Content & Media

智能测试代码生成工具，支持单元测试、集成测试、E2E测试的快速创建。支持Python(pytest/unittest)、JavaScript(Jest/Mocha)、Java(JUnit)、Go(testing)等主流测试框架。适用于生成测试、写测试、测试用例、单元测试、集成测试等场景。

Build modern Fluent Design WPF applications using the WPF UI library (lepoco/wpfui). Use when creating WPF desktop apps with Windows 11 styling, NavigationView shells, dark/light themes, Card layouts, and modern controls. Provides patterns for App.xaml setup, MVVM integration, dashboard layouts, and real-world UI improvements.

Research subject matter, align to educational standards, map prerequisites, and recommend learning theories for curriculum design. Use when starting curriculum development, exploring new topics, or needing standards alignment. Activates on "research this topic", "what standards apply", "curriculum research", or "prerequisite analysis".

ElevenLabs text-to-speech with mac-style say UX.

This skill should be used when determining when and how to interrupt autonomous work to consult the user. Use when encountering ambiguity, conflicts, or decisions requiring user input.

This skill should be used when the user asks to "design MCP tool", "create tool schema", "tool best practices", "input validation", "output schema", "error handling for tools", or discusses designing individual MCP tools with proper schemas and responses.

Core identity and continuity system. Use to grow wisdom, record failures, observe identity, and access accumulated knowledge.

MVVM pattern, Clean Architecture, Repository pattern, dependency injection, SOLID principles. Use when designing app architecture.

Decomposes requirements into executable tasks and coordinates domain orchestrators (frontend, backend, data, test, devops). Use when receiving PRDs, user requirements, or feature requests that span multiple domains. Acts as CEO of the AI development system.

Testing strategy and test pyramid for EFT-Tracker. Guides when to write unit, integration, E2E, or smoke tests. Includes MSW patterns, Playwright best practices, and contract testing. Activates when user mentions: test, unit test, integration test, E2E, Playwright, MSW, coverage, mock, test pyramid, vitest.

Systematically rebuild mental model of any repository when starting fresh sessions. Use when session starts, user says refresh context, or invokes /refresh-context. Eliminates cold start problem in <3500 tokens.

Pre-deployment verification for young-personal-site.Ensures build success, TypeScript, i18n sync, and functionality.

Design and implement the Viet K-Connect visa assessment engine (DB-driven ruleset JSON schema + versioning + effective dates). No hardcoded rules in code. Use for building /api/visa/assess and admin ruleset management.

Generate optimized Dockerfiles with multi-stage builds and best practices. Use when containerizing applications or creating Docker configurations.

Unified content extraction and action planning. Use when user says "tapestry <URL>", "weave <URL>", "help me plan <URL>", "extract and plan <URL>", "make this actionable <URL>", or similar phrases indicating they want to extract content and create an action plan. Automatically detects content type (YouTube video, article, PDF) and processes accordingly.

Elite AI/ML Senior Engineer with 20+ years experience. Transforms Claude into a world-class AI researcher and engineer capable of building production-grade ML systems, LLMs, transformers, and computer vision solutions. Use when: (1) Building ML/DL models from scratch or fine-tuning, (2) Designing neural network architectures, (3) Implementing LLMs, transformers, attention mechanisms, (4) Computer vision tasks (object detection, segmentation, GANs), (5) NLP tasks (NER, sentiment, embeddings), (6) MLOps and production deployment, (7) Data preprocessing and feature engineering, (8) Model optimization and debugging, (9) Clean code review for ML projects, (10) Choosing optimal libraries and frameworks. Triggers: "ML", "AI", "deep learning", "neural network", "transformer", "LLM", "computer vision", "NLP", "TensorFlow", "PyTorch", "sklearn", "train model", "fine-tune", "embedding", "CNN", "RNN", "LSTM", "attention", "GPT", "BERT", "diffusion", "GAN", "object detection", "segmentation".

Defines and generates OpenAPI 3.1 specifications with TypeScript type generation, validation, and documentation. Use when documenting APIs, generating client SDKs, or implementing contract-first API design.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks.

Creates Claude Code slash commands with optimized content and proper front matter following official best practices. Use when user says 'create a command' or 'make a slash command'.

Use this whenever a user wants to add a new feature or explitly states to research a feature/API or building a plan for a new feature. It iterviews the user for feature details (if not provided), research the best API/service for their needs, confirm choice, then gather all implementation notes for their request and save them as a .claude/plans file.