Agent Skills Hub

memory-systems

Guides agent memory system implementation, compares frameworks (Mem0, Zep, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention.

text-to-sql

Convert natural language queries to safe, optimized SQL. Automates database interactions with schema awareness and parameterized query generation.

orchestrator

Autonomous multi-agent orchestration framework for Claude Code with memory-driven workflows, parallel-first task execution, Aristotle-based deconstruction, and multi-stage quality gates.

code-formatter

Universal CLI tool to convert and synchronize AI agent skills between Claude Code and Gemini CLI extensions.

market-debrief-cn

A deep analysis tool for A-share markets generating interactive, FT-style HTML daily reports using multi-agent parallel architecture, AkShare data, and Tavily news.

qmd

Local hybrid search engine for markdown notes, documentation, and codebase knowledge bases to reduce token consumption and improve retrieval efficiency.

context-fundamentals

Foundational guidelines for context engineering: optimizing token budgets, attention mechanics, and system architecture for AI agents.

trulens-evaluation-workflow

A systematic workflow to instrument, evaluate, and monitor LLM applications using TruLens, supporting frameworks like LangChain, LangGraph, and LlamaIndex.

scientific-writing

Draft and format scientific manuscripts using IMRAD structure, major citation styles (APA, AMA, Vancouver), and standardized reporting guidelines (CONSORT, STROBE, PRISMA).

markdown-token-optimizer

Analyzes markdown files to identify token-wasting patterns, providing actionable suggestions to optimize documentation for LLM consumption and token efficiency.

wechat-article-writer

Automated WeChat article writing workflow including web research, viral title generation, drafting, and professional layout optimization.

nia

Research agent for Nia: index/search remote codebases, docs, and packages. Optimizes AI context by prioritizing full source indexing over web fetches to reduce hallucinations.