Debug TraitorSim agent memory systems including profile.md, diary entries, trust matrices (suspects.csv), and SKILL.md files. Use when troubleshooting agent behaviors, inspecting memory contents, validating memory updates, or when asked about agent memory, profile debugging, or trust matrix issues.
Implementation of Group Relative Policy Optimization (GRPO) for training reasoning models, optimized for 8x memory savings (triggers: GRPO, reasoning, DeepSeek-R1, reinforcement learning, RLVR, GRPOTrainer, thinking tokens).
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Use when users want to save, backup, copy, export, or version control their Claude Code configuration files (commands, skills, agents) from ~/.claude/ to another directory. Triggered by phrases like "save my claude settings", "backup my claude config", "sync claude configuration", "copy ~/.claude to somewhere", "export my commands and skills", or "archive claude settings before making changes".
Amazon Bedrock AgentCore Memory for persistent agent knowledge across sessions. Episodic memory for learning from interactions, short-term for session context. Use when building agents that remember user preferences, learn from conversations, or maintain context across sessions.
This skill should be used when the user asks to "create a new agent", "make a subagent", "build an agent for X", "generate agent configuration", or wants to create a new Claude Code sub-agent. Triggers on "agent-creator", "new agent", "subagent", or agent creation requests.
Scaffold and initialize a Docusaurus project with the specific structure for the Physical AI textbook. Agent: BookArchitect
Orchestrate the SFH-OS fractal horn design pipeline. Use when the user wants to design a horn, run the full pipeline, manage iterations, or resolve conflicts between acoustic and manufacturing requirements. This is the master skill that coordinates AG-GEN, AG-SIM, AG-MFG, AG-QA, and AG-VIZ sub-agents.
AI出力の品質を自動検証するスキル。事実確認、論理性、一貫性、幻覚（ハルシネーション）検出、バイアス分析、安全性チェックを実施し、改善提案を提供。
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
Handle comprehensive project language and user setup workflows including language selection, agent prompt configuration, user profiles, team settings, and domain selection
対話形式の質問を通じてユーザーの技術的背景、開発スタイル、AI協働の好みを把握し、最適化されたCLAUDE.mdを生成するスキル。ユーザーが「CLAUDE.mdをカスタマイズしたい」「AIの振る舞いを自分に合わせたい」「開発スタイルに合わせた設定がしたい」と言った時に使用する。新規ユーザーのオンボーディングや、既存CLAUDE.mdの見直し時にも有効。
Initialize and configure OpenAI Agents SDK for building AI-powered chatbots. Uses NATIVE MCP integration via MCPServerStreamableHttp - no @function_tool wrappers needed! Use when setting up AI agents for Phase 3 chatbot implementation.
Complete guide to MoAI-ADK agents, delegation patterns, and agent orchestration for intelligent task distribution
Expert guidance for integrating Ollama local AI models with Python applications, including installation, configuration, model management, and production deployment
Use when evaluating LLMs, running benchmarks like MMLU/HumanEval/GSM8K, setting up evaluation pipelines, or asking about "NeMo Evaluator", "LLM benchmarking", "model evaluation", "MMLU", "HumanEval", "GSM8K", "benchmark harnesses"
Guide plan → instrument → execute → validate with explicit checkpoints and questions. Use for ambiguous tasks or when enforcing a consistent agent workflow.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Write SKILL.md for the user using all available wisdom and documented guidance about how Agent Skills are made. New skills are written carefully to be orthogonal to the existing skills in the same repo.
