Analyze, compare, and work with tokenizers using Unsloth tools. Compare different tokenizers, analyze token efficiency, and integrate with Unsloth models. For SuperBPE training, see the 'superbpe' skill.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
Query and analyze W&B experiment data and Weave LLM traces using Python scripts. Use when working with Weights & Biases data, including (1) querying ML experiment runs, metrics, and hyperparameters, (2) analyzing LLM traces and evaluations, (3) creating W&B reports, (4) listing projects and entities.
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.
Simple API for interacting with locally hosted models via vLLM. Use when you need to chat with a model, send messages, or generate responses from a local model server.
Autonomous multi-agent code evolution system for optimization problems. Use when solving complex optimization problems (packing, geometry, scheduling, search) through evolutionary approaches with multiple independent AI agents. Multi-start hybrid heuristic+SLSQP methods significantly outperform single approaches. Triggers include genetic algorithms, evolutionary optimization, multi-agent problem solving, parameter tuning at scale, AlphaEvolve-style research, or evolving code solutions across generations.
Design framework-agnostic AI agents using Oracle's Open Agent Specification for portable, interoperable agentic systems with JSON/YAML definitions
Provides unified interface for all context engineering patterns. Use when optimizing AI agent context: compression, degradation detection, KV-cache optimization, or session management.
This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Google Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.
Craft effective prompts for VEO single-clip video generation - READ before any generate_video_clip call
Managing context window, token optimization, summarization strategies for long conversations.
Best practices for writing Claude Code skills, CLAUDE.md files, and prompts optimized for Opus 4.5. Use when creating or reviewing skills, writing agent instructions, or optimizing prompts for Claude 4.x models.
Vision-Language-Action model integration patterns for cognitive robotics with ROS 2.
Voyager-inspired continuous learning system with Critic Agent, Reflection Agent, and Discord-based approval workflow for skill proposals.
Creates optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce structured outputs for other prompts to consume, or when running multi-stage workflows. Do not use for simple prompts, single-step tasks, or basic conversational AI.
This is an example skill demonstrating the correct SKILL.md format. Use this as a reference when users want to learn how to create skills. Contains all required and recommended sections.
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
ROS 2 node templates and message types for robotics development. Use when creating ROS 2 nodes, understanding message types, or writing publisher/subscriber patterns.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Manages MCP (Model Context Protocol) servers for Claude Code and Claude Desktop. Activates for: finding MCP servers, MCP registries, MCP server setup, MCP configuration, MCP troubleshooting, MCP security, building MCP servers, MCP transport selection, claude mcp commands, mcp.json files, mcpServers configuration, tool poisoning prevention, MCP debugging, Smithery, Glama, GitHub MCP registry, which MCP server should I use. NOT for: general Claude Code settings (use claude-code-mastery), OAuth/authentication unrelated to MCP, generic API integrations without MCP.
Build AI applications on Azure using Azure OpenAI, Cognitive Services, and ML services with enterprise patterns
Guide for LLM security attacks: prompt injection, jailbreaking, data extraction, and where to place resources in README.md.
