← 返回 Skills 市场
Tomoviee Text to Video
作者
wondershare-boop
· GitHub ↗
· v1.0.6
· MIT-0
500
总下载
0
收藏
3
当前安装
7
版本数
在 OpenClaw 中安装
/install tomoviee-text-to-video
功能描述
Generate 5-second videos from text prompts using Tomoviee Text-to-Video API (tm_text2video_b) via Wondershare OpenAPI gateway (https://openapi.wondershare.cc...
安全使用建议
This package appears to be a straightforward client for Tomoviee via the Wondershare OpenAPI gateway. Before installing or providing credentials: 1) Only provide an app_key and app_secret you trust (from your Tomoviee/Wondershare account). 2) Be cautious with the optional 'callback' URL — only use callback endpoints you control and trust, since the service will POST result data and any passthrough params there. 3) Note the registry metadata omits that credentials are required; treat the SKILL.md as authoritative and do not store secrets in shared or public places. 4) If you allow an autonomous agent to invoke this skill, remember the agent could make API calls using any credentials you supply — restrict those credentials' permissions or use test keys if possible.
功能分析
Type: OpenClaw Skill
Name: tomoviee-text-to-video
Version: 1.0.6
The skill bundle provides a legitimate integration for the Tomoviee AI Text-to-Video service via the Wondershare OpenAPI gateway (openapi.wondershare.cc). The Python client and authentication scripts (scripts/tomoviee_text2video_client.py and scripts/generate_auth_token.py) implement standard API interaction patterns and Basic Authentication without any signs of malicious intent, data exfiltration, or obfuscation.
能力评估
Purpose & Capability
Name/description, SKILL.md, and the included Python client all consistently implement calls to the Tomoviee API via the Wondershare gateway (openapi.wondershare.cc) for 5s text-to-video generation. The code requires an app_key and app_secret (passed to the client), which is appropriate and proportionate for this purpose.
Instruction Scope
SKILL.md instructs the agent/user to pip install requests and run the included scripts. Runtime actions are limited to sending API requests to openapi.wondershare.cc and polling the unified result endpoint. One noteworthy instruction: the API supports an optional 'callback' URL — if a user supplies a callback, the service may POST generation results (and any 'params' passthrough) to that URL, so users should avoid using untrusted callback endpoints to prevent unintended data exfiltration.
Install Mechanism
No install spec that downloads arbitrary code; only a small requirements.txt (requests). The skill is instruction+client-source-only and does not fetch executables from unknown hosts or use extract/download installers.
Credentials
The client requires an app_key and app_secret to authenticate, which is appropriate for an API client. However, the skill registry metadata declares 'Required env vars: none' and 'Primary credential: none' while the SKILL.md shows explicit authentication steps (passing app_key/app_secret). This metadata omission is a mismatch users should be aware of — credentials are needed at runtime even if not declared in the metadata.
Persistence & Privilege
The skill does not request persistent 'always' inclusion and does not modify other skills or system-wide settings. It does not persist credentials on its own or require elevated system privileges.
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 tomoviee-text-to-video - 安装完成后，直接呼叫该 Skill 的名称或使用
/tomoviee-text-to-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
v1.0.6
- Updated skill name to "tomoviee-text-to-video" for consistency.
- Clarified and updated API host details: all requests now routed via https://openapi.wondershare.cc.
- Expanded provider and endpoint information to describe usage and routing.
- Improved and streamlined Quick Start and API usage instructions.
- Added requirements.txt to document dependencies.
- Clarified resource references and cleaned up wording for better clarity.
v1.0.5
- Added _meta.json for enhanced metadata management.
- No changes to core functionality or documentation.
v1.0.4
- Added a network routing notice clarifying different domains for global (.ai) and mainland China (.cn) access.
- Included separate links for developer portals, API documentation, and credential registration for both international and China-based users.
- No changes to the API, usage, or core functionality.
v1.0.3
- Updated external resource links from "tomoviee.cn" to "tomoviee.ai" in the documentation.
- No other content or feature changes.
v1.0.2
- Added Python API client and authentication script for text-to-video generation.
- Introduced reference guides: camera movements, prompt engineering, and API usage.
- Simplified and updated documentation with English quick start guide, parameter table, and workflow.
- Now supports selection of 46 camera movement types.
- Removed legacy script and migrated workflow to the new client structure.
- Updated skill description, focusing on clarity for all users.
v1.0.1
No file changes detected in this version.
- No updates or modifications were made in version 1.0.1.
- The skill remains functionally unchanged.
v1.0.0
Initial release of tomoviee-text-to-video skill.
- Generate AI videos from text prompts using the Tomoviee (万兴天幕) model.
- Supports customizable duration, resolution (up to 1080p), and aspect ratios.
- Includes access/authentication guide, environment variables, and error handling instructions.
- Provides a prompt writing guide and user parameter confirmation flow.
- Video generation script automates token retrieval, task creation, polling, and download.
- Outputs direct video URL for user access or download.
元数据
常见问题
Tomoviee Text to Video 是什么？
Generate 5-second videos from text prompts using Tomoviee Text-to-Video API (tm_text2video_b) via Wondershare OpenAPI gateway (https://openapi.wondershare.cc... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 500 次。
如何安装 Tomoviee Text to Video？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tomoviee-text-to-video」即可一键安装，无需额外配置。
Tomoviee Text to Video 是免费的吗？
是的，Tomoviee Text to Video 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Tomoviee Text to Video 支持哪些平台？
Tomoviee Text to 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 Tomoviee Text to Video？
由 wondershare-boop（@wondershare-boop）开发并维护，当前版本 v1.0.6。
推荐 Skills