Agent Skills Hub

test-skill

A testing fixture for validating AI agent skill configurations and detecting rule violations.

code-quality-review

Holistic, multi-dimensional code review skill providing prioritized, actionable feedback on correctness, security, performance, design, and accessibility.

text-to-sql

Convert natural language queries to safe, optimized SQL. Automates database interactions with schema awareness and parameterized query generation.

feature-dev

Guided, systematic feature development agent that orchestrates codebase exploration, architectural design, implementation, and automated testing.

moonwell-contracts-v2

Automates Moonwell protocol governance proposal lifecycle, from creation and verification to deployment and testing.

unity

Control the Unity Editor via Claude Code to run tests, compile scripts, manage play mode, and retrieve console logs using a file-based bridge.

indirect-injection-detection

Detects indirect prompt injection and goal hijacking in AI agents by evaluating how they process external content like RAG, documents, and web data.

session-investigator

Analyze and debug fast-agent session histories, tool execution logs, and conversation timing to resolve performance bottlenecks, tool loops, and unexpected session terminations.

claude-ralph

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

mcaf-devex

Optimize developer experience for multi-component solutions: standardize onboarding, inner-loop, debugging, and cross-platform setup to eliminate friction and tribal knowledge.

adb-controller

Control Android devices via ADB to perform taps, swipes, text input, and screenshot retrieval directly in your workflow.

peekaboo

A macOS UI automation CLI that enables agents to capture screens, target UI elements, manage applications, and execute cross-app workflows with JSON-based scripting.