Agent Skills Hub

dlt-skill

Create, manage, and debug dlt (data load tool) pipelines for ingesting data from APIs, databases, and custom sources into destinations like DuckDB, BigQuery, and Snowflake.

tanstack-query

Production-grade TanStack Query v5 patterns for async state management, including query key factories, data mutations, caching, and SSR configuration.

backend-core

Language-agnostic backend architectural patterns covering API design, authentication, security protocols, and database modeling.

product-analytics

Analyze product performance using KPI frameworks, cohort analysis, and funnel metrics to drive growth, retention, and feature adoption.

project-overview

Complete project architecture and structure guide for LobeHub. Use for codebase exploration, project organization, file location, and architectural context.

commit

Enforces Sentry-style conventional commits, branch safety checks, and structured issue referencing for AI coding agents.

tool-integration

Create, register, and manage custom agent tools and MCP servers to extend AI agent capabilities with external APIs and custom logic.

p9

P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.

upstash-vector-db-skills

Upstash Vector DB setup, semantic search, namespaces, and embedding models. Ideal for building high-performance vector search features in Next.js 16/Vercel projects.

llmfit-advisor

Analyze local system hardware (RAM, CPU, GPU/VRAM) to receive expert recommendations for optimized local LLM models, quantization settings, and performance estimates.

repo-analyzer

Analyze GitHub repository structure, documentation, dependencies, and contributor patterns for codebase health and development insights.

massive-context-mcp

Process massive files and large codebases (10M+ tokens) by recursively chunking, sub-querying, and aggregating results to overcome LLM context limits.