function-calling-agent
OpenAI/Gemini Function Calling을 활용한 에이전트 구현 가이드. LLM이 외부 API를 Tool로 호출하는 패턴. "function calling", "tool", "agent", "openai tools", "gemini tools" 키워드로 트리거.
Essential command-line tools and system utilities.
OpenAI/Gemini Function Calling을 활용한 에이전트 구현 가이드. LLM이 외부 API를 Tool로 호출하는 패턴. "function calling", "tool", "agent", "openai tools", "gemini tools" 키워드로 트리거.
AI agent with tools (search, calculator) using LangGraph and AI SDK.
DevOps engineer for serverless AI on Cloudflare Workers. Use when deploying AI endpoints or configuring Workers.
Professional engineering skill combining senior engineer thinking patterns, adaptive task assessment, and Google-grade standards. Invoke with /pro before any coding task to ensure production-quality work with proper planning, testing, and verification.
OpenRouter framework integration templates for Vercel AI SDK, LangChain, and OpenAI SDK. Use when integrating OpenRouter with frameworks, setting up AI providers, building chat applications, implementing streaming responses, or when user mentions Vercel AI SDK, LangChain, OpenAI SDK, framework integration, or provider setup.
Guide for using and supporting the AGENTS.md standard in VS Code. Use this when asked about AGENTS.md, custom instructions, or repo-level AI agent configuration.
Configure Nexus memory with your role, goals, and preferences. Load when user wants to personalize the system or teach Nexus about themselves. Keywords: setup memory, personalize, configure, my goals, my role, about me, preferences. 8 min.
Authoring CLAUDE.md Project Instructions. Design project-specific AI guidance, document workflows, define architecture patterns. Use when creating CLAUDE.md files for projects, documenting team standards, or establishing AI collaboration guidelines.
Create semantik plugins (connectors, embeddings, chunkers, rerankers, extractors, agents). Use when developing plugins, creating new integrations, or asking about plugin patterns, protocols, or testing.
Meta-skill that creates new skills. Use when user repeatedly explains the same workflow, or mentions "save this as a skill", "remember this process", or "create a skill for this".
Configure and optimize AI assistance (Copilot, agents, skills) for AROG development. Use when users ask about Copilot, custom agents, or AI integration.
Triangulates knowledge gaps from recent Claude Code chat history, searches for resources to fill them, reports back.
Practical workflows, context engineering strategies, and real-world execution examples for MoAI-ADK. Use when learning workflow patterns, optimizing context management, debugging issues, or implementing features end-to-end.
Multi-agent coordination CLI for codebases. Use when orchestrating parallel agents, claiming tasks, detecting symbol conflicts, or notifying stakeholders of breaking changes. Invoke when user mentions coordination, parallel agents, multiple agents, task claiming, or conflict detection.
Interactive MVP building adventure with a companion character. Guides non-technical founders through building their app via conversational choices. Feels like Lifeline - a character helps you solve problems together. Phases: (1) Refine the idea, (2) Set up codebase, (3) Build the app, (4) Style it, (5) Deploy. Use when: User wants to build an app, says "/start", asks "help me build", wants guidance building something, or mentions "vibe coding". Triggers: /start, /status, /next, /level, /save, /help, "help me build", "what should I build", "I want to create"
Invoke OpenAI Codex CLI with the correct configuration for autonomous code generation. Use when you need Codex to generate or regenerate code files, implement features, or execute multi-step coding tasks.
Debug and trace MachinaMed medical agent errors in GKE environments. Use for investigating agent failures, tracing invocations, analyzing MALFORMED_FUNCTION_CALL errors, and generating comprehensive error reports from agent-trace.log files.
Azure OpenAI expert for deployments, authentication, and best practices. Use when asked about Azure OpenAI configuration or troubleshooting.
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses. This is a test.
Orchestrates the async development workflow (design → develop → review → QA). Handles phase transitions when triggered by workflow-continue hook.