Data & AI

Validate that curriculum fully covers required standards, check depth and rigor of coverage, verify assessment alignment, and generate coverage reports for administrators. Use for comprehensive validation. Activates on "validate coverage", "standards compliance", or "coverage report".

将技术选型决策转换为业务语言解释，生成客户友好的技术说明。当ARCH中技术术语过多、需要向PM/客户解释时使用。

Implement GPU scheduling with VRAM budgets, work queues, and model lifecycle management. Use when building ML pipeline orchestrators.

Implement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to transcribe audio files, convert speech to text, build voice input features, or process audio recordings. Supports base64 encoded audio files and returns accurate text transcriptions.

Production deployment configurations for Celery workers and beat schedulers across Docker, Kubernetes, and systemd environments. Use when deploying Celery to production, containerizing workers, orchestrating with Kubernetes, setting up systemd services, configuring health checks, implementing graceful shutdowns, or when user mentions deployment, Docker, Kubernetes, systemd, production setup, or worker containerization.

Execute a complete TDD cycle (RED → GREEN → REFACTOR) for one test. Orchestrates the full workflow from writing a failing test through implementation and refactoring to commit.

Teaches when type assertions are safe versus dangerous in TypeScript. Use when considering using 'as' keyword, type casting, or when working with external data that might use assertions instead of proper validation.

Fetch and display filtered X (Twitter) timeline based on your interests. Shows AI/ML research, developer tools, and technical content while filtering out noise, rage bait, and irrelevant posts. Uses Claude Haiku to score relevance against your objectives.

Defines the autonomous development workflow. Use when orchestrating work between agents, managing issue lifecycles, or understanding the development loop.

Run pytest test suite for the video processing pipeline with coverage analysis. Use when the user wants to run tests, check test coverage, validate code quality, or verify pipeline functionality.

Markdown documentation standards for LLM-optimized architecture including section numbering rules for Pandoc PDF generation. Use when writing markdown documentation, creating skills, or authoring content that may be converted to PDF.

Code Review Master - Guardian of code quality, standards, and maintainability

MANDATORY protocol for parallel agent execution when facing 3+ independent failures or tasks that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

Comprehensive Spring Framework and Spring Boot best practices including dependency injection patterns, bean lifecycle and scopes, REST API development, Spring Data JPA, service layer design, Spring Security, testing strategies, caching, AOP, async processing, error handling, and common anti-patterns. Essential reference for code reviews and Spring Boot application development.

Interpretive guidance for Prettier code formatting across multiple file types (JS/TS, YAML, JSON, CSS, HTML). Use when configuring Prettier, troubleshooting formatting issues, or understanding tool selection for these file types.

Domain registration and management via Namecheap API.

Generate comprehensive implementation plans using Specification-Driven Development (SDD)methodology. Use when creating technical design, implementation roadmap, or executingthe /plan command.This skill orchestrates the plan-template.md execution flow, generating research, datamodels, API contracts, and test scenarios. It validates constitutional compliance(Library-First, Test-First, Contract-First) and prepares for task generation.Triggered by: /plan command, user request for "implementation plan", "technical design","how to implement", or "design this feature".

Implement feature code to make BDD scenarios pass. Write production code that satisfies Given/When/Then scenarios. Use after implement-step-definitions when step definitions exist but scenarios are failing.

Codex handoff checklist for agents.

Use this skill when analyzing large codebases, multiple files, or directories that exceed context limits. Leverages Google Gemini's massive context window with @ syntax for file inclusion to handle comprehensive codebase analysis, implementation verification, and architectural understanding.