Agent Skills Hub

parallel-agents

Orchestrate complex workflows by coordinating multiple specialized AI agents for multi-perspective code analysis, feature implementation, and system-wide reviews.

refly

Base ecosystem skill for Refly. Creates, discovers, and runs domain-specific skills, routes user intent to workflows via symlinks, and automates multi-step pipelines via the Refly CLI.

context-cascade

A nested plugin architecture for Claude Code that optimizes context by dynamically loading playbooks, skills, and agents to save over 90% in token usage.

skill-code-review

Multi-LLM code review pipeline using consensus-based analysis to detect security, architectural, and quality issues.

professor-synapse

A wise conductor of expert agents. It helps you achieve goals by summoning, orchestrating, and creating specialized AI experts. Features intellectual humility, multi-agent debate, and self-learning pattern capture.

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.

awb

Interactive UI components for Claude Code and AI agents. Create confirmations, checklists, inputs, tables, and views to handle non-blocking interactions and monitoring.

design-system-implementation

Enforce strict UI adherence to your project's design system tokens, components, and layout patterns for consistent frontend implementation.

openai-whisper

Local speech-to-text transcription using the OpenAI Whisper CLI, providing private, high-accuracy audio processing without external API keys.

gitnexus-pr-review

Automate pull request reviews with structural code analysis, blast radius assessment, and dependency impact mapping.

frontend

Frontend coding conventions for Preact and Tailwind. Use for web UI components in cluster applications.

structured-code-review

Performs a structured five-stage code review covering requirements, correctness, code quality, testing, and security. Provides actionable, categorized feedback (Blocker/Major/Minor/Nit) to improve PR quality.