論文

Advanced scientific computing for portfolio optimization, statistical testing, and numerical methods. Use when minimizing portfolio variance, fitting distributions to returns data, performing correlation analysis, running hypothesis tests, or solving constrained optimization problems. Provides optimization algorithms (BFGS, SLSQP) and statistical distributions essential for risk modeling.

Guide for systemd init system and service management. Use when creating, managing, or debugging system services, timers, and targets. Covers unit files, service lifecycle, dependencies, and journalctl logging.

Visualize 3D meshes, point clouds, and volumetric data using PyVista. Use for interactive plotting, mesh inspection, and creating publication-quality figures. Built on VTK with simplified Pythonic interface.

Generate LaTeX documents and compile them to PDF for publication-quality reports. Use when creating academic papers, scientific reports, mathematical documents, or professionally typeset PDF reports with equations and references.

Create static visualizations including bar charts, line plots, pie charts, and more. Use when generating charts for reports, creating data visualizations, producing publication-quality figures, or embedding plots in PDF/HTML reports.

Matplotlib library for creating financial visualizations. Use for plotting time series, creating multi-panel figures, stacked bar charts, and generating publication-quality charts.

Chapter-by-chapter outline generator for stories planned with the Crucible Structure. Use when a user has completed Crucible planning documents (thesis, strand maps, forge points, etc.) and wants to create detailed chapter outlines. Triggers on requests like "outline my book," "create chapter outline," "outline Book 1," "turn my Crucible plan into chapters," or when user has Crucible planning docs and wants to start writing. Works for single books or multi-book series.

Expert on Shelby Protocol architecture, erasure coding, placement groups, read/write procedures, Clay Codes, chunking, storage providers, RPC servers, and decentralized storage system design on Aptos blockchain. Triggers on keywords Shelby Protocol, erasure coding, Clay Codes, placement groups, Shelby architecture, storage provider, blob storage, chunking, Shelby whitepaper.

Search academic paper repositories (arXiv, Semantic Scholar) for scholarly articles in physics, mathematics, computer science, quantitative biology, AI/ML, and related fields

Structured development workflows using /brainstorm, /write-plan, and /execute-plan patterns. Transform ad-hoc conversations into systematic project execution with hypothesis-driven planning, incremental implementation, and progress tracking.

Expert research analyst specializing in comprehensive information gathering, synthesis, and insight generation. Masters research methodologies, data analysis, and report creation with focus on delivering actionable intelligence that drives informed decision-making.

Systematic research methodology for building comprehensive, current knowledge on any topic. Requires web_search tool. Use when questions require thorough investigation, recent developments post-cutoff, synthesis across multiple sources, or when Claude's knowledge may be outdated or incomplete. Triggered by "Research", "Investigate", "What's current on", "Latest info on", complex queries needing validation, or technical topics with recent changes.

Analyze AI/ML technical content (papers, articles, blog posts) and extract actionable insights filtered through enterprise AI engineering lens. Use when user provides URL/document for AI/ML content analysis, asks to "review this paper", or mentions technical content in domains like RAG, embeddings, fine-tuning, prompt engineering, LLM deployment.

Retrieves scientific papers from PubMed and creates plain-language research summaries. Use when users ask about medical research, scientific studies, clinical trials, disease treatments, or want to understand recent scientific literature on any biomedical topic.

Synthesize findings from multiple research sources into coherent insights. Use when combining data from different sub-agents or research threads.

Conducts in-depth analysis of a specific source or topic, producing comprehensive summaries for research synthesis. Use when you need detailed analysis and documentation of individual sources as part of a larger research effort.

Create exceptional, publication-quality Mermaid diagrams for ERDs, flowcharts, sequence diagrams, and system visualizations. Use this skill when the user needs to visualize data models, processes, or architecture. Generates clear, refined diagrams that communicate complex systems with precision.

Use Hypothesis for property-based testing to automatically generate comprehensive test cases, find edge cases, and write more robust tests with minimal example shrinking. Includes Polars parametric testing integration.

Systematically debug issues with reproduction steps, error analysis, hypothesis testing, and root cause fixes. Use when investigating bugs, analyzing production incidents, or troubleshooting unexpected behavior.

Implement web page content extraction capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to scrape web pages, extract article content, retrieve page metadata, or build applications that process web content. Supports automatic content extraction with title, HTML, and publication time retrieval.