NLP

Add AI features to Glide apps using AI columns like Generate Text, Image to Text, Audio to Text. Use when adding AI-powered functionality, text generation, OCR, transcription, or auto-categorization.

This skill sets up state management for React, Vue, or Svelte applications.Supports Pinia (Vue 3), Redux Toolkit (React), Zustand (React), Context API (React), Svelte stores.Creates stores, actions, selectors, TypeScript types, persistence (localStorage), and dev tools integration.Activate when user says "state management", "setup Pinia", "Redux store", "global state", or needs shared state.Output: Complete state management setup with stores, actions, TypeScript, persistence, and DevTools.

This skill must be used with any prompt that uses MXCP. MXCP is an enterprise-grade MCP (Model Context Protocol) framework for building production AI applications with SQL and Python endpoints, security, audit trails, policy enforcement, and comprehensive testing. Use this skill when working with MXCP in any capacity including creating, building, initializing, setting up, or editing MXCP servers or projects, configuring MCP tools/resources/prompts, implementing endpoints, setting up authentication/policies, debugging validation errors, or troubleshooting MXCP applications.

Choose words for register, connotation, and precision. Use when: (1) asked to adjust formality or vocabulary, (2) text contains words like "delve" or "leverage", (3) writing for technical or general audience, (4) translating between casual and formal language, (5) text uses abstract terms without concrete reference.

Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid pollution, when formal review cycles (spec compliance then code quality) are required between tasks, or when you need diff-based validation of each task before proceeding.

Automatic persistent memory for Claude Code sessions. Activates on preference statements ("I prefer", "I always", "I like"), corrections ("no, don't", "actually"), identity statements ("my name is", "I work at"), project decisions, or when the system detects memory-related context. Works invisibly in the background.

Build production-grade MCP (Model Context Protocol) servers with observability, correlation ID tracing, and dual logging. Use when creating new MCP servers, adding tools to existing servers, implementing file logging, debugging MCP issues, wrapping CLI tools with spawnSyncCollect, or following Side Quest marketplace patterns. Covers @sidequest/core/mcp declarative API, @sidequest/core/spawn CLI wrapper patterns, Zod schemas, Bun runtime, and 9 gold standard patterns validated across Kit plugin (18 tools). Includes error handling, response format switching, MCP annotations, and graceful degradation.

Guide for creating effective skills. Use when building new skills or updating existing ones that extend ChatGPT with specialized knowledge, workflows, or tool integrations.

Use the gemini-cli-integration skill PROACTIVELY when analyzing large codebases, multiple files, or directories. Leverages Google Gemini's massive context window with @ syntax for file inclusion to handle comprehensive codebase analysis, implementation verification, and architectural understanding.

Skill providing structured iOS lane knowledge: SwiftUI vs UIKit/TCA/MVVM patterns, data stack choices, and OS 2.2 iOS standards. Uses context7 libraries for global guidance.

This skill builds data tables/grids with sorting, filtering, pagination, and row actions.Supports React (TanStack Table, AG Grid), Vue 3 (Vue Good Table, AG Grid), with server/client-side data.Creates tables with column configuration, sorting (multi-column), filtering (text, date, number), pagination, row selection, export (CSV/Excel).Activate when user says "create table", "data grid", "display list", "show users table", or needs tabular data display.Output: Production-ready tables with sorting, filtering, pagination, accessibility, and export functionality.

Generates SHANNON_INDEX for 94% token reduction (58K → 3K tokens). Compresses large codebases into structured summaries with Quick Stats, Tech Stack, Core Modules, Dependencies, Recent Changes, and Key Patterns. Enables fast agent onboarding, efficient multi-agent coordination, and instant context switching. Use when: starting project analysis, onboarding new agents, coordinating waves, switching between codebases, or when context window efficiency is critical.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Orchestrates git workflow for Python feature/release/hotfix development. Loads and coordinates other skills based on current context. Includes PR feedback handling via work-item generation. Use when: - User says "next step?" or "continue workflow" - Working in git repo with TODO_[feature|release|hotfix]_*.md files - Need to determine workflow phase and load appropriate skills - Handling PR feedback via work-items Triggers: next step, continue, what's next, workflow status, PR feedback Coordinates: tech-stack-adapter, git-workflow-manager, bmad-planner, speckit-author, quality-enforcer, workflow-utilities Context management: Prompt user to run /context when context usage is high, then /init to reset before continuing workflow.

Expert guidance for creating, configuring, and deploying Model Context Protocol (MCP) servers. Use when building custom MCP servers, integrating external APIs, or extending Claude with new capabilities.

Manage project context effectively. Use when onboarding, context switching, or maintaining project knowledge. Covers context capture and sharing.

Train and use SuperBPE tokenizers for 20-33% token reduction across any project. Covers training, optimization, validation, and integration with any LLM framework. Use when you need efficient tokenization, want to reduce API costs, or maximize context windows.

Extract named entities (people, organizations, locations, dates) from text using NLP. Use for document analysis, information extraction, or data enrichment.

Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.

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).