📖Knowledge Base Skills
Browse the best Knowledge Base skills for Claude Code, Codex, Cursor and other AI agents.
748 skills · Page 2 of 32
obsidian-vault-manager
★ 5Manage Obsidian knowledge base - capture ideas, YouTube videos, articles, repositories, create study guides, and publish to GitHub Pages. Use smart AI tagging for automatic organization.
ollama-rag
★ 5Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Covers LangChain, LlamaIndex, ChromaDB, and embedding models.
recursive-knowledge
★ 2Process large document corpora (1000+ docs, millions of tokens) through knowledge graph construction and stateful multi-hop reasoning. Use when (1) User provides a large corpus exceeding context limits, (2) Questions require connections across multiple documents, (3) Multi-hop reasoning needed for complex queries, (4) User wants persistent queryable knowledge from documents. Replaces brute-force document stuffing with intelligent graph traversal.
moai-workflow-jit-docs
★ 1Enhanced Just-In-Time document loading system that intelligently discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation, when working with new technologies, when answering domain-specific questions, or when context indicates documentation gaps.
think
★ 1多视角思考框架。当用户说"帮我想想"、"分析一下这个问题"、"/think"时触发。用不同职业的思维模式作为工具，从多个角度分析问题，避免单一视角盲区。基于查理·芒格的多元心智模型理念 + 马斯克的第一性原理。
sicp
★ 1SICP: Structure and Interpretation of Computer Programs - computational processes, abstraction, and metalinguistic design
rag-expert
★ 1Expert in Retrieval-Augmented Generation systems - knowledge bases, chunking strategies, embedding optimization, and production RAG architectures
querying-logseq-data
★ 1Expert in building Datalog queries for Logseq DB graphs. Auto-invokes when users need help writing Logseq queries, understanding Datalog syntax, optimizing query performance, or working with the Datascript query engine. Covers advanced query patterns, pull syntax, aggregations, and DB-specific query techniques.
data-ai-guide
★ 1Comprehensive data science, machine learning, and AI guide covering Python, deep learning, NLP, LLMs, prompt engineering, and MLOps. Use when building AI models, data pipelines, or machine learning systems.
nia
Use Nia MCP server for external documentation, GitHub repos, package source code, and research. Invoke when needing to index/search remote codebases, fetch library docs, explore packages, or do web research.
rag-pipeline-builder
Build retrieval-augmented generation systems that ground LLM responses in your data
graphrag
Comprehensive skill for Microsoft GraphRAG - modular graph-based RAG system for reasoning over private datasets
rag-systems
Retrieval-Augmented Generation - chunking strategies, embedding, vector search, hybrid retrieval, reranking, query transformation. Use when building RAG pipelines, knowledge bases, or context-augmented applications.
reflect
Perform reflection after completing work to capture learnings in KB.Ensures knowledge is preserved for future sessions.WHEN TO USE:- After completing a ticket (before archiving)- After completing a phase- Before session ends (user says "wrapping up", "stopping for now")- When user says "reflect", "capture learnings", "what did we learn"CAPTURES:- Patterns: problems solved (resolved) OR issues found (open)- Decisions: architectural/design choices made- Code flows: new understanding of codebase- Procedures: repetitive tasks worth documenting- Learnings: in ticket's 5-final.md
obsidian-vault
Integrate with Obsidian vaults through the Local REST API plugin.Use this skill when the user wants to:- Search notes in their Obsidian vault- Read specific notes- Create new notes- Modify existing notes- Manage daily/periodic notes- Execute Dataview queriesIMPORTANT: This skill performs destructive operations (create, modify, delete).Always follow safety rules and confirmation requirements.Activates when user mentions:- "Obsidian", "my vault", "my notes"- "daily note", "journal entry"- "search my notes", "find in Obsidian"- Creating, updating, or deleting notes
llamaindex-wolfram-alpha
LlamaIndex Wolfram Alpha tool for computational knowledge queries, math solving, scientific calculations, and agent integration. Triggers: wolfram alpha, computational query, math solver, scientific calculation, WolframAlphaToolSpec.
backend-rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search in FastAPI backends. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
obsidian-vault-manager
Manage Obsidian knowledge base - capture ideas, YouTube videos, articles, repositories, create study guides, and publish to GitHub Pages. Use smart AI tagging for automatic organization.
hippocampus
Search hippocampus knowledge base for documentation, conventions, patterns, and how-to guides (discovery: requirements-clarity). Evaluate at requirements-clarity when user asks "how do I...", "find my...", "what's my convention for...", "continue working on...", or wants to create/edit persistent documentation. All markdown files must go to hippocampus - none created elsewhere.
claude-code-docs-search
Search local Claude Code documentation to answer implementation questions. Use when asked about Claude Code features, subagents, workflows, skills, hooks, MCP servers, plugins, settings, CLI options, headless mode, or any Claude Code capability.
ollama-rag
Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Covers LangChain, LlamaIndex, ChromaDB, and embedding models.
round-table-analysis
Deep pre-execution analysis framework using four philosophers (Socrates, Aristotle, Feynman, Drucker) for structured critical thinking before implementing plans. Use when users need to thoroughly understand a topic, question assumptions, clarify objectives, or explore multiple perspectives before taking action. Triggered by phrases like "help me think through," "analyze this topic," "before we start," "I want to understand," or when complex decisions require deeper exploration.
verdad-canon
Validador de coherencia canónica - garantiza que afirmaciones sobre SyV son verdaderas en el universo, ejecutando cambios automáticos moderados para asegurar consistencia narrativa
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that intelligently discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation, when working with new technologies, when answering domain-specific questions, or when context indicates documentation gaps.