Agent Skills Hub

kreuzberg

High-performance document intelligence library for extracting text, tables, code, and metadata from 91+ file formats, with OCR and LLM-ready output.

supermemory

Supermemory is a long-term memory infrastructure for AI agents, enabling persistent context, user profiles, and semantic RAG across multi-modal knowledge bases.

svelte-deployment

Expert SvelteKit deployment guidance covering production builds, static/node/cloudflare adapters, Vite configuration, and library authoring best practices.

mcp-setup

Automated setup and configuration of Model Context Protocol (MCP) servers for Claude Code to enable seamless integration with external databases, APIs, and file systems.

mls

Unified local ML inference server for ASR, TTS, Translation, Image Generation, and Vision on Apple Silicon, powered by MLX.

chromium-docs

Search and reference Chromium documentation, including design docs, APIs, and development guides. Use to locate, browse, or learn about architecture, GPU, network, security, and testing concepts within the Chromium codebase.

core-dev

Development guide for lemline-core, the stateless Serverless Workflow engine. Manage workflow execution, node navigation, state transitions, JQ expression evaluation, error handling, and parallel fork logic.

playwright-skill

Complete browser automation with Playwright. Features local dev server detection, script generation, screenshot capture, form filling, responsive testing, and UX validation.

speak

Local text-to-speech conversion using Kokoro TTS. Generate audio, read text aloud, and handle multilingual speech synthesis directly in your terminal.

beads-integration

Persistent task memory and workflow synchronization for Claude Code using Beads, enabling multi-session project management and context preservation.

native-app-performance

Native macOS/iOS app performance profiling via xctrace and CLI-based hotspot analysis without opening the Instruments UI.

autoresearch

Autonomous multi-team codebase improvement agent with specialized modes: narrow (goal-directed), broad (hypothesis-divergent), and sweep (quality-focused).