← 返回 Skills 市场
134
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install pathology-roi-selector
功能描述
Use pathology roi selector for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries.
安全使用建议
This skill appears coherent and not malicious, but take these precautions before using it:
- Review the included scripts/main.py yourself (it currently returns mocked ROIs) and do not rely on it for clinical decisions.
- Run the script in a sandboxed environment or test workspace first to avoid accidental overwrites (it writes the output path as provided without validation).
- Do not run this on sensitive or PHI-containing images until you verify behavior and add proper data handling controls.
- If you need real WSI processing, expect to add proper image-processing libraries and pin dependencies; the package currently lists none and is a draft.
- Consider adding input path validation, output directory restrictions, and error sanitization before automating execution.
- If you want higher assurance, request a version that implements the actual image-analysis logic and includes dependency/version manifests and unit tests.
能力评估
Purpose & Capability
Name, description, SKILL.md and the included script all align: this is a local pathology ROI selector script. The skill does not request unrelated credentials or binaries. Note: the packaged Python implementation is a simple placeholder that returns mocked ROI results rather than performing real WSI image analysis; this is a capability mismatch (not a security one).
Instruction Scope
SKILL.md confines actions to running the packaged script and validating inputs before execution. It does not instruct reading unrelated files or env vars. However, the documentation claims input validation and path traversal protections while the provided script performs no input/path validation or sandboxing; that gap may lead to accidental file overwrite or processing of unintended files.
Install Mechanism
No install spec is present and there are no downloads. The skill is instruction-only with a local Python script included — minimal install risk.
Credentials
The skill requests no environment variables or credentials and the code does not access external secrets or network. The requested environment is proportional to the stated local processing purpose.
Persistence & Privilege
The skill is not always-loaded and does not modify agent/system configuration. It runs only when invoked; no elevated persistence or cross-skill configuration changes are requested.
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 pathology-roi-selector - 安装完成后，直接呼叫该 Skill 的名称或使用
/pathology-roi-selector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 pathology-roi-selector.
- Provides a structured workflow for selecting regions of interest (ROIs) in whole slide images (WSI) for pathology applications.
- Includes clear output boundaries, explicit assumptions, and documented fallback/error handling paths.
- Supports key pathology data analysis use cases: AI model training, research sampling, and education.
- Main script entry point: scripts/main.py, with audit-ready commands and example usage.
- Covers basic parameters (wsi_file, tissue_type, magnification) and outputs (ROI coordinates, quality metrics, export-ready crops).
- Emphasizes input validation, reproducible outputs, risk checks, and a security checklist.
元数据
常见问题
Pathology ROI Selector 是什么？
Use pathology roi selector for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 134 次。
如何安装 Pathology ROI Selector？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pathology-roi-selector」即可一键安装，无需额外配置。
Pathology ROI Selector 是免费的吗？
是的，Pathology ROI Selector 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Pathology ROI Selector 支持哪些平台？
Pathology ROI Selector 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 Pathology ROI Selector？
由 AIpoch（@aipoch-ai）开发并维护，当前版本 v1.0.0。
推荐 Skills