菜单
Use when solving nontrivial mathematical problems or investigating conjectures that may benefit from Jacobian's local library of typed operations for exact computation, finite search, structural analysis, formal reasoning, probability, or optimization.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/morluto/jacobian --skill jacobian-math命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use Jacobian's MCP operations for nontrivial mathematical computation, finite search, structural analysis, formal checking, probability, or optimization.
Decompose a bounded corpus of mathematical proofs, formalizations, scripts, and certificates into recurring solution techniques and the smallest reusable Jacobian postconditions. Use for repository- or corpus-level “what can Jacobian learn?” audits; do not use for one operation contract or one agent trajectory.
Review completed or paused mathematical agent transcripts, visible reasoning, code, searches, tool calls, corrections, and final claims to extract evidence-backed lessons for Jacobian operations, discovery, contracts, skills, evaluations, and documentation. Use for mathematical workflow retrospectives and "what should we learn from this trajectory?" requests. Do not use to continue solving the problem or infer hidden chain-of-thought.
基于 SOC 职业分类
正在显示 SKILL.md
| name | jacobian-math |
| description | Use when solving nontrivial mathematical problems or investigating conjectures that may benefit from Jacobian's local library of typed operations for exact computation, finite search, structural analysis, formal reasoning, probability, or optimization. |
Jacobian is a local library of typed mathematical operations for computation and structural analysis.
Use math.find as the library-navigation tool: search for a desired outcome,
browse an unfamiliar domain, or inspect an operation's schema and examples.
Use math.run to execute a selected operation and obtain its typed result.
Feed results into later reasoning, further Jacobian operations, or Python
scratch work as useful.
The operations are composable. Choose the representation, decomposition, order of operations, and stopping point that fit the problem. Reach for the library proactively when exact computation, finite search, or structural analysis may help.
