Agent Skills Hub

dumbwaiter-mcp

Provider-agnostic MCP skill for wait-for-change automation on PR events like status checks, merges, and comments.

arduino-mcp

An MCP server enabling agents to edit, manage, and compile Arduino IDE 2.0 sketches, including source code manipulation and automated build capabilities via arduino-cli.

write-docs

Automate the creation and maintenance of BrowserOS feature documentation using a structured, codebase-aware workflow to generate concise Mintlify MDX pages.

split-pdf

Automated pipeline to download, split, and deeply analyze academic PDFs in structured batches to avoid context window limits and ensure high-quality comprehension.

cli

Prefect CLI skill for executing mutation operations like triggering deployments, canceling flow runs, and managing automations within your Prefect infrastructure.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

claude-opus-4-5-migration

Migrate your codebase, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to the advanced Opus 4.5 model with automated configuration adjustments.

threejs-builder

Build performant Three.js web scenes using modern ES modules. Includes scene graph setup, lighting, geometries, GLTF/GLB loading, animation loops, and performance optimization best practices.

Data Analysis Helper

A versatile data analysis assistant for loading datasets, performing statistical calculations, visualizing trends, and generating professional summary reports.

codebase-analyzer

Automates the creation and maintenance of CLAUDE.md files. It monitors codebase evolution and keeps project memory in sync with file changes, structure, and build commands.

sap-abap

Comprehensive ABAP development support for SAP systems, covering classic ABAP, ABAP Cloud, CDS views, RAP, EML, and modern syntax patterns.

code-quality-review

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