← 返回 Skills 市场
80
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install nm-pensive-math-review
功能描述
Verify math-heavy code for algorithm correctness, numerical stability, and standards alignment
安全使用建议
This skill appears to do what it says: guide a human/agent through math-heavy code review and run tests/notebooks to gather evidence. Before installing or running it: 1) Inspect the two Night Market config entries referenced (night-market.pensive:shared and night-market.imbue:proof-of-work) to ensure they don't contain secrets or tokens you don't want exposed. 2) Do not execute the skill against untrusted repositories without sandboxing — pytest and executing Jupyter notebooks can run arbitrary code, access the network, or exfiltrate data. 3) Ensure the execution environment has the needed numerical tools (SymPy, NumPy, SciPy, Jupyter) pinned and isolated (e.g., container/VM). 4) If you plan to allow autonomous invocation by an agent, restrict its runtime privileges (network, filesystem scope) or require manual approval for executing tests/notebooks. If you can confirm the config entries are safe and you will run the skill in an isolated environment, the skill is coherent with its stated purpose.
功能分析
Type: OpenClaw Skill
Name: nm-pensive-math-review
Version: 1.0.0
The skill bundle is a comprehensive toolset for reviewing mathematical and scientific code, focusing on numerical stability, derivation verification, and requirements mapping. It utilizes standard development tools such as git, pytest, and Jupyter nbconvert to perform its stated functions, and the instructions in SKILL.md and its modules (e.g., numerical-stability.md, testing-strategies.md) are strictly aligned with legitimate code auditing practices without any evidence of malicious intent or data exfiltration.
能力标签
能力评估
Purpose & Capability
Name/description match the contents: the skill is an instruction-only math/algorithm review that walks through context-sync, requirements mapping, symbolic derivation checks, numerical-stability checks, and test execution. No unrelated credentials or unrelated binaries are requested. The two declared config paths (night-market.pensive:shared, night-market.imbue:proof-of-work) plausibly belong to the Night Market ecosystem; their presence is not obviously inconsistent with a plugin that integrates with that system.
Instruction Scope
Instructions explicitly tell the agent to run repository commands (git status/diff), execute tests (pytest tests/math/ --benchmark) and execute notebooks (jupyter nbconvert --execute derivation.ipynb). That is coherent for a code-review / verification skill, but executing tests or notebooks in an unchecked environment can run arbitrary code from the repository (including network access or side effects). The SKILL.md does not include any sandboxing or explicit restrictions, nor does it list required numerical packages (SymPy, NumPy, Jupyter) even though examples reference them.
Install Mechanism
No install spec or code files are present (instruction-only), so nothing is downloaded or written by the skill itself. This is the lowest-risk install model and matches the declared manifest.
Credentials
The skill declares no required environment variables and does not request broad cloud credentials. It does require two Night Market config paths (night-market.pensive:shared, night-market.imbue:proof-of-work). The manifest does not show what these configs contain; they could be harmless settings or could hold tokens/credentials. Because the skill executes repo tests/notebooks, it could indirectly access secrets present in the repo or environment when run — consider limiting its access or inspecting those config entries before installing.
Persistence & Privilege
always:false and user-invocable:true (default) — no forced inclusion. The skill does not declare any behavior that modifies other skills or system-wide agent settings. Autonomous invocation is permitted by platform default but is not combined with other high-risk privileges in this skill.
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 nm-pensive-math-review - 安装完成后，直接呼叫该 Skill 的名称或使用
/nm-pensive-math-review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 the math-review skill.
- Provides a workflow for verifying math-heavy code for algorithm correctness, numerical stability, and standards alignment.
- Includes detailed checklists, output templates, and required workflow steps (context sync, requirements mapping, derivation verification, stability assessment, proof of work).
- Offers progressive loading for scalable analysis depth.
- Documents risk classification, essential checklist, and troubleshooting guidance.
- Integration instructions and references to authoritative standards provided.
元数据
常见问题
Nm Pensive Math Review 是什么？
Verify math-heavy code for algorithm correctness, numerical stability, and standards alignment. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 80 次。
如何安装 Nm Pensive Math Review？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nm-pensive-math-review」即可一键安装，无需额外配置。
Nm Pensive Math Review 是免费的吗？
是的，Nm Pensive Math Review 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Nm Pensive Math Review 支持哪些平台？
Nm Pensive Math Review 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 Nm Pensive Math Review？
由 athola（@athola）开发并维护，当前版本 v1.0.0。
推荐 Skills