Agent Skills Hub

epsimo-agent

Epsimo AI platform SDK and CLI for building agents with persistent state, Virtual Database, streaming conversations, and a React UI kit.

remote-browser

Controls a local or remote headless browser for automated web navigation, data extraction, form interaction, and testing from sandboxed environments.

cascade-orchestrator

Advanced workflow orchestration for AI agents, featuring multi-model routing, Codex sandbox iteration, parallel swarm execution, and persistent memory across complex pipelines.

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.

solana-dev

A unified Solana development skill hub featuring multi-agent orchestration, progressive skill loading, and deep integrations for Anchor, Token-2022, DeFi protocols, and security auditing.

strikeradar

Monitor US-Iran strike probability via real-time open-source signals including market odds, flight traffic, energy prices, and geopolitical alerts.

rigup.nix

A framework for building modular AI agent rigs using Nix, featuring parametrable skills, knowledge management, and automated tool configuration.

reverse-engineering-api

Reverse engineer web APIs by capturing browser traffic (HAR files) and generating production-ready Python API clients for automation and data extraction.

vibe-build

The final execution agent for the vibe-coding workflow. Builds your MVP incrementally by following the AGENTS.md master plan, managing session continuity, and verifying each feature via testing.

ui-mockup

Orchestrator for audio plugin WebView UI design, handling iterative mockup generation and production-ready scaffolding for JUCE-based instruments and effects.

wt

Manage isolated LlamaFarm development environments using git worktrees for parallel agent sessions and service testing.

juliaz-tool-builder

Expert guidance for designing and implementing high-quality tool schemas and descriptions for Julia's agent systems, ensuring reliable tool execution and reducing model hallucinations.