Update an existing skill based on troubleshooting or improvements discovered during usage. Use when user asks to "update a skill", "improve the skill", "fix the skill instructions", or after resolving issues with a skill execution.
Expert guidance for creating effective Claude Code agents (subagents). Use when users want to create a new agent, update an existing agent, or learn agent design best practices. Covers agent architecture, prompt engineering, tool selection, model choice, and common pitfalls. Integrates with skill-creator when agent needs accompanying skills.
Creates and configures Streamable HTTP Model Context Protocol (MCP) server connections for OpenAI Agents SDK
Expert guidance for building AI agents with Agno framework, including multi-agent systems, reasoning agents, tools integration, memory, knowledge, and production deployment
Coordinate all subagents in the Physical AI & Humanoid Robotics textbook project. Assign tasks, validate outputs, and track progress to determine eligibility for extra points and reusable intelligence.
TOON format knowledge and usage patterns for agent communication and memory persistence in plan-marshall marketplace
Unified router for reasoning, research, and analysis tasks. Consolidates reasoning-router + research-router + analysis-router.
Google python-genai SDK for Gemini 3 Flash, Gemini 3 Pro, and Gemini models. Use when building with Google's Gemini API, google-genai, implementing thinking/reasoning, structured outputs, function calling, image generation, or multimodal. Triggers on "gemini", "google ai", "genai".
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
iOS speech recognition implementation using @react-native-voice/voice. Use when debugging transcription issues, modifying session handling, or understanding the accumulated text tracking mechanism.
Patterns for wrapping any agent with RAG context from Qdrant. Use to add persistent memory to imported or external agents.
This skill should be used when integrating OpenAI Agents SDK with FastAPI, building message arrays from database history, running agents with MCP tools, parsing tool calls, executing them, and saving conversations to the database.
PCE (Process-Context Engine) のアクティブコンテキスト構築スキル。タスクに最適化されたコンテキストをコンパイルし、プロセス駆動の投入物を生成する。 トリガー条件: - 新しいタスクを開始する時（「この機能を実装して」） - AIにコード生成を依頼する時 - 複雑な問題解決に着手する時 - 「コンテキストを整理して」 - 「必要な情報をまとめて」
Add selection-based Q&A functionality to ChatKit UI allowing users to ask about highlighted text with proper integration.
Use when the user asks for a plan or the task is complex/ambiguous. Enforces AGENTS.md workflow and encourages loading other relevant skills.
Generates a static MOVA AI bootstrap pack for a target model/environment (no LLM calls). Input: env.mova_ai_bootstrap_generate_v1, output: ds.mova_ai_bootstrap_pack_v1.
Create new Claude skills following Anthropic best practices. Use when building specialized agent capabilities, packaging procedural knowledge, or extending Claude's domain expertise.
Use for LangGraph agent design and refactors. Prefer explicit state, small nodes, and clear transitions.
AI agent long-term memory management skill (openmemory-py based). Store and retrieve conversation context, user preferences, and important information via semantic search. Note: Automatic context management is handled by the context-manager plugin. This skill is used when the agent **explicitly** manipulates memory. When to use: (1) When user requests memory save/retrieve → /memory add, /memory query (2) When agent determines additional context is needed → /memory query (3) When deleting unnecessary memories → /memory delete
Two-phase reasoning paradigm that reduces hallucinations and constraint violations in complex planning tasks. Use when tasks involve multi-step planning, constraint satisfaction, resource allocatio...
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).
