Agent Skills Hub

muapi-logo-creator

Design professional-grade brand identities using geometric primitives, negative space, and flat vector-style aesthetics via AI-driven branding logic.

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.

jta

Agentic AI-powered JSON i18n file translator with auto-terminology, format preservation, and incremental updates to streamline global software deployment.

obsidian-bases

Create and edit Obsidian Bases (.base files) with database-like views, complex filters, custom formulas, and data summaries.

wechat-publisher

One-click publishing of Markdown articles to WeChat Official Account drafts, featuring automated image hosting, multi-theme styling, and code syntax highlighting.

stream-chain

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows within the Ruflo/Claude Flow ecosystem.

nano-banana

Automate Python scripting and Gemini-powered image generation using uv. Ideal for creating art, editing images, and running ad-hoc scripts.

java-dev

Standardized Java development guidelines including naming conventions, exception handling, Spring Boot best practices, and concurrency patterns.

my-openlayer-helper

Initialize OpenLayers maps, manage layers, and render features including points, lines, polygons, and animated markers using the my-openlayer library.

skill-template

A standardized template for creating and documenting modular Agent Skills to ensure consistent, efficient context engineering across AI agent systems.

transcribee

Transcribe YouTube videos and local audio/video files with high-precision speaker diarization. Supports major formats for ready-to-use LLM analysis.

design-review

Designer's eye QA: detects and automates fixes for visual inconsistencies, spacing, hierarchy, and UI polish issues. Iteratively verifies with before/after screenshots.