Use when delegating tasks to Gemini MCP. Two main use cases: (1) large-scale codebase investigation with @ syntax, (2) web search for latest information. Also for long log analysis, context optimization. Always request concrete report format without omissions or personal opinions.
Retrieve project-specific insights from file-based memory. Use when working on features, encountering domain-specific questions, or user says "--project-recall" or "--recall" (you decide which scope, may use both). Skip for routine tasks or universal pattern questions (use coder-memory-recall). MUST be invoked using Task tool to avoid polluting main context.
Advanced subagent troubleshooting. Use when subagent calls fail, return bad output, or need voting for critical decisions.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Extract information delta between Claude.ai conversation exports using ACSets morphisms and bisimulation verification
Prompt design, optimization, few-shot learning, and chain of thought techniques for LLM applications.
協調多個 AI 模型（ChatGPT、Gemini、Codex、QWEN、Claude）進行三角驗證，確保「Specification == Program == Test」一致性。過濾假警報後輸出報告，大幅減少人工介入時間。
Enterprise Vercel Edge Platform with AI-powered modern deployment, Context7 integration, and intelligent edge orchestration for scalable web applications
Create Claude Code subagents - specialized AI assistants for specific tasks. Use when setting up project workflows or creating task-specific agents.
Guide through updating AI design patterns with comprehensive checklist completion, code examples, images, documentation, and interactive demos
Routing guide for selecting the correct Perplexity tool. Reference before spawning any Perplexity agent.
Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.
Use this if the user wants to connect to Ollama or leverage Ollama in any shape or form inside their project. Guide users integrating Ollama into their projects for local AI inference. Covers installation, connection setup, model management, and API usage for both Python and Node.js. Helps with text generation, chat interfaces, embeddings, streaming responses, and building AI-powered applications using local LLMs.
This skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both platforms with format specifications, best practices, and the ai-eng-system build system.
Document domain knowledge including entities, attributes, relationships, processes, and ubiquitous language. Use when documenting domain models, entity relationships, business processes, or building a glossary of domain terms.
A subagent specialized in creating and managing OpenAI Agents SDK applications, including multi-agent workflows, tools, handoffs, and real-time voice capabilities
Build Telegram bots with modern frameworks. Use when: creating Telegram bot, chatbot, notification bot. Triggers: "telegram", "tg bot", "телеграм бот", "teloxide", "aiogram".
AgentDB integration specialist for RAN ML systems with vector storage, pattern recognition, and distributed training coordination. Achieves 150x faster search, <1ms QUIC sync, and 32x memory reduction for RAN optimization.
[Extends backend-developer] Python FastAPI specialist. Use for FastAPI apps, async endpoints, Pydantic v2, SQLAlchemy async, dependency injection. Invoke alongside backend-developer for Python API projects.
