← 返回 Skills 市场
276
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install tensorslab-video
功能描述
Generate videos using TensorsLab's AI video generation models. Supports text-to-video and image-to-video generation with automatic prompt enhancement, progre...
安全使用建议
Before installing or running this skill: 1) Know that the script requires a TENSORSLAB_API_KEY (it will fail without it) even though the registry metadata omits that — treat the registry omission as a quality/mismatch issue. 2) Confirm the legitimate upstream domains (the README/code reference api.tensorslab.com, tensorslab.tensorslab.com, and a typo-like tensorai.tensorslab.com); verify which is official and that the API key is obtained from an official site. 3) The script uploads any local images you pass to the remote API and downloads generated video files — do not supply sensitive images you don't want sent to an external service. 4) Restrict the API key scope if possible, and avoid using long-lived account-wide secrets. 5) If you need higher assurance, ask the publisher for a canonical homepage/repository and compare the packaged script to the upstream source; the metadata/source being 'unknown' is the main practical risk here.
功能分析
Type: OpenClaw Skill
Name: tensorslab-video
Version: 1.0.3
The skill bundle is a legitimate API client for the TensorsLab video generation service. The Python script (tensorslab_video.py) correctly handles API authentication via environment variables, task submission, status polling, and secure file downloading to a local directory, while the SKILL.md provides clear, non-malicious instructions for the AI agent.
能力评估
Purpose & Capability
Name, SKILL.md, and the included Python script all consistently implement text-to-video and image-to-video functionality for a TensorsLab API — that part is coherent. However, the registry metadata claims no required environment variables or primary credential while both SKILL.md and the script require a TENSORSLAB_API_KEY; the skill's listed Homepage/Source are unknown. These mismatches between metadata and runtime requirements are inconsistent and reduce trust.
Instruction Scope
The runtime instructions and script stay within the stated purpose: they check for TENSORSLAB_API_KEY, call a remote API, poll task status, and download resulting videos to a local output directory. The script will read local image files when performing image-to-video (expected). There are no instructions to read unrelated system files or to exfiltrate arbitrary local data beyond the images explicitly supplied by the user.
Install Mechanism
No install spec is provided (instruction-only skill with an included script). This is the lowest-risk install model — nothing is downloaded automatically by the platform. The script uses the pip 'requests' dependency, which is documented in SKILL.md.
Credentials
The script and SKILL.md require a TENSORSLAB_API_KEY (Bearer token) for API access, which is appropriate for the task. However, the registry metadata declares no required env vars and no primary credential, creating a discrepancy. The sole credential requested (API key) is proportional to the stated purpose, but the missing declaration in metadata is a red flag that the package metadata is out-of-sync with runtime behavior.
Persistence & Privilege
The skill is not forced always-on (always:false), is user-invocable, and does not attempt to modify other skills or system-wide settings. It doesn't request persistent privileges beyond using a single API key for calls to the service.
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 tensorslab-video - 安装完成后，直接呼叫该 Skill 的名称或使用
/tensorslab-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
v1.0.3
tensorslab-video 1.0.3
- Updated API key check instructions to avoid displaying the full key value.
- Added a dependency note for installing the `requests` library before running scripts.
- No functional changes; documentation improved for setup clarity and usage guidance.
v1.0.2
TensorLab Skills are AI task definitions for Claude Code, focusing on multimedia generation and processing using TensorsLab's AI models. It provides comprehensive capabilities including text-to-video and image-to-video generation.
v1.0.1
TensorLab Skills are AI task definitions for Claude Code, focusing on multimedia generation and processing using TensorsLab's AI models. It provides comprehensive capabilities including text-to-video and image-to-video generation.
v1.0.0
Initial release of TensorsLab Video Generation skill.
- Generate videos from text or images using TensorsLab’s AI models.
- Automatic prompt enhancement for cinematic results, various aspect ratios, and resolutions.
- Progress tracking with regular heartbeat updates during video generation.
- Local file saving with customizable output directory.
- Error messages and tips provided in both English and Chinese.
- Requires TENSORSLAB_API_KEY environment variable for use.
元数据
常见问题
Video Generation 是什么？
Generate videos using TensorsLab's AI video generation models. Supports text-to-video and image-to-video generation with automatic prompt enhancement, progre... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 276 次。
如何安装 Video Generation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tensorslab-video」即可一键安装，无需额外配置。
Video Generation 是免费的吗？
是的，Video Generation 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Generation 支持哪些平台？
Video Generation 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 Generation？
由 bob（@bob5-tensorslab）开发并维护，当前版本 v1.0.3。
推荐 Skills