← 返回 Skills 市场
Video Script Yijia
作者
vcarolxhberger
· GitHub ↗
· v1.0.0
· MIT-0
80
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-script-yijia
功能描述
Get ready-to-use scripts ready to post, without touching a single slider. Upload your text or brief (MP4, MOV, TXT, DOCX, up to 200MB), say something like "w...
安全使用建议
This skill is coherent with its stated purpose but will send any uploaded files and session tokens to mega-api-prod.nemovideo.ai. Before installing: (1) Confirm whether the skill will read/write ~/.config/nemovideo/ (manifest mismatch). (2) Only upload non-sensitive media/content you consent to send to the external service. (3) If you already have a NEMO_TOKEN in your environment, recognize the skill will use it — ensure that token's scope is appropriate. (4) If you prefer not to expose a permanent token, let the skill use the anonymous-token flow and revoke or delete any stored session tokens after use. (5) Verify the API domain and consider network-level controls or review of outgoing requests if you need to limit exposure.
功能分析
Type: OpenClaw Skill
Name: video-script-yijia
Version: 1.0.0
The skill is a functional wrapper for the 'nemovideo.ai' service, designed to generate video scripts and export MP4 files. It includes detailed instructions for the agent to manage authentication via anonymous tokens, handle session states, and interact with the service's API (mega-api-prod.nemovideo.ai). The requested permissions (NEMO_TOKEN and ~/.config/nemovideo/) and network activities are strictly aligned with the stated purpose of the tool, with no evidence of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
The skill's name/description (video script + render) aligns with its runtime actions: it requires a NEMO_TOKEN, creates sessions, uploads files, and requests renders from mega-api-prod.nemovideo.ai. One inconsistency: the registry metadata in the skill manifest reported no required config paths, but the SKILL.md frontmatter lists a config path (~/.config/nemovideo/). This mismatch should be clarified (does the skill read/write that config directory?).
Instruction Scope
SKILL.md gives concrete API calls for auth, session creation, SSE messaging, uploads, and export polling — all within the stated purpose. It instructs the agent to: use NEMO_TOKEN if present, generate an anonymous token if not, save session_id and (implicitly) tokens, read the SKILL.md frontmatter, and detect install path to set an attribution header. These instructions legitimately touch local files you choose to upload and may read the skill file or install path; they do not instruct arbitrary system-wide data collection. Still, the agent will transmit uploaded files and session tokens to the external nemovideo API, so uploaded content and tokens are exfiltrated to that service by design.
Install Mechanism
No install spec or code files are present (instruction-only). That minimizes on-disk install risk — nothing is downloaded or executed beyond the agent following the written instructions at runtime.
Credentials
The only required environment credential is NEMO_TOKEN (declared as primaryEnv), which is appropriate for a third-party rendering API. The SKILL.md also references a local config path (~/.config/nemovideo/) which was not listed in the registry metadata; this is a minor inconsistency and should be confirmed because the skill may read/write session tokens or cached credentials there.
Persistence & Privilege
The skill is not force-included (always:false) and uses normal autonomous invocation settings. It instructs saving session state/tokens (expected for session continuity) but does not request elevated platform privileges or modification of other skills. Verify where session tokens are stored (e.g., the referenced config path) if you want to control persistence.
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-script-yijia - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-script-yijia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 Script Yijia skill.
- Instantly generate ready-to-use video scripts from your brief, with AI-powered structure and export.
- Supports text and file uploads (MP4, MOV, TXT, DOCX, up to 200MB) for script generation and editing.
- Full 1080p MP4 export, with download links delivered in under a minute.
- Automated session management and credits handling (with temporary free token support).
- Clear, structured API-driven workflow for content creators and marketers needing fast turnaround.
- Includes robust error handling and timeline summarization for a smooth editing experience.
元数据
常见问题
Video Script Yijia 是什么？
Get ready-to-use scripts ready to post, without touching a single slider. Upload your text or brief (MP4, MOV, TXT, DOCX, up to 200MB), say something like "w... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 80 次。
如何安装 Video Script Yijia？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-script-yijia」即可一键安装，无需额外配置。
Video Script Yijia 是免费的吗？
是的，Video Script Yijia 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Script Yijia 支持哪些平台？
Video Script Yijia 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 Script Yijia？
由 vcarolxhberger（@vcarolxhberger）开发并维护，当前版本 v1.0.0。
推荐 Skills