Total 37,509 skills
Showing 12 of 37509 skills
Use this skill for ANY question about creating test or evaluation datasets for LangChain agents. Covers generating datasets from traces (final_response, single_step, trajectory, RAG types), uploading to LangSmith, and managing evaluation data.
Comprehensive performance specialist covering analysis, optimization, load testing, and framework-specific performance. Use when identifying bottlenecks, optimizing code, conducting load tests, analyzing Core Web Vitals, fixing memory leaks, or improving application performance across all layers (application, database, frontend). Includes React-specific optimization patterns.
Docker and Docker Compose reference for container deployment, networking, volumes, and orchestration. Includes Proxmox hosting and LXC comparison patterns. Use when working with docker-compose.yaml, Dockerfiles, troubleshooting containers, or planning container architecture. Triggers: docker, compose, container, dockerfile, volume, network, service, lxc.
Breaks work into bite-sized tasks before coding. Activates when a multi-step task needs planning — creates tasks small enough for a junior developer to follow (2-5 minutes each), with exact file paths, complete implementation details, and verification steps. References Linear issue context and project-specific test commands from CLAUDE.md.
Cloud infrastructure design and deployment patterns for AWS, Azure, and GCP. Use when designing cloud architectures, implementing IaC with Terraform, optimizing costs, or setting up multi-region deployments.
Builds scalable design systems with tokens, theming, and component architecture. Use when creating design token hierarchies, theming systems, component variant patterns, or accessibility foundations. Use for design tokens, CVA variants, dark mode, multi-brand theming, Radix headless UI, Storybook documentation, and governance.
Orchestration mode for implementation tasks. Manages the plan → code → review loop. Use /orchestrate <requirements> or let /implement invoke it.
Expert code review specialist for quality, security, and maintainability. Use when reviewing code changes, ensuring high development standards, or conducting security audits. Provides actionable feedback organized by priority.
Guide spec-driven development workflow (Requirements → Design → Tasks → Implementation) with approval gates between phases. Use when user wants structured feature planning or says "use spec-driven" or "follow the spec process".
Provide development estimates for tasks, features, or projects. Use when user asks for time estimates, effort assessment, or project sizing.
Remove AI-style code slop from a branch by reviewing diffs, deleting inconsistent defensive noise, and preserving behavior and local style.
创建高质量 MCP（模型上下文协议）服务器的指南，使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python (FastMCP) 还是 Node/TypeScript (MCP SDK)。