Agent Skills Hub

ralph

Convert markdown PRDs into structured prd.json files for the Ralph autonomous AI agent system to enable repeatable, context-aware software development.

parallel-agents

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

artifact-tracking

AI-optimized artifact tracking system for token-efficient project orchestration, phase management, and automated task delegation using YAML-Markdown hybrid formats.

steve

Automate macOS applications using the Accessibility API for deterministic UI control, automated testing, and agent-based scripting.

awb

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

git

Safe, protocol-driven Git operations for committing, pushing, and PR management using the GitHub CLI (gh).

netbox-integration-best-practices

Best practices for building integrations with NetBox REST and GraphQL APIs. Optimize performance, authentication, and architectural patterns for NetBox automations.

omnifocus

Programmatically manage OmniFocus tasks and projects. Supports creation, querying, updates, and completion tracking across all OmniFocus versions using native automation and fallback methods.

mcp-setup

Automated setup and configuration of Model Context Protocol (MCP) servers for Claude Code to enable seamless integration with external databases, APIs, and file systems.

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.

design-review

Designer's eye QA: detects and automates fixes for visual inconsistencies, spacing, hierarchy, and UI polish issues. Iteratively verifies with before/after screenshots.

generate-e2e-test

Automated end-to-end test generation using Playwright. Converts user workflows into functional test specs by interactively executing actions and following project conventions.