course-builder
Create educational course content, lesson plans, and workshop materials. Use for building structured learning experiences about AI-assisted development and vibe coding.
Find the perfect capability for your agent.
Create educational course content, lesson plans, and workshop materials. Use for building structured learning experiences about AI-assisted development and vibe coding.
Run GPT-5.2 Codex (gpt-5.2-codex high) via OpenAI Codex CLI to review code for bugs, issues, and architecture problems. Use when the user wants a second opinion on code, requests a code review from an external model, says "ask the oracle", "get codex review", "run oracle", or wants GPT-5.2 to analyze their codebase for issues.
Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns. Use when creating Claude Code extensions or configuring Claude Code features.
Integrate Databricks Genie rooms as tools in agent workflows. Use when integrating Genie spaces with AI agents, querying Genie rooms programmatically via SDK or MCP, managing Genie conversations and polling, handling Genie API responses and errors, or building tool-calling agents that use Genie as a data source. Covers SDK patterns, MCP tool integration, conversation management, error handling, and performance optimization for Genie-based agent tools.
Automatically generate comprehensive AGENTS.md files that teach AI agents how to work with a repository's structure, conventions, and guidelines
AIフィードバックループ最適化スキル。プロンプト→出力→評価→改善の反復サイクルを自動化。段階的改善、A/Bテスト、収束判定、ベスト出力選択で最高品質の結果を生成。
Use when user requests research requiring multiple sources, comprehensive analysis, or synthesis across topics - technical research, domain knowledge gathering, market analysis, or learning about complex subjects
Auto-Claude debugging and troubleshooting guide. Use when fixing installation issues, debugging build failures, resolving agent errors, or diagnosing performance problems.
Use when "RAG", "retrieval augmented generation", "LangChain", "LlamaIndex", "sentence transformers", "embeddings", "document QA", "chatbot with documents", "semantic search"
This skill provides guidance for implementing robust Qdrant vector database integration with RAG (Retrieval Augmented Generation) systems, including proper async client handling, error management, and performance optimization.
Canonical Claude Code skill authoring kit covering agent Skills, sub-agent templates, custom slash commands, orchestration patterns, hooks, memory, settings, and IAM permission rules aligned with official documentation.
Retain and recall work context across sessions. Use when user asks to remember something, recall previous work, or reference past discussions. Triggered by phrases like 'remember this', 'save for later', 'recall', 'what did we discuss about'.
Create and configure Claude Code agents with proper frontmatter, system prompts, and triggering conditions. WHEN: MUST use when creating new Claude Code agents. Invoke with "/claude-agent-creator" or "create an agent", "new Claude agent", "write agent prompt". WHEN NOT: Creating skills (use claude-skill-creator), creating commands (use claude-command-development).
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
Get real-time weather information using web search. Use when user asks about weather, temperature, forecast, or climate conditions for any location. Supports voice input (microphone) and voice output (TTS). By default outputs BOTH text and voice.
Generate images using OpenAI's GPT Image model. Use for creating images from text prompts. Keywords: image, generate, openai, gpt-image, dalle, picture, art, create.
Comprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers project structure, workflow patterns, steps, LLM integration, HTTP clients, and CLI commands.