Open source. Open possibilities.

A curated directory of 1000+ production-ready Claude Skills and plugins for enhancing AI agent productivity across Claude.ai, Claude Code, Cursor, Codex, Gemini CLI, and more.

Agent skill for OpenClaw and DeepSeek Harness enabling intelligent A-share stock selection, quantitative analysis, and stock pool management.

ClawHub is the public skill and plugin registry for OpenClaw. It enables publishing, versioning, searching, and installing text-based agent skills with vector search, plus a native package catalog for code plugins, bundle plugins, and experimental whole-agent Claw packages.

Taste Skill is a set of MIT-licensed Agent Skills that help AI coding agents produce more polished, less generic frontends, plus image-generation skills for design references and brand kits.

A Claude skill for inspecting and building Figma design systems, providing read-only audits (WCAG, token compliance, interactive states, etc.) and a build mode that creates components, adds slots, and optionally exports tokens.css and AI rules for seamless design‑to‑code integration.

Deep Lake is a serverless multimodal database for AI that combines vector search with storage for embeddings, images, video, audio, and documents. It streams data directly from cloud storage to PyTorch/TensorFlow, supports versioning, and integrates with LangChain, LlamaIndex, and Weights & Biases.

Caveman is a skill and proxy that compresses the prose of AI coding agents, cutting output tokens by up to 65% and input tokens by about a third. It works with 30+ agents via a simple CLI, offers benchmark data, and includes privacy‑friendly telemetry controls.