Agent Skills Hub

quality

Expert code reviewer for Rust projects. Performs comprehensive quality, security, performance, and architectural analysis using Bazel and project-specific conventions.

Hive Agent Architecture

Framework for building, registering, and orchestrating Model Context Protocol (MCP) tools and AI agent workflows within the Hive native Rust architecture.

Verification & Quality Assurance

A robust verification and QA system for software agents featuring real-time truth scoring, automated code validation, and instant rollback capabilities to maintain high reliability.

inno-prepare-resources

Automates research resource preparation by loading instances, searching GitHub for codebases, building dataset descriptions, and downloading arXiv papers.

writing-skills

A Test-Driven Development (TDD) framework for writing agent skills, using pressure scenarios to ensure documentation guides agent behavior effectively.

agent-sdk

Expert skill for building and maintaining AI agents using the Claude Agent SDK, covering architecture, tool integration, MCP servers, and agentic workflows.

tavily-tools

Unified Python CLI for Tavily AI operations including web search, URL extraction, site crawling, link mapping, and automated deep research reports.

wiki-architect

Analyzes codebases to generate hierarchical documentation, onboarding guides, and architectural mapping, helping teams understand and document their projects efficiently.

explain-concepts

Explains complex concepts using master teaching frameworks like Feynman, Socratic, and Cognitive Load theory to ensure deep, clear understanding.

familiar-add-tool

Scaffold and register new sensor, actuator, or service tools for familiar-ai, automating file creation and boilerplate integration in agent.py and config.py.

qwen-asr

Transcribe audio files (wav, mp3, ogg) to text using the Qwen ASR model. Fast, local-friendly, and requires no API keys.

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.