Integration patterns for web search grounding, including query operator usage, API-based search orchestration, and citation metadata mapping. Triggers: google-search, grounding, search-api, citations, search-operators, web-search.
LLM evaluation and prompt optimization with Evidently.ai. Covers text descriptors, dataset metrics, LLM-as-a-Judge patterns, and automated prompt optimization for classification and generation tasks.
Rapid topic mastery for video/content prep. Takes a topic → generates 5 research questions → parallel PubMed + web search → outputs McKinsey-style brief in 5 minutes. Use BEFORE recording videos or writing content.
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。
This skill should be used when the user asks "what evals can we create", "how do I evaluate this", "design an eval", "create evals for", "how do I know if my LLM is working", "measure quality", or mentions evals, evaluation, scoring rubrics, golden datasets, LLM-as-judge, quality metrics, or judge prompts.
Example skill providing background knowledge and context
Intelligent memory search with automatic method selection. Supports semantic (vector), keyword, and recent queries. Includes fallback strategies and optional summary inclusion.
Leverages the multiple CLIs including PEX, pdf-search, hge, researcher, limitless, pieces, screenapp and more, to extract all relevant LOs across both CICM and ANZCA PEX exams, cross reference them with past SAQ questions, extract examiner comments, cross reference this with recommended textbooks via pdf-search, generate a hypergraph using hge, validate insights with researcher, evaluate against pkm using limitless and pieces, and look for additional context to add polish with screenapp and others. Then leverages the PEX and SAQ skill, as well as the metaskills that exist in .claudeate a scaffolding for a modular, programmatic, state of the art skill that integrates quantitative physiological parameters using the qp skill, teleologically grounded framing using the physiology-style and telos skill and follows all of the principles of the code, mega, and agency skills. Finally it should be recursively optimised with the abduct, critique and refactoring agent skillls. Ergo, this skill makes SOTA PEX LO skills.
Call OpenAI Codex CLI for tasks. Use when user wants to ask Codex, get GPT's opinion, get a second opinion, compare with OpenAI, have Codex review something, or let Codex perform a task.
Orchestrate comprehensive 7-phase RBMAS research for multi-dimensional queries (4+ dimensions). Coordinates multiple specialist agents through SCOPE → PLAN → RETRIEVE → TRIANGULATE → DRAFT → CRITIQUE → PACKAGE methodology. Use for thorough internet research requiring multiple sources, iterative refinement, and quality gates. Triggers - research, investigate, analyze with 4+ distinct dimensions or comprehensive depth requirements.
Run OpenAI Codex CLI reviews from Claude Code. Use when the user asks for a Codex review or mentions triggers like "codex-review", "/codex-review", or "codex review".
Extract entities and concepts from documents using HAIOS memory system. Use when ingesting new documents, analyzing content structure, or populating the knowledge base.
Research external topics, create comprehensive analysis, determine project applicability, and incorporate learnings into Brain memory system. Transforms knowledge into searchable, actionable project context.
Search RAG database for relevant content. Use for semantic queries over processed documents, code, or papers.
Synthesizes lesion data and historical cases into a comprehensive risk profile using WebLLM SmolLM2
Personalize textbook chapter content for logged-in users based on their background, preferences, and learning style collected during signup.
Research voids (cognitive gaps, unchartable territories). Daily. Outputs research notes for voids articles.
Evidence-based learning and study skill for deep, durable understanding. Triggers when users want to learn or understand a topic, ask to be quizzed or tested, use phrases like "I'm studying [topic]", "help me learn [topic]", "quiz me on [topic]", or provide course materials/textbook references for learning purposes. Implements retrieval practice, desirable difficulties, elaboration, and Socratic questioning rather than giving direct answers.
Research-driven investigation skill for validating solutions and exploring documentation. Never ask questions you can answer yourself through research. Use WebFetch, WebSearch, and testing to validate ideas before presenting them. Deliver concrete, tested recommendations with evidence.
Comprehensive research and synthesis agent specializing in multi-source information gathering, critical analysis, and integrated knowledge synthesis. Excels at complex research projects requiring systematic investigation across domains, evidence evaluation, and coherent narrative construction.
