菜单
Use when the user explicitly needs MATLAB or .m scripts for local scientific computing, simulation, signal processing, image processing, statistics, or experiment reproduction. Prefer command-line MATLAB batch execution and do not imply GUI control.
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。
基于 SOC 职业分类
Use this skill for academic reports, literature reviews, experiment reports, user-selected reference styles, innovation-point mining, or when the user wants a topic turned into a paper-backed evidence bundle instead of generic web research.
Use this skill whenever the user wants reproducible CS/AI experiments, model evaluation, regression/classification/clustering analyses, bioinformatics workflows, QC, differential expression, single-cell starter analysis, or manuscript-ready experiment bundles with scientific figures. Also use it when the user asks for heatmaps, ROC/PR curves, volcano plots, UMAP/PCA projections, or wants experimental results packaged for a paper or report.
Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity, or when a SOUL.md is missing. Also trigger for updates to an existing SOUL.md or AI personality.
Interact with MedrixFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to MedrixFlow for research/analysis, start a MedrixFlow conversation thread, check MedrixFlow status or health, list available models/skills/agents in MedrixFlow, manage MedrixFlow memory, upload files to MedrixFlow threads, or delegate complex research tasks to MedrixFlow. Also use when the user mentions medrix_flow or wants to run a deep research task that MedrixFlow can handle.
Use when the user asks for latest datasets, benchmark suites, leaderboards, baseline or SOTA comparisons, dataset selection for experiments, or evidence that a paper needs complete experimental validation. This skill routes to the dataset_benchmark_discovery tool and keeps access/license limits explicit.
Use this skill for general web research that needs current online information, multiple source angles, and synthesis, when no more specific research skill applies. Prefer academic-deep-research for scholarly literature, github-deep-research for GitHub/open-source repositories, and consulting-analysis for consulting-grade market or industry reports.
| name | matlab-execution |
| description | Use when the user explicitly needs MATLAB or .m scripts for local scientific computing, simulation, signal processing, image processing, statistics, or experiment reproduction. Prefer command-line MATLAB batch execution and do not imply GUI control. |
Use this skill only when MATLAB itself is needed. Prefer Python/R tooling for
normal data analysis unless the user requires MATLAB code, .mat files, or a
MATLAB-specific toolbox.
matlab -batch using the matlab_execution tool..m script with deterministic inputs and output paths..mat, .csv, and logs under the output directory provided by the tool.matlab_execution(script_content=..., script_name=...).