Agent Skills Hub

claude

Anthropic Claude AI models for high-performance coding, large-context analysis, and GUI interaction.

spec-to-code-compliance

Verifies blockchain smart contract code against technical specifications, whitepapers, and design documents to ensure exact implementation compliance.

ai-llm-patterns

Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.

prompt-engineering-patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production applications.

exa

Neural web search and code context retrieval via Exa AI. Ideal for documentation, technical research, code examples, and company intelligence.

math-extractor

Extracts mathematical content like definitions, theorems, and proofs from documents (PDF, MD, TEX, TXT) using AI-based cleaning and conversion.

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.

deepwiki

Search and retrieve AI-generated documentation, architecture guides, and API references for 300+ popular GitHub repositories using DeepWiki and MCP.

zotero-mcp-code

Efficiently search your Zotero library using Python code execution. Enables comprehensive multi-strategy queries, automated deduplication, and relevance ranking without context overflow or system crashes.

web-search-patterns

Advanced Gemini-powered web search plugin with smart caching, subagent context isolation, and automated query optimization.

personal-brand-agent

Autonomous multi-agent LinkedIn system using LangGraph and Claude Opus 4.5 for trend research, content creation, voice profiling, and analytics-driven optimization.

deepwiki-rs

AI-powered documentation engine that automatically generates C4 architecture diagrams, technical specs, and codebase analysis from any source code directory.