← 返回 Skills 市场
peand-rover

Ugc Video

作者 peandrover adam · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
96
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ugc-video
功能描述
content creators and marketers create raw phone footage into authentic UGC clips using this skill. Accepts MP4, MOV, WebM, AVI up to 500MB, renders on cloud...
安全使用建议
This skill will upload whatever video you provide to an external service (mega-api-prod.nemovideo.ai) and use a bearer token (NEMO_TOKEN) to operate; if NEMO_TOKEN is missing it will attempt to create an anonymous token via the API. Before installing or using it: (1) Do not upload private or proprietary footage until you confirm the service operator, privacy/data retention policy, and whether uploaded files are stored or shared. (2) Ask the publisher why the registry requires NEMO_TOKEN but the skill auto-creates an anonymous token, and whether the anonymous token is persisted on disk (and where). (3) Confirm what the quoted 'credits' and expiry mean and whether operations could incur charges. (4) If you need to test, do so with non-sensitive content only. (5) Prefer skills with a verifiable homepage/source and documented privacy/security posture; consider an offline tool if you cannot accept sending media to a third party.
功能分析
Type: OpenClaw Skill Name: ugc-video Version: 1.0.0 The skill is a well-documented integration for a UGC video creation service (nemovideo.ai). It provides clear instructions for the agent to handle authentication via anonymous tokens, manage video processing sessions, and perform file uploads and cloud rendering. While it includes platform fingerprinting for attribution and requires network and file access, these behaviors are directly aligned with its stated purpose and lack any indicators of malicious intent, data exfiltration, or unauthorized execution. The instructions even include security-conscious directives such as hiding raw tokens and API outputs from the user.
能力评估
Purpose & Capability
The declared purpose (cloud UGC video rendering) matches the API calls and upload/upload+render workflow described in SKILL.md. However the registry requires NEMO_TOKEN while the runtime instructions explicitly support obtaining an anonymous token via the nemovideo.ai API if NEMO_TOKEN is missing — this mismatch between declared requirements and actual behavior is incoherent and should be clarified.
Instruction Scope
SKILL.md instructs the agent to upload user-provided video files to https://mega-api-prod.nemovideo.ai, use SSE endpoints, poll render status, and handle multipart file uploads. It also instructs auto-creation of tokens and to 'auto-detect' platform from install path (which implies reading agent filesystem). These are within the skill's editing/rendering purpose, but they involve network exfiltration of user-supplied media and reading local install/config locations — both are sensitive operations and not fully justified in the manifest.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so it does not write executables to disk. That lowers install-time risk.
Credentials
Registry lists a single required env var (NEMO_TOKEN), which is appropriate for a cloud API. But SKILL.md both reads/will use NEMO_TOKEN if present and will POST to an anonymous-token endpoint to obtain a token if it isn't present — an inconsistency. The SKILL.md frontmatter also references a config path (~/.config/nemovideo/) that the registry did not list. These mismatches raise questions about what credentials/config the skill will read or write and where any auto-created tokens are stored.
Persistence & Privilege
The skill is not always-enabled and does not request system-wide privileges. It does ask to keep session_id in memory for operations, which is normal for a session-based API. There is no install-time persistence declared.
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 ugc-video
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /ugc-video 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
Initial release of UGC Video — Create Authentic UGC Creator Clips: - Accepts raw phone video (MP4, MOV, WebM, AVI) up to 500MB and turns it into polished UGC clips on cloud GPUs. - Supports 1080p MP4 output in 1–2 minutes; works best with vertical 9:16 footage for TikTok and Reels. - Automatic setup: manages tokens, session, and cloud back-end connection with clear user feedback. - User-driven workflow: upload footage and give editing instructions (trim, overlay text, etc.), then receive ready-to-download video links. - Exposes simple chat commands for export, upload, status, and credits; robust error-handling and file support details provided.
元数据
Slug ugc-video
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

Ugc Video 是什么?

content creators and marketers create raw phone footage into authentic UGC clips using this skill. Accepts MP4, MOV, WebM, AVI up to 500MB, renders on cloud... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 96 次。

如何安装 Ugc Video?

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

Ugc Video 是免费的吗?

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

Ugc Video 支持哪些平台?

Ugc 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 Ugc Video?

由 peandrover adam(@peand-rover)开发并维护,当前版本 v1.0.0。

💬 留言讨论