數據與 AI
機器學習、數據科學和人工智慧開發技能
22656 skills in this category
database-designer
Design database schemas for PostgreSQL, Neon, Convex, or Supabase. Use when users need to create tables, define relationships, plan migrations, optimize indexes, or implement data models. Covers normalization, denormalization strategies, and platform-specific features.
packx
Bundle code context for AI. ALWAYS use --limit 49k unless user explicitly requests otherwise. Use for creating shareable code bundles and preparing context for LLMs.
sqlalchemy-coding-agent
Turn the model into a SQLAlchemy-focused Python coding agent for designing models, writing queries, debugging database issues, and integrating SQLAlchemy with Alembic and FastAPI in new or existing Python projects.
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
review-parallel
複数のAIレビュアーを並列実行し、結果を統合処理して単一のレポートを生成
testing-builder
Automatically generates comprehensive test suites (unit, integration, E2E) based on code and past testing patterns. Use when user says "write tests", "test this", "add coverage", or after fixing bugs to create regression tests. Eliminates testing friction for ADHD users.
generate-spec
Generates app_spec.txt specification files from codebases. Use when you need to create specification documents, analyze code structure, document project architecture, or generate comprehensive project overviews in XML format.
technical-indicators
计算股票技术指标(MA、MACD、RSI、BOLL等)。适用于技术分析、量化回测、趋势判断等场景。支持单个指标计算或批量计算所有指标,返回包含指标值的DataFrame。
google-workspace
Manage Google Workspace with Docs, Sheets, Slides, Drive, Gmail, Calendar, and Contacts operations. Full document/spreadsheet/presentation editing, file management, email, and scheduling.
beanie-odm
This skill should be used when the user asks to "create MongoDB model", "define Beanie document", "write MongoDB query", "create aggregation pipeline", "run database migration", "index MongoDB collection", or mentions Beanie, Motor, MongoDB documents, or async database operations. Provides MongoDB/Beanie ODM patterns for FastAPI.
context-handover
Create concise handover summary for seamless continuation in new chat session
clickhouse-python
Write Python code to interact with ClickHouse using clickhouse-connect. Use when creating ETL scripts, data pipelines, analytics applications, or any Python code that needs to query or insert data into ClickHouse.
obsidian-tasks
Obsidian Vault의 TaskManager에서 작업을 읽고 관리하는 스킬. Board.md(Kanban), Table.md(Dataview), Notes/* 를 지원하며 workspace 프로젝트와 자동 연동합니다. '작업 목록', '할일 조회', 'task 읽기', 'obsidian 작업' 요청 시 활성화됩니다.
wallet-send-bsv
Send BSV transactions using @bsv/sdk. Build, sign, and broadcast transactions to the BSV blockchain.
numpy-fft
Discrete Fourier Transform routines for spectral analysis, signal filtering, and frequency-domain operations. Triggers: fft, fourier transform, spectral analysis, rfft, fftshift, ifft.
always-works-testing
Default testing standard for all implementation work - ensures code actually works through mandatory execution validation before confirming to user. Applies automatically whenever writing, modifying, debugging, or implementing any code (scripts, APIs, UI, configs, data operations, logic changes). This is the baseline expectation, not an optional extra - every implementation must be verified through actual execution, not assumed correct.
repo-reorganization
Python package reorganization with pyproject.toml inside package directory
new-db-schema
Create new database tables with Drizzle ORM schemas and Valibot validation.使用 Drizzle ORM 创建新的数据库表模式和 Valibot 验证。Use when:- Adding new database tables- Creating entity schemas- User mentions "new table", "database schema", "add entity", "新增表", "数据库模式"
delontheme-integration
Implement ng-alain theming system with layout configuration, responsive design, menu management, and settings drawer for ng-lin project
pytorch-cuda
PyTorch CUDA environment and performance guidance, with emphasis on CUDA 13 toolkit/driver requirements, PyTorch wheel compatibility, and runtime checks. Use when configuring PyTorch on NVIDIA GPUs, debugging CUDA setup, or migrating to CUDA 13; triggers: pytorch cuda, cuda 13, driver version, nvcc, torch.version.cuda, tf32, streams.