This skill should be used when configuring, installing, or managing MCP (Model Context Protocol) servers in Claude Code. Use when users need to connect Claude Code to external tools, databases, APIs, or services through MCP integration.
LMQL constraint-guided generation DSL for type-safe prompting with grammar constraints and logical conditions. Use when building structured LLM outputs with guaranteed format compliance, implementing constrained decoding with logical operators, creating type-safe prompt templates, or combining neural generation with symbolic constraints for reliable AI outputs.
Training manager for RunPod GPU instances - configure pods, launch training, monitor progress, retrieve checkpoints
Validate datasets for Unsloth fine-tuning. Use when the user wants to check a dataset, analyze tokens, calculate Chinchilla optimality, or prepare data for training.
Execute work session initialization routine at conversation start. Identifies new skills, researches improvements for existing skills, and updates skill library. Triggers automatically at session start.
OpenProse is a programming language for AI sessions. An AI session is a Turing-complete computer; OpenProse structures English into unambiguous control flow. OpenHands-Tab integration: - This repo vendors the OpenProse VM docs as your Skill. - When you see a `.prose` program, use `prose.md` for execution semantics and `docs.md` for syntax/validation. Activate when: running `.prose` files, mentioning OpenProse, or when a task is best expressed as an orchestrated multi-agent workflow.
Generate Unsloth training notebooks and scripts. Use when the user wants to create a training notebook, configure fine-tuning parameters, or set up SFT/DPO/GRPO training.
Guidance for selecting appropriate AI model (sonnet vs haiku) based on task complexity, reasoning requirements, and performance needs. Use when implementing agents or justifying model selection.
Get a specific vector entry by key. Requires authentication. Use for Agentuity cloud platform operations
Use the Gemini CLI to search the web for current information. Use this skill whenever the user explicitly asks to "ask gemini" or wants to query Gemini with web search capabilities.
実在する専門家の思想をエージェントに移植し、その専門性と思考パターンを再現するスキル。 Anchors: • 『心の社会』（Marvin Minsky） / 適用: 複雑系とエージェントシステム / 目的: 小規模エージェントの集合知実現 • 『ファスト&スロー』（Daniel Kahneman） / 適用: 意思決定と思考パターン / 目的: 専門家の直感と論理の統合 Trigger: Use when designing or improving agent personas, modeling expert thinking patterns, upgrading existing personas, or building multi-persona systems. persona design, expert modeling, thinking patterns, agent architecture, multi-agent systems
This skill should be used when conducting structured multi-perspective debates to stress-test ideas, evaluate tradeoffs, or reach well-reasoned decisions. Provides the Socratic debate framework with 4 subagent roles.
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
Keyword-based automatic skill detection and activation system for Claude conversations
Coordinate Holo output formatting and telemetry so 0102, Qwen, and Gemma receive exactly what they need.
Create a new Claude Code agent with proper YAML frontmatter structure. Use when the user wants to add a specialized agent to a plugin. Handles agent file creation with name, description, tools, model selection, and color configuration.
Compact the conversation context by summarizing what was accomplished and updating CLAUDE.md with any learnings. Use when context is getting long or when transitioning between work sessions.
LLM4S Scala functional LLM interfaces with Effect system integration. Use when building LLM applications in Scala with ZIO or Cats Effect, implementing type-safe AI pipelines with functional error handling, creating composable prompt systems in Scala, or leveraging Scala's type system for robust AI applications.
Create and manage reusable agent skills with proper structure and frontmatter
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
AI agent development standards including frontmatter structure, naming conventions, tool access patterns, model selection, and Bash-only file operations for .claude/ folders
Execute implementation tasks with different approaches (single, dual-agent, plan-based).
