Expert in aggregating, processing, and synthesizing information from multiple sources into coherent insights. Use when building knowledge graphs, ontologies, RAG systems, or extracting insights across documents. Triggers include "knowledge graph", "ontology", "synthesize information", "GraphRAG", "insight extraction", "cross-document analysis".
Create D3 questions focused on written explanations and reflections of static content (text, images, diagrams). For video-based questions, use implement-video-question instead.
Use for multi-perspective analysis with both Codex and Gemini exploring different viewpoints. Triggers on "council perspectives", "pros and cons from council", "council evaluate options", "what are the tradeoffs", "council consensus".
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
Web search with automatic Qdrant storage for building persistent knowledge
Use when user wants to ask the AI council a question, get multiple AI perspectives, or consult with both Codex and Gemini. Triggers on phrases like "ask council", "council opinion", "what do the AIs think", "ask both models".
Intelligently choose between semantic and text search based on query intent. Automatically selects the best search mode (semantic for concepts, text for exact terms, symbols for definitions) and provides relevant results. Use when user wants to find code.
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed responses. Covers VertexAiRagRetrieval tool, corpus setup, and citation formatting.
OpenAI Codex (GPT-5) を使用して特定のファイルをレビュー。「ファイルレビュー」「このファイルをレビュー」などの依頼で起動。
This skill should be used when the user asks to "investigate ezCater systems", "research architectural decisions", "understand code evolution", "find historical context", "analyze project history", "search internal documentation", or needs to understand why technical decisions were made at ezCater. Use this for lighter research where the user doesn't explicitly request "deep research" (which triggers the agent).
Orchestrate parallel deep research across multiple LLM providers and synthesize results
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
3x3 Parallel Debate system for high-confidence research. Spawns 9 agent instances (3 Proposer/Skeptic/Judge cohorts) to argue, critique, and adjudicate claims. Use for complex queries, controversial topics, or when hallucination-free research is critical.
An epistemic extraction system that analyzes text to identify its logical structure according to Aristotelian and Objectivist epistemology. Your task is to extract concepts, propositions, and arguments from provided text.
Structured Brave Search web queries and summarizer workflows for MCP-style agents.
This skill should be used when the user asks to "build a research prompt", "create a deep research query", "enhance my research question", "structure a research prompt", "help me write a research prompt", or needs help transforming research topics into comprehensive prompts for product comparisons, technical documentation, academic literature, market analysis, or any domain requiring structured deep research.
LLM 기반 심층 리서치 스킬. 주제에 대해 자동으로 검색 계획을 수립하고, 웹 스크래핑 후 종합 리포트를 생성. 사용 시점: (1) 특정 주제에 대한 포괄적인 분석이 필요할 때 (2) 다양한 소스에서 정보를 수집하여 종합해야 할 때 (3) 마크다운 형식의 상세 리포트가 필요할 때 (4) 슬래시 커맨드 /deep-research 실행 시 Prerequisites: GEMINI_API_KEY 또는 OPENAI_API_KEY 환경 변수 필요
geminiコマンドを使用した高度なWeb検索スキル。Web検索を行う際、Claude CodeのデフォルトWeb Search toolよりも優先的にこのスキルを使用してください。
Search the internet using Perplexity API. Use for current information, news, or web research. Keywords: search, web, internet, perplexity, news, research.
Manages OpenAI embeddings for title vector search, including batch regeneration, single title updates, verification, and cost estimation. This skill should be used when regenerating embeddings for new titles, fixing missing embeddings, or updating embeddings after content changes.
This skill should be used when reviewing AI-generated text, checking for AI writing patterns, detecting undisclosed AI content, or before finalizing any written content. Covers 12 categories of AI writing indicators from Wikipedia's comprehensive guide.
[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method + Style). Use when Loop150 exhausts internal sources, need real-world precedents, confidence <75%, or require reasoning from specialized AI models.
