LLM & Agents

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Backend AI functionality with Vercel AI SDK v5 - text generation, structured output with Zod,tool calling, and agents. Multi-provider support for OpenAI, Anthropic, Google, and Cloudflare Workers AI.Use when: implementing server-side AI features, generating text/chat completions, creating structuredAI outputs with Zod schemas, building AI agents with tools, streaming AI responses, integratingOpenAI/Anthropic/Google/Cloudflare providers, or encountering AI SDK errors like AI_APICallError,AI_NoObjectGeneratedError, streaming failures, or worker startup limits.Keywords: ai sdk core, vercel ai sdk, generateText, streamText, generateObject, streamObject,ai sdk node, ai sdk server, zod ai schema, ai tools calling, ai agent class, openai sdk, anthropic sdk,google gemini sdk, workers-ai-provider, ai streaming backend, multi-provider ai, ai sdk errors,AI_APICallError, AI_NoObjectGeneratedError, streamText fails, worker startup limit ai

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Maintains high-quality, concise, project-aligned documentation. Creates, updates, and validates README.md, CLAUDE.md, code comments, and other documentation. Activates after implementing features, when documentation is outdated, or when explicitly requested.

Complete guide for OpenAI's Assistants API v2: stateful conversational AI with built-in tools(Code Interpreter, File Search, Function Calling), vector stores for RAG (up to 10,000 files),thread/run lifecycle management, and streaming patterns. Both Node.js SDK and fetch approaches.⚠️ DEPRECATION NOTICE: OpenAI plans to sunset Assistants API in H1 2026 in favor of Responses API.This skill remains valuable for existing apps and migration planning.Use when: building stateful chatbots with OpenAI, implementing RAG with vector stores, executingPython code with Code Interpreter, using file search for document Q&A, managing conversation threads,streaming assistant responses, or encountering errors like "thread already has active run", vectorstore indexing delays, run polling timeouts, or file upload issues.Keywords: openai assistants, assistants api, openai threads, openai runs, code interpreter assistant,file search openai, vector store openai, openai rag, assistant streaming, thread persistence,state

Git workflow patterns for agents. Invoke at session start when working in a git repository, before any git operations (status, add, commit, push, rebase), when making code changes, or when the user asks to commit, create PRs, or manage branches. Covers atomic commits, intentional staging, history restructuring, and safe parallel work patterns.

Web scraping templates, scripts, and patterns for documentation and content collection using Playwright, BeautifulSoup, and Scrapy. Includes rate limiting, error handling, and extraction patterns. Use when scraping documentation, collecting web content, extracting structured data, building RAG knowledge bases, harvesting articles, crawling websites, or when user mentions web scraping, documentation collection, content extraction, Playwright scraping, BeautifulSoup parsing, or Scrapy spiders.

Select appropriate Claude model (Opus 4.5, Sonnet, Haiku) for agents, commands, or Task tool invocations based on task complexity, reasoning depth, and cost/speed requirements.

Builds LLM-powered applications with LangChain.js for chat, agents, and RAG. Use when creating AI applications with chains, memory, tools, and retrieval-augmented generation in JavaScript.

Create custom slash commands for Claude Code. Use when users want to create, modify, or understand slash commands for Claude Code CLI tool. Slash commands are markdown files that define reusable prompts and workflows with custom behavior, parameters, and tool access controls.

Modular orchestration of agent patterns from Anthropic's engineering guide. Intelligently selects and implements prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer, and autonomous agents. Includes pattern combinations and language-specific implementations.

Orchestrates the full development workflow (design → develop → review → QA) using sequential async sub-agents. Use this skill when executing /dev command.

Current state of CI/CD automation infrastructure, pre-built Docker images, and performance optimization strategies. Use when dealing with slow builds, container timeouts, yarn install issues, or when you need to understand available pre-built images and automation tooling.

Use this skill when working with Apple's Foundation Models framework for on-device AI and LLM capabilities in iOS/macOS apps

Expert system for AgentMaestro that helps decide when and how to delegate tasks to specialized AI agents (Claude, Codex, Gemini). Use when you need to determine which agent is best suited for a task, or when a task should be broken down and delegated to multiple agents.

Expert LLC operations management for ID8Labs LLC (Florida single-member LLC). 9 specialized agents providing PhD-level expertise in compliance, tax strategy, asset protection, and business operations. Triggers on keywords like LLC, taxes, expenses, annual report, EIN, compliance, bookkeeping, deductions, filing, sunbiz, quarterly, S-Corp, retirement, audit, insurance, cash flow, mentor, teach, learn.

Query Prometheus metrics, check resource usage, and analyze platform performance in the Kagenti platform

Complete Supabase setup for Mem0 OSS including PostgreSQL schema with pgvector for embeddings, memory_relationships tables for graph memory, RLS policies for user/tenant isolation, performance indexes, connection pooling, and backup/migration strategies. Use when setting up Mem0 with Supabase, configuring OSS memory backend, implementing memory persistence, migrating from Platform to OSS, or when user mentions Mem0 Supabase, memory database, pgvector for Mem0, memory isolation, or Mem0 backup.

Routes to local LLM for sensitive operations. Use when user says "로컬에서 처리해줘", "외부로 보내지 마", "민감한 데이터야", "보안 감사해줘", "credential 분석", "시크릿 확인", or handles sensitive data that should not leave the machine.

Expert on Aptos gas optimization, performance tuning, storage costs, execution efficiency, inline functions, aggregator usage, parallel execution, table vs vector tradeoffs, and gas profiling tools. Triggers on keywords gas optimization, performance, gas cost, storage fee, inline, aggregator, parallel execution, gas profiling, optimization