Agent Skills Hub

testing-hashql

Guidelines for testing HashQL code using compiletest (UI tests), unit tests, and insta snapshots. Includes commands for --bless, annotation syntax, and strategies for compiler components.

agentdb-state-manager

Persistent state management and workflow analytics using DuckDB for task dependency tracking, historical metrics, and context checkpointing.

box-least-squares

BLS periodogram tool for detecting transiting exoplanets and eclipsing binaries in photometric light curves. An astropy-based implementation for period, duration, and depth analysis.

smithery-ai-cli

Find, connect, and use over 100,000 MCP tools and skills via the Smithery CLI to integrate external services, manage agent workspaces, and automate workflows.

mijia-control

Control and monitor Xiaomi Mijia smart home devices including status switching, device discovery, automation scenes, and environmental statistics.

voice-apply

Transforms content to match specific voice profiles, tones, or styles using configurable YAML templates for consistent brand and narrative output.

common

Infrastructure for cross-product HealthSim data persistence, entity correlation via SSN, and DuckDB database operations.

spark-optimization

Optimize Apache Spark jobs with partitioning strategies, memory management, shuffle tuning, and data skew mitigation for high-performance data processing pipelines.

performance-optimization

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

Building Frontend Dashboards

Build responsive React dashboards using TypeScript, shadcn/ui, TanStack Query, and Supabase. Ideal for creating KPI cards, data tables, charts with Recharts, and admin interfaces for event-studio.

stream-validator

Validate WebSocket and HTTP stream health for WaveCap-SDR. Measure latency, throughput, packet loss, and signal quality for audio, spectrum, and IQ streams.

kreuzberg

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