LLM & Agents

Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.

Automatically check available scripts and tools before creating new ones. Use this when you need to execute bash, python, or npm scripts to avoid duplicating existing tools. This skill lists all tools in .claude/scripts/ and helps you discover reusable scripts.

Complete full-stack development with Next.js 13+, React, Firebase, Tailwind CSS, and payment integration (Stripe, JazzCash, EasyPaisa). Build production-ready e-commerce platforms, SaaS applications, and scalable web applications. Comprehensive coverage of frontend architecture, backend API routes, database design, authentication systems, payment processing, form handling, error management, and optimization. Generate complete project structures, pages, components, API routes, database schemas, security rules, and deployment configurations using TypeScript.

This skill provides comprehensive knowledge for integrating Vercel KV (Redis-compatible key-value storage powered by Upstash) into Vercel applications. It should be used when setting up Vercel KV for Next.js applications, implementing caching patterns, managing sessions, or handling rate limiting in edge and serverless functions. Use this skill when: - Setting up Vercel KV for Next.js applications - Implementing caching strategies (page cache, API cache, data cache) - Managing user sessions or authentication tokens in serverless environments - Building rate limiting for APIs or features - Storing temporary data with TTL (time-to-live) - Migrating from Cloudflare KV to Vercel KV - Encountering errors like "KV_REST_API_URL not set", "rate limit exceeded", or "JSON serialization errors" - Need Redis-compatible API with strong consistency (vs eventual consistency) Keywords: vercel kv, @vercel/kv, vercel redis, upstash vercel, kv vercel, redis vercel edge, key-value vercel, vercel cache, vercel sessions, vercel rate limit, redis upstash, kv storage, edge kv, serverless redis, vercel ttl, vercel expire, kv typescript, next.js kv, server actions kv, edge runtime kv

Troubleshoot GCP services using tool-first access (via MCP when available), falling back to the CLI only when necessary. Focus on Firestore, Cloud Run, networking, load balancers, IAM, Pub/Sub, Cloud SQL, and Storage.

Explore AMPECO Public API endpoints, schemas, and develop integrations with the EV charging platform. Use for API exploration, building integrations, or understanding available endpoints. Trigger keywords: "ampeco api", "public api", "ev charging api", "ampeco integration"

Automated test generation, review, and execution for pytest-based projects. Auto-activates on keywords test, coverage, pytest, unittest, integration test, e2e, performance, benchmark, security testing. Routes to specialized testing workflows based on user intent.

Execute Gemini CLI commands for AI-powered coding assistance, file analysis, and complex development tasks. Use when user wants to run gemini commands, query Gemini models, or leverage Gemini's agentic capabilities.

Comprehensive Supabase expert with access to 2,616 official documentation files covering PostgreSQL database, authentication, real-time subscriptions, storage, edge functions, vector embeddings, and all platform features. Invoke when user mentions Supabase, PostgreSQL, database, auth, real-time, storage, edge functions, backend-as-a-service, or pgvector.

Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples

Run repo startup: prompt load, checklist sync, optional PR triage, worktree hygiene, and CI pull. Best-effort with structured status.

Agent Skills 통합 워크플로우를 자동으로 관리하고 조율합니다. 사용자 요청을 분석하여 Router, Sequential, Parallel, Orchestrator, Evaluator를 자동으로 순차 호출하며, 전체 프로세스를 모니터링하고 진행 상황을 리포팅합니다.

Apply Anthropic's production multi-agent research patterns for complex research tasks. Use when research involves multiple independent dimensions, requires synthesis across many sources, or needs parallelization for speed. Includes query complexity assessment, parallel execution, progressive search refinement, thinking strategies, and findings compression.

Expert guide for crafting high-performance Claude prompts, based on Anthropic's interactive tutorial.

Claude技能质量检查器,自动验证技能是否符合官方最佳实践标准。Use when 创建新技能需要验证规范、 修改现有技能需要质量检查、从他人处获取技能需要评估质量、批量检查多个技能的合规性。 适用于: (1) 新技能开发后的质量验证 (2) 技能更新后的合规检查 (3) 第三方技能的质量评估 (4) 团队技能库的标准化管理 (5) 技能打包前的最终审核

Automatically applies when building LLM applications. Ensures proper async patterns for LLM calls, streaming responses, token management, retry logic, and error handling.

Autonomous patent application drafting agent. Drafts complete patent applications including claims, specification, and abstract from invention descriptions.

Master Supabase patterns for migrations, RLS policies, pgvector, and authentication. Use when creating database schemas, writing migrations, implementing row-level security, setting up auth, or debugging Supabase issues. Triggers on "supabase migration", "RLS policy", "row level security", "pgvector", "supabase auth", "magic link".

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Create and maintain well-structured Claude Code skills. Use when creating, updating, or improving skills in .claude/skills/.