機器學習

This skill trains machine learning models using automated workflows. It analyzes datasets, selects appropriate model types (classification, regression, etc.), configures training parameters, trains the model with cross-validation, generates performance metrics, and saves the trained model artifact. Use this skill when the user requests to "train" a model, needs to evaluate a dataset for machine learning purposes, or wants to optimize model performance. The skill supports common frameworks like scikit-learn.

This skill enables Claude to generate Kubernetes deployment manifests, services, and related configurations following best practices. It should be used when the user asks to create a new Kubernetes deployment, service, ingress, or other related resources. Claude will generate YAML files for Deployments, Services, ConfigMaps, Secrets, Ingress, and Horizontal Pod Autoscalers. Use this skill when the user mentions "Kubernetes deployment", "K8s deployment", "create service", "define ingress", or asks for a manifest for any K8s resource.

Write E2E tests with Playwright including Page Object Model, visual regression testing, and CI/CD integration. Use when testing user flows, integration testing, or visual regression testing.

This skill enables Claude to automatically scan for XSS (Cross-Site Scripting) vulnerabilities in code. It is triggered when the user requests to "scan for XSS vulnerabilities", "check for XSS", or uses the command "/xss". The skill identifies reflected, stored, and DOM-based XSS vulnerabilities. It analyzes HTML, JavaScript, CSS, and URL contexts to detect potential exploits and suggests safe proof-of-concept payloads. This skill is best used during code review, security audits, and before deploying web applications to production.

Create HTML diagrams for Marp slides and capture them as PNG screenshots using Playwright MCP

Create new skills with proper structure and YAML frontmatter. Use when building new slash command skills, ensuring consistent formatting, directory structure, and validation. Guides through the complete skill creation workflow.

Master declarative, no-code data dashboards with Lumen YAML specifications. Use this skill when building standard data exploration dashboards, connecting multiple data sources (files, databases, APIs), creating interactive filters and cross-filtering, designing responsive layouts with indicators and charts, or enabling rapid dashboard prototyping without writing code.

UI component best practices for vanilla JavaScript and HTML. Use this skill when creating or modifying HTML elements, building reusable JavaScript modules, or structuring DOM components in this static website. Apply when working on .html files, JavaScript modules in js/ that manage UI state or rendering, or when creating modular, reusable UI patterns.

This skill enables Claude to automatically detect performance regressions in a CI/CD pipeline. It analyzes performance metrics, such as response time and throughput, and compares them against baselines or thresholds. Use this skill when the user requests to "detect performance regressions", "analyze performance metrics for regressions", or "find performance degradation" in a CI/CD environment. The skill is also triggered when the user mentions "baseline comparison", "statistical significance analysis", or "performance budget violations". It helps identify and report performance issues early in the development cycle.

This skill provides a complete and streamlined workflow for performing methylation variability and epigenetic heterogeneity analysis from whole-genome bisulfite sequencing (WGBS) data. It is designed for researchers who want to quantify CpG-level variability across biological samples or conditions, identify highly variable CpGs (HVCs), and explore epigenetic heterogeneity.

Web accessibility patterns and WCAG compliance guidelines. Use when implementing accessible UI components, keyboard navigation, screen reader support, or auditing for a11y compliance. Triggers: accessibility, a11y, WCAG, ARIA, screen reader, keyboard navigation, color contrast, semantic HTML, assistive technology.

This skill empowers Claude to build AutoML pipelines using the automl-pipeline-builder plugin. It is triggered when the user requests the creation of an automated machine learning pipeline, specifies the use of AutoML techniques, or asks for assistance in automating the machine learning model building process. The skill analyzes the context, generates code for the ML task, includes data validation and error handling, provides performance metrics, and saves artifacts with documentation. Use this skill when the user explicitly asks to "build automl pipeline", "create automated ml pipeline", or needs help with "automating machine learning workflows".

This skill enables Claude to deploy machine learning models to production environments. It automates the deployment workflow, implements best practices for serving models, optimizes performance, and handles potential errors. Use this skill when the user requests to deploy a model, serve a model via an API, or put a trained model into a production environment. The skill is triggered by requests containing terms like "deploy model," "productionize model," "serve model," or "model deployment."

This skill enables Claude to track and manage AI/ML model versions using the model-versioning-tracker plugin. It should be used when the user asks to manage model versions, track model lineage, log model performance, or implement version control for AI/ML models. Use this skill when the user mentions "track versions", "model registry", "MLflow", or requests assistance with AI/ML model deployment and management. This skill facilitates the implementation of best practices for model versioning, automation of model workflows, and performance optimization.

Code reviewer focusing on correctness, regressions, security, and test coverage - P0/P1/P2 severity

This skill empowers Claude to build AutoML pipelines using the automl-pipeline-builder plugin. It is triggered when the user requests the creation of an automated machine learning pipeline, specifies the use of AutoML techniques, or asks for assistance in automating the machine learning model building process. The skill analyzes the context, generates code for the ML task, includes data validation and error handling, provides performance metrics, and saves artifacts with documentation. Use this skill when the user explicitly asks to "build automl pipeline", "create automated ml pipeline", or needs help with "automating machine learning workflows".

Generate exhaustively complete and accurate Datadog Software Catalog entity YAML files (v3 schema) by examining project source code and interviewing engineers. Use when engineers need to create or update entity.datadog.yaml files for services, datastores, queues, APIs, or systems. Triggers include: "create entity yaml", "generate service catalog entry", "document this project in datadog", "create service definition", "add to software catalog", or any request involving Datadog entity/service documentation. Supports all v3 entity kinds: service, datastore, queue, api, system. Fetches existing Datadog data via API. Validates against official JSON schema. Merges with existing definitions. Outputs to .datadog/ directory.

Expert IT Risk Manager with deep knowledge of ISO 27005 (IT risk management), ISO 31000 (enterprise risk management), and ISO 27001 integration. Specializes in optimizing workflows through the Data Reuse principle - leveraging existing Assets, Incidents, Controls, and Business Processes to streamline risk assessments. Automatically activated when user asks about risk management, risk assessment, risk treatment, risk appetite, risk acceptance, ISO 27005, ISO 31000, threat analysis, vulnerability assessment, or risk matrices.

This skill enables Claude to seamlessly integrate with various secrets managers like HashiCorp Vault and AWS Secrets Manager. It generates configurations and setup code, ensuring best practices for secure credential management. Use this skill when you need to manage sensitive information, generate production-ready configurations, or implement a security-first approach for your DevOps infrastructure. Trigger terms include "integrate secrets manager", "configure Vault", "AWS Secrets Manager setup", "manage credentials securely", or requests for secure configuration generation.

Evaluates machine learning models for performance, fairness, and reliability using appropriate metrics and validation techniques. Trigger keywords: model evaluation, metrics, accuracy, precision, recall, F1, ROC, AUC, cross-validation, ML testing.