← 返回 Skills 市场
254
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install tl-image
功能描述
Generate and edit images using TensorsLab's AI models. Supports text-to-image, image-to-image generation, plus advanced editing: avatar generation, watermark...
安全使用建议
This skill appears to be a normal API client for TensorsLab, but two things to check before installing: (1) registry metadata does not list the required TENSORSLAB_API_KEY even though SKILL.md and the script require it — confirm the skill will only use that one API key and that the registry entry is corrected; (2) the publisher/source/homepage are missing, so verify the author and the API domain (api.tensorslab.com) are legitimate. Be mindful that features like watermark removal and face replacement can have privacy or legal implications — don't upload sensitive or copyrighted images unless you have rights to them. If you proceed, scope the API key (use a limited key), run the script in an isolated environment, and review network traffic (or the included code) to confirm no unexpected endpoints are contacted.
功能分析
Type: OpenClaw Skill
Name: tl-image
Version: 0.1.0
The skill bundle provides a legitimate interface for TensorsLab's image generation and editing API. The Python script (scripts/tensorslab_image.py) handles API requests, task polling, and image downloads to a local directory as described in the documentation. The instructions in SKILL.md and scenarios.md are well-aligned with the stated purpose of enhancing user prompts for high-quality image output and do not contain any malicious instructions or data exfiltration logic.
能力评估
Purpose & Capability
The skill's stated purpose (TensorsLab image generation) matches what the code and README do (call https://api.tensorslab.com, upload local images, download outputs). However the registry metadata lists no required environment variables while SKILL.md and the script explicitly require TENSORSLAB_API_KEY — this inconsistency is unexplained and should be resolved before trusting the skill.
Instruction Scope
SKILL.md and the script stay within the image-generation/editing scope: they read local image files, upload them to the TensorsLab API, poll task status, and save outputs locally. That scope includes higher-risk operations (watermark removal, object erasure, face replacement) which are legitimate features but have privacy/legal implications; the instructions do not ask for unrelated system data or other credentials.
Install Mechanism
There is no install spec (instruction-only), and the bundled Python script only requires the common 'requests' package (SKILL.md tells the user to pip install requests). No remote installers, URL downloads, or opaque binaries are present.
Credentials
The code and SKILL.md require a single credential (TENSORSLAB_API_KEY) — appropriate and proportionate for a remote API client — but the registry metadata fails to declare this required env var. The missing declaration is a mismatch that reduces transparency. No other unrelated secrets are requested.
Persistence & Privilege
Skill does not request always: true and does not modify other skills or system-wide settings. It writes output files to a local directory and uses a single API key; this is typical for a CLI client and within expected privilege boundaries.
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 tl-image - 安装完成后，直接呼叫该 Skill 的名称或使用
/tl-image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
v0.1.0
- Initial release of TensorsLab Image Skill.
- Generate and edit images with TensorsLab models (text-to-image, image-to-image).
- Supports advanced tasks: avatar creation, watermark removal, object erasure, face replacement, and more.
- Automatic prompt enhancement for high-quality results, with progress updates and easy local file saving.
- Flexible model selection and resolution options.
- Requires TENSORSLAB_API_KEY environment variable for use.
元数据
常见问题
Tensorslab Image 是什么？
Generate and edit images using TensorsLab's AI models. Supports text-to-image, image-to-image generation, plus advanced editing: avatar generation, watermark... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 254 次。
如何安装 Tensorslab Image？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tl-image」即可一键安装，无需额外配置。
Tensorslab Image 是免费的吗？
是的，Tensorslab Image 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Tensorslab Image 支持哪些平台？
Tensorslab Image 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 Tensorslab Image？
由 bob（@bob5-tensorslab）开发并维护，当前版本 v0.1.0。
推荐 Skills