← 返回 Skills 市场
Social Video
作者
francemichaell-15
· GitHub ↗
· v1.0.0
· MIT-0
97
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install social-video
功能描述
Get shareable social clips ready to post, without touching a single slider. Upload your raw video clips (MP4, MOV, WebM, AVI, up to 500MB), say something lik...
安全使用建议
This skill sends your uploaded media and session tokens to https://mega-api-prod.nemovideo.ai for cloud rendering — that's expected for a hosted video editor. Before installing: 1) Confirm you trust the nemovideo.ai service (no homepage is provided here). 2) Understand that video/audio files and the NEMO_TOKEN (anonymous or provided) will be transmitted to that external API; avoid uploading sensitive content. 3) Note the skill can auto-create anonymous tokens and refresh them, so the agent will make outbound authentication requests without additional prompts. 4) If you need stricter privacy, require a vetted service or review network endpoints and retention/privacy policy from the vendor. Finally, the SKILL.md frontmatter mentions a local config path (~/.config/nemovideo/) even though registry metadata omitted it — ask the publisher which local files (if any) the skill will access or store.
功能分析
Type: OpenClaw Skill
Name: social-video
Version: 1.0.0
The skill is a functional wrapper for the Nemo Video AI editing service, facilitating video uploads and processing via the mega-api-prod.nemovideo.ai backend. It includes logic for automated anonymous authentication, session management, and credit tracking. While it performs minor environment fingerprinting to identify the host platform (e.g., Cursor or OpenClaw) for telemetry and instructs the agent to suppress token display in the UI, these actions are consistent with its stated purpose and standard UX/security practices for API integrations.
能力评估
Purpose & Capability
The name/description (AI social video editing) match the SKILL.md actions (upload, SSE chat, export, poll render). Requesting a single NEMO_TOKEN for remote API access is appropriate. Minor inconsistency: the registry metadata listed no required config paths, while the SKILL.md frontmatter's openclaw metadata includes a configPaths entry (~/.config/nemovideo/). This is a small mismatch in metadata but does not contradict the declared purpose.
Instruction Scope
The instructions confine themselves to authenticating (anonymous-token if needed), creating a session, uploading files, driving edit actions via SSE/API, polling exports, and returning download URLs. There is no instruction to read unrelated local files or secrets. The skill does ask the agent to detect install path to set an attribution header (X-Skill-Platform), which requires checking known path locations — reasonable for attribution but worth noting.
Install Mechanism
No install spec or code files are present (instruction-only). No downloads, package installs, or disk writes are specified by the skill itself.
Credentials
Only one credential is declared (NEMO_TOKEN) and that is the primary credential used for the described API workflow. The SKILL.md also mentions a config path in its frontmatter (see purpose_capability) which could imply reading local config; the runtime instructions themselves only check for NEMO_TOKEN in the environment and create an anonymous token if missing. Reauth and token storage behavior is expected for this functionality but means the agent will perform network calls to obtain/refresh tokens.
Persistence & Privilege
always:false and model invocation not disabled (normal). The skill does request storing a session_id and using tokens for subsequent requests (normal for a session-based API). It does not request persistent system-wide privileges or modify other skills.
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 social-video - 安装完成后，直接呼叫该 Skill 的名称或使用
/social-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 social-video skill for rapid social clip creation.
- Instantly create and export platform-ready video clips for TikTok, Instagram, and more, using natural language prompts.
- Upload raw video files (MP4, MOV, WebM, AVI, up to 500MB), request edits (e.g., "cut this into a 30-second Instagram Reel with captions and background music"), and download a 1080p MP4 in seconds.
- Automated backend handles authentication, session management, job queueing, and file exports; includes free credits for new users.
- Built-in error handling for authentication, credits, file support, and rate limiting.
- Supports multipart uploads, export in multiple formats, tracking session state, and cloud GPU rendering.
- Optimized for creators wanting fast, no-slider social video editing and export.
元数据
常见问题
Social Video 是什么？
Get shareable social clips ready to post, without touching a single slider. Upload your raw video clips (MP4, MOV, WebM, AVI, up to 500MB), say something lik... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 97 次。
如何安装 Social Video？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install social-video」即可一键安装，无需额外配置。
Social Video 是免费的吗？
是的，Social Video 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Social Video 支持哪些平台？
Social 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 Social Video？
由 francemichaell-15（@francemichaell-15）开发并维护，当前版本 v1.0.0。
推荐 Skills