arog-ai-assistance
Configure and optimize AI assistance (Copilot, agents, skills) for AROG development. Use when users ask about Copilot, custom agents, or AI integration.
Configure and optimize AI assistance (Copilot, agents, skills) for AROG development. Use when users ask about Copilot, custom agents, or AI integration.
Browser Controller拡張機能を使ってChatGPT 5.2 Thinkingで3並列以上のウェブ検索・ブレスト・情報収集を実行する。難問にはHeavy thinking(heavy/extended)を使用。指定時のみChatGPT Proで深い考察・ファクトチェック。マルチターン継続(chat)、再取得(recover)、ファイル添付、タブ管理にも対応。「ウェブ検索」「横断検索」「並列検索」「ブレスト」「情報収集」「リサーチ」「再取得」「追加質問」を依頼されたときに使用する。
Azure OpenAI expert for deployments, authentication, and best practices. Use when asked about Azure OpenAI configuration or troubleshooting.
Initialize a new feature area for exploration and decision-making. Use when user says "create feature {feature-name}" or "new feature {feature-name}". Creates folder structure with readme.md and investigations directory.
Configure Claude Code GitHub Actions workflows effectively. Covers automatic mode detection, event routing, subagent coordination, hooks for quality gates, MCP server integration, reusable workflows, performance optimization, and security best practices for fork-based PRs. Use when working with GitHub Actions, CI/CD automation, PR reviews, issue automation, claude-code-action, chatops, MCP servers, fork safety, or reusable workflows.
Use this skill whenever the user mentions a skill or is creating/updating/reviewing SKILL.md or any file under skills (any language); ALWAYS read this SKILL.md first and treat it as the authoritative instructions for the session.
LLMアプリケーションの設計・運用・評価・最適化。プロンプト管理、RAG構築、ファインチューニング、評価パイプライン、コスト最適化、本番運用。「LLM」「プロンプト」「RAG」「ファインチューニング」「AI運用」「評価」に関する質問で使用。
Research solutions, algorithms, and best practices from the SurrealDB GraphRAG knowledge base containing 600+ scientific papers, StackOverflow answers, and GitHub repositories.
Build enterprise RAG solutions using Foundry IQ with Azure AI Search agentic retrieval. Use when implementing policy assistants, knowledge bases with citations, or multi-hop question answering systems.
This skill should be used when the user asks about "AI development", "AI coding", "AI assistant", "CLAUDE.md", "AI context", "AI guidelines", "code generation", "AI workflow", "AI review", "AI configuration", or needs guidance on configuring AI assistants and AI-assisted development workflows.
Unified Memory Contract for Flowbaby integration. Defines when and how to retrieve and store memory. Load at session start - memory is core to agent reasoning, not optional.
Generate custom GitHub Copilot agents (.agent.md files) for VS Code with proper YAML frontmatter, tools configuration, and handoff workflows. Use when "create copilot agent", "generate github copilot agent", "new copilot agent for", "make a copilot agent", or "build copilot agent".
Brief description of when Copilot should use this skill (e.g., "Use this for database migrations").
AI agent specialist for Faiston NEXO. Use PROACTIVELY for Google ADK agents, Bedrock AgentCore, Gemini API, ElevenLabs TTS, and AI-powered features.
Creates, refines, ingests, and evaluates agent skills using archetype-driven design. Use when building skills from scratch, extracting knowledge from documentation, or auditing skill quality. Do not use for non-skill related tasks or when other specialized skills are more appropriate.
Add AI model authentication to any project. Supports GitHub Copilot, Anthropic, OpenAI, OpenRouter, AWS Bedrock, Google Vertex, Cloudflare, and 50+ OpenAI-compatible providers. Uses OpenCode's proven 5-tier auth priority system (env vars, stored credentials, config files, OAuth plugins, public keys). Enables users to leverage their existing paid services without new API keys.
A tiered approach to answering research questions with clear stop rules, evidence capture, and escalation to Tavily/Playwright only when needed.
Activate when users ask about Claude Code installation, slash commands (/cook, /plan, /fix, /test, /docs, /design, /git), creating/managing Agent Skills, configuring MCP servers, setting up hooks/plugins, IDE integration (VS Code, JetBrains), CI/CD workflows, enterprise deployment (SSO, RBAC, sandboxing), troubleshooting authentication/performance issues, or advanced features (extended thinking, caching, checkpointing).