← 返回 Skills 市场
图可丽视觉api
作者
cutout-pro
· GitHub ↗
· v1.0.0
· MIT-0
243
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install tukeli-visual-api
功能描述
调用图可丽（Tukeli）视觉处理 API，实现通用抠图、人脸变清晰、AI背景更换三项能力。支持文件上传、图片URL两种输入方式，返回二进制流或Base64编码结果。AI背景更换为异步接口，需先提交任务再查询结果。
安全使用建议
This skill appears to do what it says (calls Tukeli's image APIs) but the package metadata failed to declare the required API key. Before installing: (1) confirm you obtained a TUKELI_API_KEY from the real tukeli.net site and are comfortable providing it; (2) run the code in an isolated environment if you are unsure about the API domain (picupapi.tukeli.net) and verify the domain is legitimate; (3) ensure your .env file is not checked into source control; (4) inspect scripts/tukeli.py and config.py yourself (they are small and readable) to verify no extra exfiltration; and (5) ask the publisher/registry to update the skill metadata to explicitly require TUKELI_API_KEY so the platform can surface the secret requirement during installation.
功能分析
Type: OpenClaw Skill
Name: tukeli-visual-api
Version: 1.0.0
This skill bundle provides a legitimate interface for the Tukeli (图可丽) image processing API, supporting tasks like background removal, face enhancement, and AI-generated backgrounds. The implementation in `scripts/tukeli.py` and `scripts/config.py` follows standard practices, using the `requests` library to interact with the official API endpoint (picupapi.tukeli.net) and managing API keys through environment variables or a `.env` file. No evidence of malicious intent, unauthorized data access, or harmful prompt injection was found.
能力评估
Purpose & Capability
The skill's name/description (image matting, face enhancement, AI background) match the implementation: network calls to picupapi.tukeli.net and local file handling. However, the registry metadata lists no required environment variables or primary credential, while both SKILL.md and the code clearly require TUKELI_API_KEY. The omission of this required secret from metadata is inconsistent and reduces visibility of the credential requirement.
Instruction Scope
Runtime instructions and code are focused on image processing: they read an API key from environment or a .env file, validate local image files, POST/GET to the documented API domain, and save outputs + metadata to data/outputs. There are no instructions to read unrelated system files or to send data to third-party endpoints beyond the documented API domain.
Install Mechanism
No install script is provided; the only runtime dependency is the well-known 'requests' Python package. The skill is instruction/code-only and does not download or execute code from external arbitrary URLs during install.
Credentials
The code requires a single API credential (TUKELI_API_KEY) and may reference an optional TUKELI_MAX_IMAGES_PER_DAY env var in docs, but the skill metadata declares no required env vars or primary credential. Requiring an API key is reasonable for a remote API integration, but failing to declare it in registry metadata is misleading and reduces the platform's ability to prompt users for secrets securely.
Persistence & Privilege
The skill does not request elevated platform privileges and does not set always:true. It writes outputs and metadata into its own data/outputs directory and does not modify other skills or global agent settings.
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 tukeli-visual-api - 安装完成后，直接呼叫该 Skill 的名称或使用
/tukeli-visual-api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
Initial release of tukeli-visual-api — a toolset for image processing via Tukeli's visual API.
- Provides automatic background removal, face enhancement, and AI-based background generation.
- Supports both file upload and image URL as inputs; returns results as binary or Base64.
- AI background change is asynchronous: submit a task, then query the result.
- Flexible usage scenarios: quickly remove backgrounds, improve face images, or apply AI-generated backgrounds.
- Detailed command-line interface and usage examples included.
- Limits, supported formats, billing, and integration guides documented.
元数据
常见问题
图可丽视觉api 是什么？
调用图可丽（Tukeli）视觉处理 API，实现通用抠图、人脸变清晰、AI背景更换三项能力。支持文件上传、图片URL两种输入方式，返回二进制流或Base64编码结果。AI背景更换为异步接口，需先提交任务再查询结果。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 243 次。
如何安装 图可丽视觉api？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tukeli-visual-api」即可一键安装，无需额外配置。
图可丽视觉api 是免费的吗？
是的，图可丽视觉api 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
图可丽视觉api 支持哪些平台？
图可丽视觉api 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 图可丽视觉api？
由 cutout-pro（@cutout-pro）开发并维护，当前版本 v1.0.0。
推荐 Skills