Agent Skills Hub

claude-copilot

Analyze markdown documentation files to ensure compliance with predefined AI token budgets and optimize content for efficient AI ingestion.

glyphbox

A framework for an LLM-based NetHack agent that dynamically synthesizes Python code in a secure sandbox to perform complex dungeon exploration and gameplay actions via a high-level API.

agentdb-state-manager

Persistent state management and workflow analytics using DuckDB for task dependency tracking, historical metrics, and context checkpointing.

debug-hooks

Systematic debugging workflow for Claude Code hooks. Use to troubleshoot non-firing hooks, output errors, or unexpected behavioral issues.

design-system-patterns

Master design system architecture: implement design tokens, multi-brand theming, component libraries, and automated design-to-code pipelines for scalable UI foundations.

mcp-patterns

Maintenance patterns for the @youdotcom-oss/mcp STDIO bridge, focusing on transport lifecycle management, shutdown guards, and robust error handling.

session-init

Initializes a development session with environmental health checks, task status synchronization, and contextual memory restoration for Claude Code.

personal-productivity

Help users manage time and tasks effectively. Use for overcoming overwhelm, improving focus, balancing responsibilities, and increasing personal productivity.

seatbelt-sandboxer

Generates minimal macOS Seatbelt sandbox configurations for application isolation and security profiling.

ctf-solver

An expert-level CTF solver agent that automates reconnaissance, vulnerability analysis, and exploit generation for web, pwn, crypto, reverse, and forensic challenges.

code-auditing

A systematic code auditing framework for identifying technical debt, security vulnerabilities, dead code, and code quality issues in software projects.

test-skill

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