Agent Skills Hub

typescript

TypeScript development standards for LobeHub, covering type safety, async patterns, import organization, UI component integration, and performance optimization.

agentic-workflows

Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.

server-actions

Expert skill for Next.js Server Actions, covering form handling, data mutations, revalidation, and optimistic UI updates in the App Router.

data_processor

A multi-paradigm ETL pipeline agent supporting batch and streaming data processing, schema inference, and configurable DAG-based transformations for heterogeneous data sources.

jujutsu

Manage version control with Jujutsu (jj): perform rebasing, conflict resolution, bookmark management, and commit manipulation in your Git-compatible workflow.

reload

Clean up your current Claude Code session and automatically resume in a fresh, optimized terminal window.

land

Automated PR lifecycle management: monitors conflicts, resolves CI failures, handles review feedback, and executes squash-merges for safe code integration.

java-test

Executes Gradle-based Java tests, filters results for failures and key statistics, and provides concise reports to streamline backend development and debugging.

jenkins

Manage Jenkins CI/CD pipelines via REST API. Trigger builds, monitor job status, view console logs, and manage nodes and queues directly from your terminal or AI agent.

elasticsearch

Elasticsearch DBA skill for cluster architecture, mapping design, performance tuning, and production operations including ILM, shard strategy, and troubleshooting.

Delegating to AWS Agent

Implement an AI agent delegation architecture to keep your main context clean, reduce token costs, and isolate specialized infrastructure or API tasks.

meta

Meta Marketing CLI for Graph API automation, managing ad campaigns, insights reporting, and Instagram publishing with fail-closed security.