claude-code

Comprehensive SEO analysis and optimization for content creators and marketers.

Comprehensive performance optimization guide for Tailwind CSS v4 applications. Contains 44 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.

Source details, install context, and public review data are available on the full page.

Implement robust database migration systems with version control, rollback capabilities, and data transformation strategies. Includes migration frameworks and production deployment patterns.

Comprehensive performance optimization guide for Expo React Native applications. Contains 54 rules across 9 categories, prioritized by impact to guide automated refactoring and code generation.

Skill for managing and interacting with Model Context Protocol (MCP) servers.

专业的 Dify 工作流 DSL/YML 文件自动生成工具，基于对 86+ 实际工作流案例的深度学习，能够根据用户的业务需求自动生成符合 Dify 规范的完整工作流配置文件。

Comprehensive guide for building modern full-stack web applications using Next.js, Turborepo, and RemixIcon.

OpenAI's model that understands images from natural language.

Source details, install context, and public review data are available on the full page.

Comprehensive guide to running ML workloads on Lambda Labs GPU cloud with on-demand instances and 1-Click Clusters.

NeMo Guardrails adds programmable safety rails to LLM applications at runtime.

bitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with <1% accuracy loss.

Establish semantic versioning practices to maintain consistent version numbering aligned with release significance, enabling automated version management and release notes generation.

SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.

Source details, install context, and public review data are available on the full page.

Visual regression testing captures screenshots of UI components and pages, then compares them across versions to detect unintended visual changes. This automated approach catches CSS bugs, layout issues, and design regressions that traditional functional tests miss.

Web performance audits measure load times, identify bottlenecks, and guide optimization efforts to create faster, better user experiences.

Load with: base.md + [typescript.md | python.md]

LitGPT provides 20+ pretrained LLM implementations with clean, readable code and production-ready training workflows.

Implication : Core logic is framework-agnostic. When contributing or debugging, check if issue is in @xyflow/system or framework-specific package.

Comprehensive design rules for Apple Vision Pro based on Apple Human Interface Guidelines. These rules ensure spatial computing apps are comfortable, intuitive, and consistent with platform conventions.

Load with: base.md + (typescript.md or python.md)

Slow database queries are a common performance bottleneck. Optimization through indexing, efficient queries, and caching dramatically improves application performance.