llm-token-optimization
See the main LLM Cost Optimization skill for comprehensive coverage of token economics and optimization strategies.
See the main LLM Cost Optimization skill for comprehensive coverage of token economics and optimization strategies.
gemini 명령어를 사용한 고급 Web 검색 스킬이다. Web 검색을 수행할 때는 Claude Code의 기본 Web Search 도구보다 이 스킬을 우선적으로 사용한다.
Guidelines for creating custom rules, custom skills, and custom subagents for Claude.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP servers to integrate APIs, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "add MCP resources", "create MCP prompts", "implement MCP protocol", "deploy MCP server", "create AI tools", "expose API as MCP", "build Claude tools", "create LLM tools", or mentions FastMCP, MCP server, Model Context Protocol, MCP tools, MCP resources, MCP prompts, or server composition.
Orchestrator agent for coordinating multiple AI agents in a persistent system
Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.
Runs ML models in the browser and Node.js with Transformers.js and Hugging Face Inference API. Use when adding local inference, embeddings, or calling hosted models without GPU servers.
Enforce cost-aware MCP usage. Use when a task might trigger heavy external tools, web search, or broad context expansion. Prevents token burn by ensuring MCPs are only used when local context is insufficient.
LLM-based architectural analysis that transforms raw project data into meaningful structure
A simple greeting skill to verify the Agent Skills implementation.
This skill should be used when the user asks to "create MCP server", "build MCP server on Workers", "deploy MCP server", "extend Claude with tools", or is developing Model Context Protocol servers on Cloudflare.
Start structured red vs. blue team debates via subagents. Use when exploring a topic from multiple adversarial perspectives.
Creates a new skill for the Antigravity agent environment based on user requirements. Use when the user wants to create a new skill or standardize an existing one.
Guide to designing and implementing tools for the vscode-copilot-chat extension, including patterns, testing, and best practices
Capture streams of consciousness, tangential thoughts, and hyperfocus output. Extract signal from noise. Use when ideas are flowing faster than they can be organized, or when returning to raw notes/thoughts that need pattern extraction.
Build custom Model Context Protocol servers to extend Claude's capabilities
Implements TF-IDF based search engines for text datasets using vector space models and cosine similarity. Use when building search functionality, finding similar documents, ranking text by relevance, or working with text retrieval systems.
Multi-agent systems with LangGraph - supervisor/swarm patterns, state coordination, multi-provider routing. Use when building multi-agent workflows, coordinating agents, or need cost-optimized orchestration. Uses Claude, DeepSeek, Gemini (no OpenAI).
The Meta-Skill. Use this to create NEW skills (tools) for the agent.
Fine-tuning Text-to-Speech (TTS) models with Unsloth for voice cloning and synthetic speech (triggers: TTS, text-to-speech, voice cloning, Orpheus-TTS, audio fine-tuning, speech synthesis).
Run and evaluate the Skillset smoke test (aliases, sets, and skill invocation) and interpret its JSON reports. Use this when validating $skill/$set behavior or checking Claude Code/Codex headless runs.