Agent Skills Hub

blogwatcher

Monitor and track updates from blogs, RSS, and Atom feeds directly using the blogwatcher CLI within your OpenClaw assistant.

retro

Weekly engineering retrospective tool that analyzes commit history, coding patterns, and quality metrics with automated session detection and trend tracking.

wavespeed-nano-banana-2

Generate and edit images using Google's Nano Banana 2 via WaveSpeed AI. Supports text-to-image, natural language editing, multi-image composition, 4K resolution, and various aspect ratios.

connections

Lightweight MCP (Model Context Protocol) connection handler supporting stdio, SSE, and streamable HTTP transports for seamless server integration.

feishu-weekly-report

Generate professional weekly reports by aggregating Feishu chat history and local daily memory logs into a structured template.

golang

Production-ready Go development support: concurrency patterns, idiomatic error handling, interface design, testing with testify, and Go best practices for scalable backend services.

agent-sdk

Expert skill for building and maintaining AI agents using the Claude Agent SDK, covering architecture, tool integration, MCP servers, and agentic workflows.

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.

component-workflow

Guidance for creating and integrating new ECS components, including class design, JSON serialization, custom editor UI implementation, and DI registration.

everything-test

Verify Everything Search integration (CLI, HTTP, SDK) for inventory_master to ensure connectivity, service health, and provider availability.

vm-infrastructure-ops

Troubleshoot and manage the GCP e2-micro VM running the eth-realtime-collector. Handle systemd failures, network connectivity issues, and real-time data stream monitoring for Ethereum network data.

vibe-build

The final execution agent for the vibe-coding workflow. Builds your MVP incrementally by following the AGENTS.md master plan, managing session continuity, and verifying each feature via testing.