機器學習
1913 skills in 數據與 AI > 機器學習
dapr-config-validator
Automatically validate DAPR configuration files (dapr.yaml, component YAML files) when they are created or modified. Checks for schema compliance, missing required fields, invalid values, and common misconfigurations. Use when validating DAPR configs, reviewing component setup, or before deployment.
plotting
Creates publication-quality scientific plots. Use when making plots, figures, or visualizations. Applies tueplots TMLR styling, LaTeX rendering, no titles.
document-converter-suite
Convert between 8 formats (PDF, DOCX, PPTX, XLSX, TXT, CSV, MD, HTML). Best-effort text extraction, batch processing, and document format transformation.
hotwire-patterns-turbo-stimulus
This skill should be used when the user asks about "Hotwire", "Turbo", "Stimulus", "Turbo Frames", "Turbo Streams", "progressive enhancement", "HTML over the wire", or building interactive Rails frontends without heavy JavaScript frameworks. Load this skill when implementing modern Rails frontend patterns.
conversational-goal-discovery
Chat-based goal classification (habit/distance/speed/race) with constraint clarification. Use during onboarding or when user wants to update their running goals through conversation with weekly commitment discovery.
helm-charts
Creates and manages Helm charts for Kubernetes deployments. This skill should be used when packaging applications for Kubernetes using Helm, creating Chart.yaml, values.yaml, and templates. It covers chart structure, templating, dependencies, and deployment patterns. Use this skill for Phase IV+ Kubernetes deployments.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
mapping-html-to-api
Maps HTML content elements to API response fields and generates data binding specifications. Updates the "APIマッピング" section in screen spec.md.
full-video-workflow-skill
Complete pre-production workflow that chains research, project creation, script generation, and presentation in one seamless flow. Use when starting a new video from competitor research all the way through to a ready-to-record script.
Running and Debugging Tests
Executes language-agnostic test suites to validate behavioral correctness, enforce regression safety, and automatically debug or repair test failures. Includes fallback loops, coverage validation, and failure classification to maximize suite reliability. Use to validate code changes proactively, or when the user mentions running tests, test failures, or test debugging.
clarity-streamline
Simplify without losing essential accuracy by identifying what is load-bearing versus decorative. Use when: (1) asked to simplify or reduce wordiness, (2) text repeats same concept in different words, (3) text contains hedges like "it should be noted that", (4) user says explanation is too long.
testing
Comprehensive testing strategies including TDD, unit, integration, E2E, and property-based testing. Ensures code quality and prevents regressions. Use when writing tests, implementing features test-first, or improving coverage.
venue-templates
Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
Unnamed Skill
This skill should be used when the user asks about Hotwire, Turbo Drive, Turbo Frames, Turbo Streams, Stimulus controllers, frontend interactivity, server-rendered HTML updates, websocket updates, progressive enhancement, data attributes, importing JavaScript modules, or building interactive UIs without React/Vue. Also use when discussing the "HTML over the wire" approach or NO BUILD philosophy. Examples:
web-development-skill
Master modern web development. Learn HTML/CSS/JavaScript fundamentals, React/Vue/Angular frameworks, Node.js backend, databases, APIs, and full-stack architectures. Use when building web applications, learning web technologies, or choosing tech stacks.
web-accessibility
Webアクセシビリティ対応ガイド。WCAG 2.1準拠、セマンティックHTML、ARIA属性、キーボード操作、スクリーンリーダー対応など、誰もが使えるWebアプリケーション構築のベストプラクティス。
mermaid-diagramming
Creates Mermaid v11+ diagrams with ELK layout and YAML frontmatter. Covers 22 diagram types: flowchart, mindmap, block, sequence, journey, state, ER, class, requirement, pie, quadrant, sankey, xy, radar, gantt, treemap, C4, architecture, packet, timeline, gitgraph, kanban. Use when visualizing: logic flow, interactions, state machines, data models, charts, system architecture, or any diagram requiring theming, classDef styling, or accessibility.
Refactoring Test Suites
Enforces consistent test quality, structure, and maintainability across any programming language by applying project-wide conventions for test naming, structure, parameterization, and classification. Use for messy test suites, inconsistent naming, improving CI alignment and developer readability, or when the user mentions test cleanup, test organization, or test standardization.
playwright-scraper
Production-proven Playwright web scraping patterns with selector-first approach and robust error handling. Use when users need to build web scrapers, extract data from websites, automate browser interactions, or ask about Playwright selectors, text extraction (innerText vs textContent), regex patterns for HTML, fallback hierarchies, or scraping best practices.