Data & AI
Machine Learning, Data Science, and AI development skills
22656 skills in this category
Subcategories
ai-annotation-workflow
Эксперт по data annotation. Используй для ML labeling, annotation workflows и quality control.
training-archive-gating
Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpoint recommendations for overfitting.
sql
Expert SQL Server / T-SQL developer for stored procedures, functions, query optimization, and database programming. Use for .sql files, stored procedures, functions, views, or when user mentions SQL Server, T-SQL, or database queries.
drawio
Guidelines and best practices for creating draw.io diagrams with proper formatting, font handling, and layout rules. Use when creating or editing .drawio files, generating architecture diagrams, or working with draw.io XML format. Ensures high-quality PNG output with correct Japanese text rendering and professional appearance.
fastapi-api-patterns
REST API design and implementation patterns for FastAPI endpoints including CRUD operations, pagination, filtering, error handling, and request/response models. Use when building FastAPI endpoints, creating REST APIs, implementing CRUD operations, adding pagination, designing API routes, handling API errors, or when user mentions FastAPI patterns, REST API design, endpoint structure, API best practices, or HTTP endpoints.
current-location-weather
Get current weather conditions for a location. Use this skill when users ask about weather, temperature, current conditions, forecasts, or any weather-related queries like "What's the weather?", "Is it raining?", "How hot is it outside?", "What's the temperature?", or "Should I bring an umbrella?". Supports automatic location detection via IP or specific location queries.
frontend-components
Design and build reusable, composable UI components with clear interfaces and single responsibilities. When creating or modifying React components, Vue components, or any UI component files. When working on files that define reusable UI elements (*.tsx, *.jsx, *.vue, components/*). When structuring component props, state management, or component composition. When building component libraries, designing component APIs, or refactoring UI code into smaller components. When implementing hooks, context, or passing data between components.
protect
Annotate passing code with protection levels (@protected/@immutable/@maintainable). Use when stabilizing working features to prevent regressions.
asyncpg-detection
This skill should be used when the user asks to "detect asyncpg usage", "find asyncpg patterns", "scan for asyncpg imports", or "identify asyncpg database code in FastAPI projects". It automatically scans Python files to identify asyncpg imports, connection patterns, and query execution methods that need conversion to SQLAlchemy.
unityaiforge
AI-powered Unity development toolkit with Model Context Protocol integration
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. Use when Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
design-fundamentals
Core design principles for creating distinctive, beautiful UIs with technical excellence.Combines creative direction with practical foundation for memorable, accessible interfaces.Use when building UI without specific design specs (Figma, screenshots, design files):- Creating landing pages, home pages, marketing pages from scratch- Building web apps, dashboards, admin panels without design- Choosing design system: typography, colors, spacing, visual hierarchy- Need to propose complete design (fonts, colors, layout, spacing)- Building distinctive UIs that avoid generic AI aestheticsKeywords: landing page, design system, typography, colors, spacing, visual hierarchyTwo-part approach:1. Creative Direction: Choose aesthetic tone (minimal, bold, elegant, playful)2. Technical Foundation: Spacing scales, typography specs, WCAG contrast, hierarchyGoal: Create UIs that are BOTH beautiful (distinctive, memorable) AND correct (accessible, consistent, professional).
claude-code-capabilities
Comprehensive guide to Claude Code's extensibility features including subagents, skills, plugins, commands, hooks, MCP servers, permissions, and automation. Use when the user asks about Claude Code features, capabilities, customization, extensibility, how to extend Claude Code, or automation workflows.
architecture-paradigm-modular-monolith
Maintain a single deployable artifact while enforcing strong internal boundaries between modules.
global-validation
Implement comprehensive input validation on server-side with complementary client-side validation for user experience, using allowlists, type checking, and sanitization to prevent injection attacks. Use this skill when validating user inputs, form data, API requests, file uploads, query parameters, or any external data entering the application. Apply this skill when implementing server-side validation as the primary security layer, adding client-side validation for immediate user feedback, validating data types and formats, checking ranges and required fields, sanitizing inputs to prevent SQL injection and XSS attacks, using allowlists over blocklists, providing field-specific error messages, or enforcing business rules at appropriate application layers. This skill ensures validation happens at all entry points consistently, security is never dependent on client-side checks alone, users receive helpful immediate feedback, and data integrity is maintained through multiple layers of validation.
claude-codex-guardrail-loop
Use after planning or implementing non-trivial tasks - runs Codex MCP background verification/review for quality gates (plan validation + implementation review)
validation-scripts
Data validation and pipeline testing utilities for ML training projects. Validates datasets, model checkpoints, training pipelines, and dependencies. Use when validating training data, checking model outputs, testing ML pipelines, verifying dependencies, debugging training failures, or ensuring data quality before training.
mermaid-diagram-patterns
Create Mermaid diagrams for technical documentation including ERDs, sequence diagrams, flowcharts, and architecture diagrams. Use when: (1) designing database schemas (ERD), (2) documenting API interactions (sequence), (3) illustrating process flows (flowchart), (4) visualizing system architecture.
create-coverage-report
Generate comprehensive coverage report with requirement traceability mapping. Shows coverage per REQ-*, gaps, trends, and recommendations. Use for status dashboards, quality reviews, or compliance audits.
dara-dataset-expert
Warehouse-Prozess-Analyse mit 207 Labels, 47 Prozessen, 8 Szenarien, 10 Triggern. Vollständige Expertise für DaRa Datensatz - Chunking, Semantik, BPMN-Logik. 100% faktenbasiert ohne Halluzinationen.