Agent Skills Hub

anthropic-api

Expert guidance for building production-ready applications with Anthropic's Claude API. Covers SDKs, prompt caching, batch processing, streaming, tool use, and cost optimization strategies.

web-shader-extractor

Extract, deobfuscate, and port WebGL/Canvas/Shader visual effects from websites into standalone, native JavaScript projects.

xurl

Unified CLI tool to read, query, discover, and write AI agent conversations using the agents:// URI scheme across multiple coding agents and providers.

lint

Executes standard Deno linting, formatting, and type-checking for the vibe-kanban CLI codebase.

i18n-expert

Automate i18n setup, string extraction, and locale parity audits for React/TS codebases. Features framework-aware config, automated audit scripts, and safe string replacement to ensure seamless localization.

research-review

Get deep, critical, NeurIPS/ICML-style peer reviews of your research, paper drafts, and experimental setups using external LLMs via Codex MCP.

multi-llm-advisor

Fetches expert perspectives from OpenAI Codex and Google Gemini for architecture, code reviews, and debugging, with transparent LLM synthesis.

command-executor

Safely execute, test, and verify commands discovered in documentation with real output capture, performance tracking, and git-aware safety protocols.

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.

persona

An AI-driven framework for crafting bespoke, authentic portfolio websites from scratch. Guides agents through research, design, and code implementation to build unique developer and professional sites.

n8n-expression-testing

Validate n8n expression syntax, perform context-aware testing, detect common pitfalls, and optimize data transformations within your workflows.

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.