Agent Skills Hub

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.

ui

Generates UI components, hero sections, and feedback forms with integrated accessibility checks, leveraging specialized design references and quality gates.

langgraph-workflows

Master multi-agent orchestration with LangGraph. Build stateful, fault-tolerant AI workflows using supervisor-worker patterns, conditional routing, and advanced state management.

cascade-orchestrator

Advanced workflow orchestration for AI agents, featuring multi-model routing, Codex sandbox iteration, parallel swarm execution, and persistent memory across complex pipelines.

transcription

Production-ready audio/video transcription using OpenAI Whisper. Features model selection, timing synchronization, speaker diarization, and batch processing for media workflows.

castella-packaging

Package Castella UI applications into cross-platform executables, macOS app bundles, or installers using ux, PyInstaller, or Nuitka. Includes code signing and notarization support.

mcp-csharp-test

Test C# Model Context Protocol (MCP) servers using unit tests for tools and integration tests for protocol compliance and end-to-end scenarios.

design-review

Designer's eye QA: detects and automates fixes for visual inconsistencies, spacing, hierarchy, and UI polish issues. Iteratively verifies with before/after screenshots.

prompt-lookup

Search, discover, and refine AI prompts using the prompts.chat library. Access thousands of community-curated prompts for ChatGPT, Claude, and other AI models.

study-note

Log ideas, notes, and learning progress chronologically to project archives using a CLI helper tool for systematic knowledge retention.

gopls-mcp

Semantic Go code navigation and analysis tool using the Language Server Protocol (LSP) for accurate, high-performance project intelligence.

fiftyone-find-duplicates

Find, review, and remove duplicate or near-duplicate images in FiftyOne datasets using computer vision similarity embeddings.