Data & AI
Machine Learning, Data Science, and AI development skills
22656 skills in this category
Subcategories
tavily-search
Real-time web search and research with AI-powered result synthesis
handoff-to-human
Transfer conversation to human agent. Use when customer explicitly requests human support, issue is too complex, customer is frustrated, or situation requires human judgment.
senior-computer-vision
World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.
learning-needs-analysis
Conduct comprehensive learning needs analysis including stakeholder interviews, performance gap identification, job/task analysis, and competency mapping. Use when starting any learning project to identify what training is actually needed. Activates on "needs analysis", "training needs", "performance gaps", or "what should we teach".
moai-lang-elixir
Elixir 1.17+ development specialist covering Phoenix 1.7, LiveView, Ecto, and OTP patterns. Use when developing real-time applications, distributed systems, or Phoenix projects.
unsloth-cpt
Strategies for continued pretraining and domain adaptation in Unsloth (triggers: continued pretraining, CPT, domain adaptation, lm_head, embed_tokens, rsLoRA, embedding_learning_rate).
deepagent
Expert guidance for DeepAgents framework - simplified agent creation with tool integration for LangChain/LangGraph workflows.
tdd-red-phase
Guide experienced developers through RED phase of TDD cycle - writing failing tests
context-engineering
Comprehensive context engineering and management system based on the framework C = A(câ, câ, câ, câ, câ , câ). Use this skill when users work with context files, ask about context engineering, need to create/update/analyze contexts, validate context quality, detect discrepancies between contexts, or manage their Context Engineering system. Triggers include: "create a context", "analyze context", "check for inconsistencies", "validate context quality", "update context", "context engineering", "manage contexts", "c1-c6 components", or when working with .claude/contexts/ directories.
responsive-ui
Build truly responsive SPA, MPA, or landing pages that adapt gracefully from foldable phones (280px) to ultra-wide desktops (2560px+). Use when the user asks to create responsive websites, landing pages, mobile-first designs, or any web interface requiring broad device support. Generates semantic HTML5, mobile-first CSS with fluid typography, CSS Grid/Flexbox layouts, accessible navigation with hamburger menus, and responsive images with srcset/lazy loading.
nextjs
Guide for implementing Next.js - a React framework for production with server-side rendering, static generation, and modern web features. Use when building Next.js applications, implementing App Router, working with server components, data fetching, routing, or optimizing performance.
data-quality
Data quality testing with dbt tests, Great Expectations, and monitoring.
brainstorm
Collaborative brainstorming partner for multi-session ideation projects. Use when the user wants to brainstorm, ideate, explore ideas, or think through problemsâwhether for SaaS products, software tools, book ideas, newsletter content, business strategies, or any creative/analytical challenge. Handles session continuity across days/weeks via versioned markdown documents. Includes brainstorming methods catalog and supports both connected (cross-project awareness) and clean-slate modes.
ruby
Comprehensive Ruby development skill covering language fundamentals, object-oriented design patterns, error handling strategies, performance optimization, modern Ruby 3.x features (pattern matching, ractors, typed Ruby), testing patterns, metaprogramming, concurrency, and Rails-specific best practices. Use when writing Ruby code, refactoring, implementing design patterns, handling exceptions, optimizing performance, writing tests, or applying Ruby idioms and conventions.
pydantic-models
Automatically applies when creating data models for API responses and validation. Uses Pydantic BaseModel with validators, field definitions, and proper serialization.
pmc-planning
Update planning docs from PRD files or discrepancies report. Use this skill to update roadmap and dependencies without creating tickets. Works directly with PRD documents and/or 99-discrepancies.md when available.
implementation-guide
Generate comprehensive implementation guides for coding tasks instead of writing code directly. Use when the user requests detailed implementation documentation, step-by-step development guides, or when they want to implement features themselves using tools like Cursor. Creates exhaustive guides with background context, architecture decisions, milestones with verification points, and rationale for a "build-it-yourself" workflow.
global-error-handling
Implement robust error handling with user-friendly messages, proper exception types, and graceful degradation. Use this skill when writing try-catch blocks, defining custom exceptions, or handling failures from external services. When implementing retry strategies, cleaning up resources, or designing centralized error handling. When validating preconditions or failing fast with clear error messages.
seo
Generate SEO-optimized code snippets for websites. Use when asked to optimize SEO, generate meta tags, create structured data (JSON-LD/schema.org), fix heading hierarchy, or audit page SEO. Outputs implementation-ready code for handoff to developers. Supports multilingual sites (Ukrainian/English) and industry-specific schemas for construction equipment, aquaculture, and engineering services.
debugging-systematic
Expert systematic debugging through root cause analysis. Reflects on 5-7 possible sources, distills to 1-2 most likely causes, adds strategic logging to validate assumptions, and confirms diagnosis before fixing. Uses MCP servers for database validation. Use when troubleshooting errors, debugging issues, investigating bugs, analyzing problems, or when user mentions error, bug, not working, broken, or debugging.