← 返回 Skills 市场
481
总下载
0
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install scipy
功能描述
Solve optimization, statistics, signal processing, and linear algebra problems with SciPy recipes and ready-to-run code.
安全使用建议
This skill appears coherent and low-risk: it generates SciPy-based Python code and does not ask for secrets or install anything. Before using: (1) confirm you have python3 and SciPy/NumPy installed (or install them in a virtualenv: pip install numpy scipy), (2) review any generated code before running it (check for unintended file or network access and for heavy computation that could strain your machine), and (3) if you prefer, run examples in an isolated environment (virtualenv or container). The skill source is listed as "unknown" in the registry metadata — that's common for third-party skills, but if provenance matters to you, consider verifying the homepage/owner or preferring skills from known publishers.
功能分析
Type: OpenClaw Skill
Name: scipy
Version: 1.0.0
The OpenClaw SciPy skill bundle is benign. All code examples provided in `SKILL.md` are standard computational Python using SciPy and NumPy, without any risky functions like `os.system`, network calls, or file I/O. The `SKILL.md` explicitly states that the skill does not send data externally, create persistent files, or access network resources, which is consistent with the analyzed content. Instructions to the AI agent in `SKILL.md`, `setup.md`, and `memory-template.md` are focused on providing helpful code and understanding user needs, with no evidence of prompt injection or malicious intent.
能力评估
Purpose & Capability
Name and description match the instructions: SKILL.md directs the agent to produce ready-to-run SciPy code (optimize, stats, signal, linalg, etc.). The only required binary is python3, which is appropriate for a Python/SciPy skill. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
Instructions keep scope to providing runnable Python/SciPy examples and validation. The skill expects code to run in the user's Python environment and instructs the agent to always include complete code. It does not tell the agent to read unrelated system files, exfiltrate data, or call external endpoints. One practical gap: the skill does not provide installation steps for SciPy/NumPy (it assumes they exist in the user's environment), so users may need to install packages themselves before running examples.
Install Mechanism
No install spec and no code files — instruction-only — which is the lowest-risk pattern. Nothing will be downloaded or written by the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportional to its stated purpose of producing SciPy code snippets.
Persistence & Privilege
always:false (default). The skill is stateless by design and offers an optional user-controlled memory template; it does not request persistent or elevated privileges or modify other skills' config.
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 scipy - 安装完成后，直接呼叫该 Skill 的名称或使用
/scipy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
元数据
常见问题
SciPy 是什么？
Solve optimization, statistics, signal processing, and linear algebra problems with SciPy recipes and ready-to-run code. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 481 次。
如何安装 SciPy？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install scipy」即可一键安装，无需额外配置。
SciPy 是免费的吗？
是的，SciPy 完全免费（开源免费），可自由下载、安装和使用。
SciPy 支持哪些平台？
SciPy 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（linux, darwin, win32）。
谁开发了 SciPy？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.0。
推荐 Skills