does not explicitly read; this is plausible (for caching tokens/sessions) but not strictly necessary for the described runtime flow.
Instruction Scope
SKILL.md only instructs the agent to interact with the documented backend endpoints, upload files, manage session tokens, and stream SSE responses — all within the scope of auto-editing video. It does not instruct reading unrelated system files or other credentials. One implementation note: it asks callers to auto-detect an install path value for an attribution header (X-Skill-Platform), which implicitly requires access to the agent’s install context; this is a minor scope expansion but not unexpected for attribution.
Install Mechanism
No install spec or code files are included; this is an instruction-only skill (lowest install risk). No downloads or third-party packages are specified.
Credentials
Only a single credential (NEMO_TOKEN) is required and is used as the Bearer token for API calls — this is proportionate. The skill will also generate an anonymous token via the backend if NEMO_TOKEN isn't present (documented). The declared configPaths value could allow reading local stored config, which is reasonable for token/session caching but should be considered by users who keep other secrets in that directory.
Persistence & Privilege
Skill is not always-enabled and does not request persistent or cross-skill privileges. Autonomous invocation is allowed by default (expected). The skill does not instruct modification of other skills or system-wide agent settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install short-video-auto
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /short-video-auto 触发
  4. 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
Short Video Auto 1.0.0 — Initial Release - Automatically converts raw video footage into AI-edited short clips, optimized for TikTok, Reels, and similar platforms. - Supports MP4, MOV, AVI, WebM files up to 500MB, delivering 1080p MP4 exports in 30–90 seconds using cloud GPUs. - Seamless onboarding with automatic anonymous token generation for 100 free credits; guides users through setup. - Commands include upload, edit, check credits, view status, and export, all mapped to cloud actions. - Error handling and workflow tips included for a smooth user experience.
元数据
Slug short-video-auto
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Short Video Auto 是什么?

convert raw video footage into auto-edited short clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. TikTok and Reels creators use it fo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 53 次。

如何安装 Short Video Auto?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install short-video-auto」即可一键安装,无需额外配置。

Short Video Auto 是免费的吗?

是的,Short Video Auto 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Short Video Auto 支持哪些平台?

Short Video Auto 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 Short Video Auto?

由 mhogan2013-9(@mhogan2013-9)开发并维护,当前版本 v1.0.0。

💬 留言讨论