Machine Learning

无障碍检查助手，审查Web应用的可访问性，基于WCAG 2.1标准提供改进建议，包括语义HTML、ARIA属性、键盘导航、屏幕阅读器兼容性等。

Creates or updates skills with proper YAML frontmatter, progressive disclosure, and best practices per the open Agent Skills specification. Supports simple, tool-restricted, multi-file, and script-based skills. Use when creating new skills, authoring skills, extending agent capabilities, or when `--create-skill` or `--new-skill` flag is mentioned.

Expert skill for setting up modern Python projects with pyproject.toml configuration and uv package/environment management.

Create structured sprint plans with automated Git workflow. Generates TOML sprints, creates feature branches, and enforces proper development workflow.

Validate HTML5 structure and basic syntax. BLOCKING quality gate - stops pipeline if validation fails. Ensures deterministic output quality.

Generate Kubernetes YAML manifests for deployments, services, ingress, configmaps, and other resources with best practices. Triggers on "create Kubernetes manifest", "generate k8s yaml", "kubernetes deployment for", "k8s config".

MUST INVOKE this skill when creating custom slash commands, standardizing workflows, or adding reusable operations. Secondary: understanding command structure, learning YAML configuration, or optimizing existing commands. Create, audit, and maintain custom slash commands.

정적 HTML/CSS를 RNBT 동적 컴포넌트로 변환합니다. Figma Conversion에서 생성된 정적 파일을 RNBT_architecture 패턴에 맞게 동적 컴포넌트로 변환합니다. Use when converting static HTML to dynamic components, creating RNBT components, or implementing components with data binding and event handling.

Google Cloud Platform configuration templates for BigQuery ML and Vertex AI training with authentication setup, GPU/TPU configs, and cost estimation tools. Use when setting up GCP ML training, configuring BigQuery ML models, deploying Vertex AI training jobs, estimating GCP costs, configuring cloud authentication, selecting GPUs/TPUs for training, or when user mentions BigQuery ML, Vertex AI, GCP training, cloud ML setup, TPU training, or Google Cloud costs.

HTML metadata and head content. Use when writing or reviewing page head sections including SEO, social sharing, performance hints, and bot control.

Teaches Web Components (Custom Elements) support in React 19, including property vs attribute handling and custom events. Use when integrating Web Components or working with custom HTML elements.

Analyze, update, and manage Python dependencies in pyproject.toml, checking for version compatibility, security vulnerabilities, and suggesting upgrades.

Create a new Claude Code skill with proper structure, YAML frontmatter, and documentation. Use when user asks to "create a skill", "make a skill", "build a new skill", or "add a skill".

Use this skill when reviewing pull requests, branch changes, or code diffs. Triggers on "review this PR", "review my changes", "code review", "review branch", or when user shares a GitHub PR URL. Focuses on ML research and internal tooling quality.

High-performance semantic search and document parsing toolkit. Use PROACTIVELY for searching across documentation, YAML manifests, configuration files, or any text where semantic understanding is needed. Particularly effective when exploring unfamiliar codebases, finding conceptually related content, or when exact keywords don't match the desired information.

Reusable UI component design and implementation methodology.Integrates design tokens, accessibility (a11y via W3C APG), and semantic HTML.Reference for building accessible, theme-compliant React components.

Эксперт A/B тестирования. Используй для статистических тестов, экспериментов и ML-оптимизации.

Build TM Forum (TMF) MCP servers from TMF OpenAPI specs (TMF6xx/7xx YAML). Use when you are given a TMF OpenAPI file and asked to (1) implement an MCP server exposing TMF operations as tools, (2) generate a mock TMF API server + client + MCP layer, or (3) standardize tool naming, create/update inputs, $ref/allOf handling, and /hub event-subscription patterns for TMF APIs.

Docker, Kubernetes, CI/CD, model monitoring, and cloud platforms. Use for deploying ML models to production, setting up pipelines, or infrastructure.

Work on the LaTeX thesis or LaTeXML HTML output. Use for build/lint/serve commands, LaTeX style rules, HTML pipeline notes, or assets conventions.