Claude Skills

Master quick plotting and interactive visualization with hvPlot. Use this skill when creating basic plots (line, scatter, bar, histogram, box), visualizing pandas DataFrames with minimal code, adding interactivity and hover tools, composing multiple plots in layouts, or generating publication-quality visualizations rapidly.

Autonomous validation of authentication security. Checks password hashing, cookie configuration, CSRF protection, and session management for OWASP compliance.

Get GitHub user profile information including repos, followers, and activity. Use when the user asks for GitHub user details, profile information, or developer stats.

Ensures engaging user experience through validation of animations, transitions, micro-interactions, and feedback states, preventing flat/static interfaces that lack polish and engagement. Works with Tanstack Start (React) + shadcn/ui components.

Introduces property-based testing with proptest, helping users find edge cases automatically by testing invariants and properties. Activates when users test algorithms or data structures.

Helps design port traits and adapter implementations for external dependencies. Activates when users need to abstract away databases, APIs, or other external systems.

Guides users in creating rich domain models with behavior, value objects, and domain logic. Activates when users define domain entities, business rules, or validation logic.

This skill should be used when CodeRabbit code review feedback needs to be processed and fixed systematically. Use after running `coderabbit --plain` to automatically save feedback, analyze issues using MCP tools, and implement minimal code fixes with proper planning.

Use when designing content systems where 5+ distinct types need to comingle in feeds, timelines, or searches with shared metadata and operations - NOT for simple polymorphic associations or 1-3 similar types

Local Kubernetes development with EKS parity using Kind, LocalStack for AWS services, and local Keycloak for authentication testing

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

计算短波辐射、长波辐射、潜在蒸散发、日出日落时间、湿度的基本变量处理。

Path to the spec file to analyze

Retrieval Augmented Generation systems with vector search, document processing, and hybrid retrieval.

Prompt design, optimization, few-shot learning, and chain of thought techniques for LLM applications.

LLM deployment strategies including vLLM, TGI, and cloud inference endpoints.

Implement authentication and authorization with Better Auth - a framework-agnostic TypeScript authentication framework. Features include email/password authentication with verification, OAuth providers (Google, GitHub, Discord, etc.), two-factor authentication (TOTP, SMS), passkeys/WebAuthn support, session management, role-based access control (RBAC), rate limiting, and database adapters. Use when adding authentication to applications, implementing OAuth flows, setting up 2FA/MFA, managing user sessions, configuring authorization rules, or building secure authentication systems for web applications.

LLM architecture, tokenization, transformers, and inference optimization. Use for understanding and working with language models.

LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.