brave-search
Structured Brave Search web queries and summarizer workflows for MCP-style agents.
investigation-cycle
HAIOS Investigation Cycle for structured research and discovery. Use when starting or resuming an investigation. Guides HYPOTHESIZE->EXPLORE->CONCLUDE workflow with phase-specific tooling.
deep-research-prompt-builder
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.
data-designer
Generate high-quality synthetic datasets using statistical samplers and Claude's native LLM capabilities. Use when users ask to create synthetic data, generate datasets, create fake/mock data, generate test data, training data, or any data generation task. Supports CSV, JSON, JSONL, Parquet output. Adapted from NVIDIA NeMo DataDesigner (Apache 2.0).
ultimate-research
Elite multi-agent research orchestration utilizing ref MCP, exa MCP, brave-search MCP, and context7 with parallel execution of deep-research-agent, search-specialist, trend-researcher, and ux-researcher. Use for comprehensive research requiring maximum depth, breadth, and quality. Automatically invoked during /sc:research commands for world-class research capabilities surpassing any traditional deep research approach.
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
pacer-classifier
Classifies information into PACER categories (Procedural, Analogous, Conceptual, Evidence, Reference) and recommends appropriate digestion protocols. Use when learning new material, studying, reading educational content, processing information for retention, or when user asks about how to study or remember something.
web-search
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。
internet-search
Search the internet using Perplexity API. Use for current information, news, or web research. Keywords: search, web, internet, perplexity, news, research.
regenerate-embeddings
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.
ai-anti-patterns
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.
skillful-latex-creta-researcher
Mine AI research insights and generate professional LaTeX reports for creta.mx (Center for Research on Economics and Technology Applications). Triggers on "CRETA", "research insights", "LaTeX report", or economics/technology documentation requests.
23-understand-ask-ai-150
[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.
deep-research
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
compsci-math
Comprehensive computational mathematics toolkit for Claude Code agents. Provides tools for five core domains from MIT's Mathematics for Computer Science curriculum - Proofs (propositions, predicates, induction, verification), Structures (number theory, graphs, RSA, partial orders), Counting (asymptotics, combinatorics, generating functions), Probability (distributions, Bayes, random walks, bounds), and Recurrences (divide-and-conquer, Master theorem, Akra-Bazzi). Use when solving algorithm analysis, proving correctness, computing probabilities, analyzing complexity, or working with discrete mathematical structures. Implemented in Python with TypeScript tool definitions for Claude Code integration.
blog-trend-researcher
Researches topics and trends for blog content with parallel multi-agent execution. USE WHEN orchestrator invokes research phase OR user says 'research topic', 'find trends', 'gather information for blog'.
rag-optimization
RAG 파이프라인 최적화 스킬. 검색 품질, 리랭킹, 쿼리 확장, 하이브리드 검색 관련 작업에서 자동으로 활성화됩니다. retrieval, rerank, embedding, vector search, semantic search 키워드에 반응합니다.
cass-memory
Cross-agent learning with cm (cass-memory). Use before starting non-trivial tasks, when looking for patterns from past work, when the user mentions "cm", "memory", "learned rules", or "what do we know about".
research-router
Routes research and investigation tasks. Triggers on research, investigate, deep-dive, explore, understand, learn, study, compare, thorough, comprehensive.
rag-retrieval
Hybrid search (embedding + BM25) for retrieving relevant clinical note passages. Use for finding source evidence to support claims in summaries and recommendations.
aiproofing-text
Analyzes narrative text and files to identify and remove AI-generated signals while preserving authentic voice and style. Runs input through comprehensive protocols covering vocabulary, syntax, character voice, emotional depth, and readability. Use this skill when you need to proof narrative content against AI detection patterns or humanize AI-assisted writing.
