← 返回 Skills 市场
Pixverse Ai
作者
vcarolxhberger
· GitHub ↗
· v1.0.0
· MIT-0
110
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install pixverse-ai
功能描述
Tired of spending hours trying to produce cinematic video content without a film crew or budget? PixVerse AI changes that entirely. This skill connects you d...
安全使用建议
This skill appears to do what it says: it sends prompts and any uploaded images to mega-api-prod.nemovideo.ai to generate videos and needs one token (NEMO_TOKEN). Before installing, consider: 1) The skill will use any NEMO_TOKEN in your environment — that token may be charged or tied to your account, so remove or rotate it if you do not want your account used. 2) Uploaded files and prompts are sent to an external service (privacy implications); do not upload sensitive files. 3) The registry metadata and SKILL.md disagree about a config path (~/.config/nemovideo/) — ask the maintainer to clarify what, if anything, will be written or read from disk. 4) There is no homepage or publisher info in the registry entry; if you need accountability or a privacy policy, request the service's documentation before use. If you trust nemovideo.ai and are comfortable with the above, the skill's requirements look proportionate to its purpose.
功能分析
Type: OpenClaw Skill
Name: pixverse-ai
Version: 1.0.0
The skill is a functional integration for the PixVerse AI video generation service, facilitating text-to-video and image-to-video workflows. It provides detailed instructions for the agent to interact with the 'nemovideo.ai' backend, including session management, SSE stream handling, and asset export. The requested permissions (NEMO_TOKEN and ~/.config/nemovideo/) are consistent with the tool's purpose, and there is no evidence of data exfiltration, unauthorized execution, or malicious prompt injection.
能力评估
Purpose & Capability
Name/description (AI video generation) lines up with the runtime instructions and the single required credential (NEMO_TOKEN). The API endpoints and operations described (session creation, SSE, upload, export, credits) are consistent with a cloud video-generation service. One minor inconsistency: the registry metadata provided earlier listed no required config paths, but the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/). This is likely a metadata mismatch but does not change the skill's stated purpose.
Instruction Scope
Instructions are explicit about network calls to mega-api-prod.nemovideo.ai, using Authorization: Bearer <NEMO_TOKEN>, creating sessions, uploading files/URLs, and using SSE streams. The skill tells the agent to read its YAML frontmatter and to detect install path (~/.clawhub/, ~/.cursor/skills/) to set an attribution header — reading the install path is reasonable for the requested X-Skill-Platform header but does require filesystem metadata access. The skill will upload user-supplied files and prompts to the remote service (expected for this capability). The guidance to 'keep technical details out of the chat' is a UX instruction and does not imply extra data collection, but it does reduce transparency of those network actions in chat.
Install Mechanism
No install/spec files and no code shipped — instruction-only. This is low-risk because nothing is written to disk by an installer. There are no remote downloads or package installs described.
Credentials
Only one environment variable is required (NEMO_TOKEN), which matches the need to authenticate to the external video service. That is proportionate for the stated purpose. Caveat: if a user already has NEMO_TOKEN in their environment the skill will use it (acting under that account); if no token exists it will request an anonymous starter token from the service. Also note the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata earlier indicated none — this is a metadata mismatch worth clarifying.
Persistence & Privilege
always is false and the skill does not request elevated or permanent platform privileges. It does not ask to modify other skills or system-wide configs. Autonomous invocation (model can call the skill) is the platform default and is not in itself a concern here.
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 pixverse-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/pixverse-ai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
PixVerse AI Skill v1.0.0 — Turn text and images into cinematic videos in seconds.
- Instant AI video generation from text prompts or image uploads — no video editing required.
- Seamless connection to the PixVerse backend: handles authentication, session management, and API routing automatically.
- Supports credits checking, export/download workflow, and session state tracking.
- Detailed error handling for tokens, credits, file support, and rate limits, with clear user guidance.
- Includes prompt suggestions and best practices to help users get high-quality results faster.
元数据
常见问题
Pixverse Ai 是什么？
Tired of spending hours trying to produce cinematic video content without a film crew or budget? PixVerse AI changes that entirely. This skill connects you d... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 110 次。
如何安装 Pixverse Ai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pixverse-ai」即可一键安装，无需额外配置。
Pixverse Ai 是免费的吗？
是的，Pixverse Ai 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Pixverse Ai 支持哪些平台？
Pixverse Ai 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 Pixverse Ai？
由 vcarolxhberger（@vcarolxhberger）开发并维护，当前版本 v1.0.0。
推荐 Skills