Agent Skills Hub

plugin-best-practices

Validates Claude Code plugins against architectural standards, checking manifest files, frontmatter, and tool invocation patterns to ensure high-quality, compliant plugin development.

FastMCP Development

Build and manage MCP servers using the FastMCP framework. Guide for creating tools, resources, prompts, Claude Desktop integration, and deployment with Python and TypeScript.

document

Interactive terminal canvas for rendering, editing, and selecting markdown text, emails, and project documentation in Claude Code.

quality

Expert code reviewer for Rust projects. Performs comprehensive quality, security, performance, and architectural analysis using Bazel and project-specific conventions.

worker

Autonomous agent for ticket-driven development, managing the full software lifecycle from polling providers to automated PR creation with ERNE standard validation.

context-detection

Systematic project technology stack detection, framework-specific skill auto-loading, and multi-stack analysis for fullstack projects like React + Go.

awb

Interactive UI components for Claude Code and AI agents. Create confirmations, checklists, inputs, tables, and views to handle non-blocking interactions and monitoring.

context-bar

A color-coded, real-time context usage progress bar for the Claude Code statusline and manual on-demand checks.

commit

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

commit-messages

Generate consistent, Conventional Commits-compliant messages directly from your staged git diffs.

network-watcher

Audit outbound network requests and detect data exfiltration patterns in OpenClaw skills to ensure secure outbound communication.

structuring-plugins

Guides the creation and organization of Claude Code plugins, including directory scaffolding, manifest setup, component management (commands, agents, skills, hooks), and auto-discovery configuration.