llm-models-reference
Reference guide for OpenAI model IDs, capabilities, pricing, and provider endpoints. Use when selecting a model, comparing OpenAI capabilities, or validating model IDs for {{PROJECT_NAME}}.
发现 部署与运维 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。
Reference guide for OpenAI model IDs, capabilities, pricing, and provider endpoints. Use when selecting a model, comparing OpenAI capabilities, or validating model IDs for {{PROJECT_NAME}}.
Manage tri-tier agent memory (hot/warm/cold) with event consolidation and weekly cleanup. Use for memory updates after completing tasks.
Backend testing with pytest including fixtures, mocking, async tests, and database testing. Use for FastAPI/Python test implementation.
Build Next.js 13+ App Router applications with server components, client components, API routes, middleware, and streaming. Use when implementing Next.js features, route handlers, or RSC patterns.
Backend testing with pytest including fixtures, mocking, async tests, and database testing. Use for FastAPI/Python test implementation.
Expanded smart-grep playbook for token-efficient rg --json searches with examples and budgeting.
Build production-ready FastAPI applications with async patterns, Pydantic validation, dependency injection, middleware, and database integration. Use for FastAPI endpoints, async workflows, or API design.
Token-efficient codebase search using ripgrep with JSON output. Reduces token usage by 90-95% vs standard grep. Use for any codebase search to save tokens.
Performance testing using Chrome DevTools, Lighthouse, and Core Web Vitals monitoring. Use for performance profiling or optimization validation.
Advanced Tailwind CSS patterns including custom themes, responsive design, dark mode, animations, and component variants. Use for complex styling or design system implementation.
Complete testing toolkit for web applications - backend pytest, E2E Playwright, performance profiling, and local automation.
Complete testing toolkit for web applications - backend pytest, E2E Playwright, performance profiling, and local automation.
Validate file placement against canonical structure rules and auto-fix violations. Use before committing or when validating project structure.
Vercel deployment management for frontend apps: CLI, env vars, config, troubleshooting, rollback.
Debug and analyze {{PROJECT_NAME}} errors and exceptions. Use when investigating crashes, error patterns, performance issues, or understanding what went wrong in production. Covers error queries by agent, excep...
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use for ML training, analyt...
DPPM (Discover, Plan, Prototype, Monitor) planning and orchestration with mandatory plan documents, impact analysis, ASCII diagrams, task breakdowns, evidence gating, context-compaction check-ins, and user test...
Railway deployment management for {{PROJECT_NAME}}: CLI, env vars, health checks, troubleshooting, rollback.
Build production-ready FastAPI applications with async patterns, Pydantic validation, dependency injection, middleware, and database integration. Use for FastAPI endpoints, async workflows, or API design.
Validate file placement against canonical structure rules and auto-fix violations. Use before committing or when validating project structure.
Update Agent Communication Board with task status, completion messages, and blocker tracking. Use after completing tasks or when blocked.
Advanced AI Solution Architect wisdom for designing production-grade AI systems. Use when (1) architecting new agents, workflows, or AI features, (2) debugging agent behavior or performance issues, (3) making t...
Performance testing using Chrome DevTools, Lighthouse, and Core Web Vitals monitoring. Use for performance profiling or optimization validation.
End-to-end testing with Playwright including page objects, fixtures, visual regression, and CI integration. Use for E2E test implementation or test architecture.
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。