NLP

Use when implementing models that learn from minimal data or need to adapt to new market regimes rapidly. Covers episodic learning, context sets, support and query sequences, zero-shot vs few-shot learning, meta-learning for finance, transfer learning across assets and regimes, and quick adaptation to market changes.

REPL debugging tool for capturing and inspecting local scope at runtime.Use when debugging functions, investigating test failures, understanding intermediate values,or when you need to recreate the runtime context of code without manually fabricating values.

Phase-aware context management for coder agents to prevent token bloat through checkpoint/restore pattern

Laravel Prompts - Beautiful and user-friendly forms for command-line applications with browser-like features including placeholder text and validation

UI component definitions for the East language. Use when building UIs with @elaraai/east-ui. Triggers for: (1) Creating UI components with Stack, Box, Grid, Card, Text, Button, (2) Building forms with Input, Select, Checkbox, Switch, Slider, (3) Displaying data with Table, DataList, Chart, Badge, Tag, Stat, (4) Using overlays like Dialog, Drawer, Popover, Tooltip, Menu, (5) Working with UIComponentType, (6) Styling with variants (FontWeight, TextAlign, ColorScheme, Size).

Instrument agent tool executions with proper context and error handling

This skill should be used when designing context management, implementing tiered fidelity, reducing token waste, applying Four Laws patterns, creating "NOT PASSED" sections, optimizing agent context, or debugging context-related issues. Provides SOTA patterns for context-efficient multi-agent systems achieving 60-80% token reduction.

Search Claude conversation history from JSONL files. Use when looking for previous discussions, past decisions, code solutions, or context from earlier conversations.

Automatically applies when creating AI tool functions. Ensures proper schema design, input validation, error handling, context access, and comprehensive testing.

Automatically discovers and loads relevant project context from markdown documentation before each task. This skill should be used at the start of every task to ensure Claude has access to project plans, architecture, implementation status, and feedback. It intelligently matches context documents based on keywords, file paths, and task types, then loads relevant documentation to inform the current work.

This skill should be used when reviewing AI-generated text, checking for AI writing patterns, detecting undisclosed AI content, or before finalizing any written content. Covers 12 categories of AI writing indicators from Wikipedia's comprehensive guide.

AI-powered enterprise MCP (Model Context Protocol) server development orchestrator with Context7 integration, intelligent code generation, automated architecture design, and enterprise-grade server deployment patterns for advanced LLM service integration

Analyze text to identify technical domains and suggest appropriate specialized agentsfor delegation following Constitutional Principle X (Agent Delegation Protocol).This skill examines specifications, plans, tasks, or any technical text to detectdomain keywords and recommend whether to use single-agent or multi-agent delegation.It ensures specialized work is routed to specialists rather than handled by generalists.Triggered by: User request for "which agent?", "who should do this?", domainidentification needs, or automatically by /specify, /plan, /tasks commands.

Write and update RSpec tests following BDD principles with behavior-first approach, characteristic-based context hierarchy, and happy path priority. **Activate when:** user mentions RSpec/specs/testing, works with *_spec.rb files, asks to write/add/update/fix tests, or requests test coverage. Ensures tests describe observable behavior, not implementation details.

Analyze videos using Google's Gemini API - describe content, answer questions, transcribe audio with visual descriptions, reference timestamps, clip videos, and process YouTube URLs. Supports 9 video formats, multiple models (Gemini 2.5/2.0), and context windows up to 2M tokens (6 hours of video).

Generates typography scales using modular ratios with auto-calculated line heights. Use when setting up font-size tokens, heading hierarchy (h1-h6), or text sizing systems. Outputs CSS, Tailwind, or JSON.

Retrieve project-specific insights from file-based memory. Use when working on features, encountering domain-specific questions, or user says "--project-recall" or "--recall" (you decide which scope, may use both). Skip for routine tasks or universal pattern questions (use coder-memory-recall). MUST be invoked using Task tool to avoid polluting main context.

Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery. | Sử dụng khi: quản lý MCP, tool server, kết nối external tools.

On-demand Azure DevOps operations (PRs, work items, pipelines, repos) using context-efficient patterns. Loaded only when needed to avoid polluting Claude context with 50+ MCP tools.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).