Agent Skills Hub

multi-tenant-isolation

Enables multi-tenant isolation for AI agent swarms, ensuring strict data separation, process isolation, and secure resource management between deployments.

dlt-skill

Create, manage, and debug dlt (data load tool) pipelines for ingesting data from APIs, databases, and custom sources into destinations like DuckDB, BigQuery, and Snowflake.

performance-optimization

Optimize Node.js performance via Redis caching, clustering, profiling, and monitoring to build fast, scalable, and efficient backend services.

openclaw-release-maintainer

Manages the OpenClaw release lifecycle: prepares branches, updates versioning across multiple platforms, generates changelogs, and orchestrates npm and binary artifact publishing.

connections

Lightweight MCP (Model Context Protocol) connection handler supporting stdio, SSE, and streamable HTTP transports for seamless server integration.

skyll

A runtime skill discovery engine for AI agents. Search and retrieve specialized agent skills (SKILL.md) on-demand via REST API or MCP to inject procedural knowledge into your agent's context.

jupyter-notebook-testing

Test Adobe EDS blocks interactively in the browser with Jupyter notebooks. Features ES6 imports, overlay previews, responsive device testing, and zero-dependency execution.

mcp-rails

Implement a full Model Context Protocol (MCP) stack in Rails. Connect to external servers, expose your Rails app as an MCP server, or manage subprocess MCP containers via Docker with OAuth 2.1 PKCE support.

pipeline

Manage dlt data pipelines and Temporal workflows for the SignalRoom marketing platform. Sync sources like Everflow, Redtrack, and S3 to Postgres, check status, and debug ingestion.

hf-mcp

Connect your AI agent to the Hugging Face Hub via MCP. Search models, datasets, and papers, manage repos, run cloud compute jobs, and invoke Gradio Spaces as functional AI tools.

gdoc

Reliably read and extract content from publicly shared Google Docs using curl for full document retrieval.

debug-hooks

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