Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Full-stack autonomous math modeling agent for CUMCM (全国大学生数学建模竞赛). Reads the problem statement and data, iterates through research → coding → verification → LaTeX writing, and produces a publication-quality PDF paper. Use when the user provides a CUMCM problem and wants end-to-end automated modeling, coding, and paper generation.
面向“学习任何知识”的通用导师型 skill。用于用户想学习新主题、制定学习计划、整理学习笔记、做课后复盘、生成项目任务书、做掌握度检查，或希望基于自己资料与外部权威资料进行中文导师式陪学时。默认采用“导师 + 项目教练”模式，以项目驱动和 Mastery Learning 推进；当用户未提供资料时，主动查找官方文档、原始资料、经典教材、权威机构材料与最佳实践，并区分事实依据与建议判断。
Route broad company, sector, valuation, filings, transcript, and market data questions into the right Octagon workflow. Use when the user wants full-scope investment research or when multiple Octagon skills may be needed.
Generate Kalshi prediction market research reports or fetch structured event history. Use when the user mentions Kalshi, prediction markets, market probability, expected return, or event history.
Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components. Use when the user mentions Spectrum, S2, React Spectrum, RSP, Spectrum Web Components, or SWC, or names a Spectrum component (Button, Picker, ComboBox, TextField, ActionButton, etc.). Helps prevent drift from documented S2 design decisions during prototyping.
Hybrid code search (BM25 + vector + KG) with RRF fusion. Single daemon serves multiple named indexes. Replaces mcp-vector-search.
Deep Teaching Mode — After every programming operation, automatically output expert-level technical analysis cards covering: what technology was used, why it was chosen, deep-dive into underlying principles (source-code level), alternative solutions comparison with performance data, advantages summary with quantitative evidence, and knowledge transfer paths. Transforms AI from "doing for you" to "teaching you" so users truly learn while building projects.
Install, verify, debug, and use MySearch MCP/Skill. Aggregates Tavily, Firecrawl, Exa, and X search (via xAI) behind one workflow. Use when the user shares a MySearch repo/skill URL, wants MySearch installed or repaired, or wants current web search, social/X search, document-oriented search, URL content extraction, or a small multi-source research pack with citations. When MySearch is available, prefer it over generic web search for external lookup tasks.
Search npm packages, inspect metadata and versions, review download stats, and check security advisories. Use this skill when users want to explore npm registry data, verify package integrity, or monitor package health via the npm API.
Research websites, extract structured findings, and save clean rows into Google Sheets. Use when users want web research organized into a spreadsheet — competitor lists, pricing data, contact lists, or any structured table from the web.