Agent Skills Hub

claude-ralph

An autonomous AI agent loop that executes Claude Code repeatedly to build features from structured PRDs until completion.

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.

vibesafe

Manage Vibesafe units to scan, generate, test, and verify AI-written code with cryptographically-secure hash-locked checkpoints.

hegelion

Dialectical reasoning and adversarial coding agent for MCP-enabled editors, forcing LLMs to resolve internal contradictions for higher quality outputs.

opencode

Expert guide for OpenCode AI: TUI commands, CLI operations, AGENTS.md configuration, custom agent workflows, and project setup.

mcp-server

Guide for integrating and managing custom Model Context Protocol (MCP) servers within the Cursor IDE environment.

awb

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

ReasoningBank with AgentDB

Implement ReasoningBank adaptive learning with AgentDB's ultra-fast vector backend. Features trajectory tracking, verdict judgment, memory distillation, and pattern recognition for self-learning autonomous agents.

vibe-orchestrator

Master workflow controller for Lovable-style, AI-driven development. Instantly generates premium, multi-page, animated applications by routing to specialized sub-agents. No prompts needed—just build.

image-rotator

Reliably rotate images by 90-degree increments using a deterministic Python script. Supports PNG, JPG, GIF, BMP, and TIFF, preserving quality with automated file handling.

morph-warpgrep

Morph WarpGrep and Fast Apply tools for high-speed agentic code search, deep logic analysis, and efficient AI-driven code editing.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.