Agent Skills Hub

certification-proflie

A project-specific template skill for maintaining architectural consistency, coding standards, and deployment workflows in AI-powered full-stack applications.

PRISM.unified

UI component patterns and touch input handling for M5Stack Tab5 applications using M5GFX and LVGL.

pencil-ui-design

A professional workflow and component library for industrial-grade UI design using Pencil MCP, featuring standardized tokens for color, typography, spacing, and shadows.

senior-frontend-engineer-react

Enterprise-grade React CRUD development skill for React 16.14 and DVA 2.x, featuring automated page generation, form management, and service layer integration.

pytorch-lightning

PyTorch Lightning skill for scalable deep learning: automates model training, multi-GPU orchestration, data pipelines, and distributed training strategies like DDP, FSDP, and DeepSpeed.

library

Private skill distribution system for managing agentics across devices and teams. Install, sync, add, and update your agents, skills, and prompts via a central library catalog.

tdd-enforce

Enforce Test-Driven Development (TDD) via pre-commit hooks and CI/CD coverage gates. Automates test execution and ensures compliance with minimum code coverage thresholds.

database-patterns

Expert database design and access patterns: schema architecture, indexing strategies, query optimization, repository patterns, and transaction management for SQL and NoSQL databases.

bun

A comprehensive guide for using Bun as a high-performance alternative to Node.js. Supports project initialization, dependency management, script execution, and migration checklists.

tdd-guide

Comprehensive Test Driven Development (TDD) assistant for engineering teams, featuring intelligent test generation, coverage analysis, and multi-framework support.

higress-auto-router

Manage automatic model routing for Higress AI Gateway via CLI. Configure triggers for intelligent model selection based on request content.

root-cause-tracing

Systematic debugging skill to trace errors backward through call stacks, identify original triggers, and implement layered defenses instead of patching symptoms.