langfuse-observability
LLM observability with self-hosted Langfuse 3.x - tracing, evaluation, monitoring, prompt management, and cost tracking
发现 研究与调研 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
LLM observability with self-hosted Langfuse 3.x - tracing, evaluation, monitoring, prompt management, and cost tracking
Implement real-time data streaming with Server-Sent Events (SSE), WebSockets, and ReadableStream APIs. Master backpressure handling, reconnection strategies, and LLM streaming for 2025+ real-time applications.
Use this skill when creating comprehensive testing strategies for applications. Provides test planning templates, coverage targets, test case structures, and guidance for unit, integration, E2E, and performance...
Structured logging, metrics, distributed tracing, and alerting strategies
Capture content from JavaScript-rendered pages, login-protected sites, and multi-page documentation using Playwright MCP tools or Claude Chrome extension. Use when WebFetch fails on SPAs, dynamic content, or au...
Backup, restore, and validate golden datasets for AI/ML systems - ensuring test data integrity and preventing catastrophic data loss
Achieve end-to-end type safety with Zod runtime validation, tRPC type-safe APIs, Prisma ORM, exhaustive type checking, and TypeScript 5.7+ features. Build fully type-safe applications from database to UI for 20...
Create beautiful ASCII art visualizations for plans, architectures, workflows, and data
CI/CD pipelines, containerization, Kubernetes, and infrastructure as code patterns
Validation rules, schema checks, duplicate detection, and coverage analysis for golden dataset integrity
GitHub CLI (gh) mastery for issues, PRs, Projects v2, and automation. Modern development workflow patterns for 2025.
Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for...
Use this skill when designing database schemas for relational (SQL) or document (NoSQL) databases. Provides normalization guidelines, indexing strategies, migration patterns, and performance optimization techni...
Use this skill when creating or evolving design systems for applications. Provides design token structures, component architecture patterns, documentation templates, and accessibility guidelines. Ensures consis...
Design and implement React Server Components with Next.js 15 App Router. Master server-first architecture, streaming SSR, Server Actions, React 19 patterns, and modern data fetching for 2025+ development.
Design and implement multi-agent workflows with LangGraph 0.2+ - state management, supervisor-worker patterns, conditional routing, and fault-tolerant checkpointing
Quality criteria, workflows, and multi-agent analysis patterns for curating high-quality golden dataset entries
Production hybrid search with PGVector 0.7+ and BM25 using Reciprocal Rank Fusion, metadata filtering, and HNSW indexing for semantic retrieval
Use this skill when designing REST, GraphQL, or gRPC APIs. Provides comprehensive API design patterns, versioning strategies, error handling conventions, authentication approaches, and OpenAPI/AsyncAPI template...
Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and increm...
Playwright testing with autonomous test agents (planner, generator, healer) and visual regression testing
Tailwind CSS v4 best practices, CSS-first configuration and modern patterns. Use when writing styles, configuring themes or migrating from v3.
React 19 best practices, hooks, state management and data fetching. Use when writing components, hooks, managing state, handling async operations or reviewing React code.
Tauri v2 and Rust backend best practices, commands, state management, IPC and security patterns. Use when writing Rust backend code, creating commands or integrating with the frontend.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。