Agent Skills Hub

hive-mind-advanced

Queen-led multi-agent orchestration for Claude Code, featuring Byzantine consensus, persistent collective memory, and adaptive task distribution for complex software projects.

stable-baselines3

Production-ready reinforcement learning using Stable Baselines3. Train agents, design custom environments, implement training callbacks, and optimize workflows with a scikit-learn-style API.

context-engineering-expert

Advanced context engineering system for orchestrating AI agents, memory management, and token optimization to improve long-term persistence and project intelligence.

mind

Persistent, Git-friendly memory for Claude. Automatically store and retrieve project decisions, bug fixes, and coding patterns in a local .mv2 file.

flow-nexus-neural

Train and manage neural networks in distributed E2B sandboxes using the Flow Nexus platform, supporting custom architectures like Transformers, LSTMs, and GANs.

agentic-workflows

Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.

drawnote-skill

An automated visual note and flowchart generator. Converts text or keywords into styled diagrams, mind maps, and handwritten notes exported as images without requiring file-reading permissions.

massive-context-mcp

Process massive files and large codebases (10M+ tokens) by recursively chunking, sub-querying, and aggregating results to overcome LLM context limits.

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.

hunt-focus-definition

Synthesize research on system internals and adversary tradecraft into a concrete, testable hunt hypothesis.

PAI

Physical hardware synthesis bridge for PAI. Generates blueprints, 3D printing code, SVG paths for laser cutting, and G-Code for CNC machining to bring agentic designs into the physical world.

implementation

Structured, template-driven workflow for end-to-end feature development including coding, automated testing, verification, and session-based improvement.