NLP

WHEN: Ambiguous prompts, vague requirements, missing context, unclear instructionsWHAT: Ambiguity detection + AskUserQuestion clarification + Interactive option selectionWHEN NOT: Clear detailed instructions → proceed directly

ユーザーメモリ、プロジェクトメモリ、READMEを再読み込み。「コンテキストを再読み込み」「設定をリロード」「CLAUDE.mdを読み直して」と言われた時、またはclear後にコンテキストを復元したい時に使用

Design assessments that work across languages, avoid language-dependent cultural bias, support multilingual learners, and validate assessment equivalence across translations. Use when creating fair assessments for multilingual contexts. Activates on "multilingual assessment", "language-fair testing", or "assessment translation".

Use when needing Claude bot review recommendations from PR - automatically waits for workflows (including Claude review) to complete, then extracts recommendations and returns concise summary without loading full review into context

TypeScript SDKとzodバリデーション、Express統合を使用したModel Context Protocol (MCP) サーバー構築のガイド。TypeScriptベースのMCPサーバーの作成、デバッグ、最適化を行う際に使用してください。

AI-powered enterprise internal communications orchestrator with Context7 integration, intelligent content generation, automated workflow optimization, multi-format support (reports, newsletters, FAQs), and enterprise-grade communication intelligence

Handle template comparison and optimization workflows including backup detection, smart merging, and update completion reporting. Enhanced with Context7 MCP for up-to-date documentation.

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Analyzes images and generates optimized prompts for Google's Veo 3.1 video generation model. Use when users provide an image and want to animate it or create a video prompt from it. Applies Veo 3.1's five-part formula (Cinematography + Subject + Action + Context + Style & Ambiance) and best practices from the official prompting guide.

Enterprise Firebase Platform with AI-powered Google Cloud integration, Context7 integration, and intelligent Firebase orchestration for scalable mobile and web applications

This skill should be used when the user asks "what plugins are available", "list data science tools", "what MCP servers can I use", "enable code intelligence", or needs to discover available plugins like serena, context7, or data access skills like wrds and lseg-data.

HASH error handling patterns using error-stack crate. Use when working with Result types, Report types, defining custom errors, propagating errors with change_context, adding context with attach, implementing Error trait, or documenting error conditions in Rust code.

Enterprise Configuration Management with AI-powered settings architecture, Context7 integration, and intelligent configuration orchestration for scalable applications

Knowledge graph-based text replacement using Terraphim hooks.Intercepts commands and text to apply transformations defined in the knowledge graph.Works with Claude Code PreToolUse hooks and Git prepare-commit-msg hooks.

A skill for performing database CRUD operations following best practices. Includes guidance on session management, query building (filters, joins, aggregations), transaction handling, bulk operations, error handling, connection pooling, and query optimization. Provides reusable templates for database session dependencies, CRUD service classes, and transaction context managers.

Generate images from text prompts using fal.ai Gemini 3 Pro. Use when the user asks to create, generate, or make an image from a text description. Supports multiple aspect ratios and resolutions up to 4K.

Internationalization for TSH Clients Console (English/Arabic with RTL). Use when:(1) Adding new text strings that need translation(2) Creating components with user-facing text(3) Working with RTL layout for Arabic(4) Setting up new pages with proper i18n(5) Debugging translation issues(6) Adding metadata translations for SEO

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

Project memory and learning system that tracks interactions, learns from corrections, maintains knowledge across sessions, and generates token-efficient context. Use when you need to remember project-specific patterns, avoid repeating mistakes, track what works and what doesn't, or maintain institutional knowledge across multiple sessions. Integrates with guardian, wizard, summoner, and style-master.

Writes marketing content (landing pages, tweets, emails) for product features with a casual, direct brand voice. Use when the user ships a feature, needs marketing copy, mentions "marketing content", "landing page", "tweet about", "launch email", "announce", or requests help promoting/explaining product features. Automatically analyzes the codebase to understand the product context before writing.