Agent Skills Hub

prompt-improver

Enriches vague prompts by performing codebase research and asking targeted questions to clarify user intent before execution.

mls

Unified local ML inference server for ASR, TTS, Translation, Image Generation, and Vision on Apple Silicon, powered by MLX.

ui-design-review

Gemini-powered UI design review, accessibility auditing, and design system validation tool for software agents.

opper-api

Direct access to the Opper REST API for LLM orchestration, model management, task execution, and seamless migration from OpenAI, Anthropic, or OpenRouter.

massgen-config-creator

Guide for creating properly structured YAML configuration files for MassGen. Use this when creating new configs for examples, case studies, testing, or feature demonstrations.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.

request-optimizer

An intelligent gateway that analyzes, scores, and routes user requests across 27 agents, 27 skills, and 14 MCPs to optimize Claude Code execution.

gemini-api

Google Gemini Image Generation API interface for text-to-image, editing, style templates, and automated retry workflows.

Agent Communication Debugger

Diagnose and debug Agent-to-Agent (A2A) communication, including orchestrator routing, transport connectivity, agent status, and log analysis for multi-agent systems.

Ralph-Loop-Ultra

Seamlessly toggle between live and mocked external dependencies using the Model Context Protocol (MCP) for autonomous development environments.

memory-hygiene

Audit, prune, and maintain vector memory for Clawdbot. Prevents token waste, clears junk data, and automates memory hygiene via LanceDB maintenance.

gemini-manager

Claude Code as an architect: delegate all coding and file edits to the Gemini CLI while maintaining control through planning, verification, and oversight.