機器學習
1913 skills in 數據與 AI > 機器學習
html-tools
This skill should be used when building single-file browser applications, client-side utilities, or interactive tools that need no backend. Covers patterns for state persistence, API integration, and advanced browser capabilities without React or build steps.
web-components-architecture
Build web components using Custom Elements v1 API with Declarative Shadow DOM, attribute-driven state, handleEvent pattern, and zero DOM selection. Use when creating custom elements, extending built-in HTML elements, or implementing component-based architecture. NO querySelector, NO innerHTML, NO external libraries - pure web platform APIs only.
semantic-html
Semantic HTML5 markup patterns for meaningful, accessible, and SEO-optimized content structure
htmlgraph-tracker
HtmlGraph workflow skill combining session tracking, orchestration, and parallel coordination. Activated automatically at session start. Enforces delegation patterns, manages multi-agent workflows, ensures proper activity attribution, and maintains feature awareness. Use when working with HtmlGraph projects, spawning parallel agents, or coordinating complex work.
pdf-to-markdown-converter
Converts PDF files to Markdown format using PyMuPDF, extracting text content and embedded images. Fast and lightweight. Automatically fixes LaTeX umlauts (¨a → ä, etc.) and converts ß to ss (Swiss German). Use when converting PDFs to Markdown, extracting document content, or processing PDF files for text analysis. Generates one .md file and 0..n .png files for images.
moonbit-spec-test-development
Create formal spec-driven MoonBit APIs and test suites. Use when asked to set up a spec.mbt, spec-driven tests, or a formal contract-first workflow (e.g., "set up a formal spec & test suite for Yaml in MoonBit"), including moon.mod.json/moon.pkg.json scaffolding and guidance to implement in separate files.
rdc-brand-style-guide
Realtor.com brand guidelines for creating branded reports, presentations, dashboards, and visualizations. Includes official colors, typography, logo usage rules, and styling guidance. Use when creating reports, HTML dashboards, presentations, charts, or any deliverable that should follow RDC brand standards. Triggers include requests for "branded" outputs, company presentations, executive reports, slide decks, or visualizations needing consistent Realtor.com styling.
arena-cli
CLI tools for Are.na: export blocks, enrich with vision AI, generate views. Use when: (1) exporting Are.na blocks incrementally, (2) enriching images with AI-generated titles/tags/patterns, (3) generating browsable HTML views, (4) searching blocks by UI patterns or tags, (5) visual search results when terminal output is insufficient. Triggers: "export arena", "enrich arena", "sync arena", "arena view", "search arena for [pattern]", "show me [pattern]".
research-pdf
Create distinctive HTML one-pagers with curated aesthetics, then convert to PDF using headless browser.
quality-assurance
Copilot agent that assists with comprehensive QA strategy and test planning to ensure product quality through systematic testing and quality metrics Trigger terms: QA, quality assurance, test strategy, QA plan, quality metrics, test planning, quality gates, acceptance testing, regression testing Use when: User requests involve quality assurance tasks.
backend-bugfix
This skill should be used when the user asks to "debug backend tests", "fix pytest failures", "analyze Python errors", "fix FastAPI bugs", or mentions keywords like "pytest", "IntegrityError", "ValidationError", "SQLAlchemy", "FastAPI". It provides the complete bugfix workflow knowledge including error classification, confidence scoring, and TDD best practices for Python/FastAPI backends.
security-bluebook-builder
Create or refine a concise, normative security policy ("Blue Book") for sensitive applications. Use when users need a threat model, data classification rules, auth/session policy, logging and audit requirements, retention/deletion expectations, incident response, or security gates for apps handling PII/PHI/financial data.
web-ui-ux
Web UI/UX specialist guidance for designing, reviewing, and polishing web product UI (layout, usability, microcopy, accessibility, responsive behavior, forms, navigation). Use when asked to improve UI/UX, audit a page, design a screen, create a component spec, or generate HTML head/manifest/icon guidance for a web app; optionally applicable to Unreal UI (UMG) for UX heuristics.
openapi-contract-editor
Guides editing and creation of OpenAPI 3.0 contracts in binora-contract submodule with modular YAML structure, Redocly validation, and Django/DRF consistency checks. Auto-activates when editing contracts, implementing endpoints, or modifying serializers.
Unnamed Skill
I/O platform functions for the East language on Node.js. Use when writing East programs that need SQL databases (SQLite, PostgreSQL, MySQL), NoSQL databases (Redis, MongoDB), S3 storage, file transfers (FTP, SFTP), file format parsing (XLSX, XML), or compression (Gzip, Zip, Tar). Triggers for: (1) Writing East programs with @elaraai/east-node-io, (2) Database operations with SQL.SQLite, SQL.Postgres, SQL.MySQL, NoSQL.Redis, NoSQL.MongoDB, (3) Cloud storage with Storage.S3, (4) File transfers with Transfer.FTP, Transfer.SFTP, (5) Format parsing with Format.XLSX, Format.XML, (6) Compression with Compression.Gzip, Compression.Zip, Compression.Tar.
frontend-guide
Comprehensive frontend development guide covering HTML, CSS, JavaScript, TypeScript, React, Vue, Angular, and modern web technologies. Use when working on frontend development, web applications, or UI/UX implementation.
dapr-azure-integration
Configure Azure services as DAPR components with best practices. Supports Azure Cosmos DB, Service Bus, Key Vault, Blob Storage, Event Grid, and Container Apps. Automatically generates component YAML with managed identity support. Use when integrating Azure services or deploying to Azure.
fiftyone-dataset-inference
Create a FiftyOne dataset from a directory of media files (images, videos, point clouds), optionally import labels in common formats (COCO, YOLO, VOC), run model inference, and store predictions. Use when users want to load local files into FiftyOne, apply ML models for detection, classification, or segmentation, or build end-to-end inference pipelines.
skill-review
Audit claude-skills repository documentation with systematic 9-phase review: standards compliance, official docs verification via Context7/WebFetch, code examples accuracy, cross-file consistency, and version drift detection. Auto-fixes unambiguous issues with severity classification. Use when: investigating skill issues, major package updates detected (e.g., v1.x → v2.x), skill not verified >90 days, before marketplace submission, or troubleshooting outdated API patterns, contradictory examples, broken links, version drift.
cv-data-ingestion
Ingest and organize raw career data from Obsidian notes, CSV files, zip archives, and markdown documents into the Universal CV portfolio system. Use when processing career history, work experience, testimonials, case studies, or resume data from multiple sources. Outputs structured YAML/Markdown validated against Zod schemas.