Agent Skills Hub

fhir-developer-skill

FHIR API development guide for building compliant healthcare endpoints. Includes resource validation, coding systems, and standard error handling.

agent-architecture

Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.

playwright-cli

Token-efficient CLI for browser automation, web testing, and agentic workflows using Playwright.

eval

Evaluate Deca agent prompts and behavioral consistency through automated test runners, manual LLM judgment, and structured reporting.

flowgram.ai

Development guide for creating custom nodes in FlowGram.ai workflows, supporting both auto-generated simple forms and complex custom UI components.

requesting-code-review

Enforces code quality by dispatching a dedicated subagent to review work against project plans, requirements, and git commit history before tasks are completed or merged.

music-theory-visual-design

Visual design and UI styling guidelines for the Harmonic Orbit music theory application, covering typography, color systems, spacing, animations, and accessibility standards.

mcp-add

Easily configure and add Model Context Protocol (MCP) servers to various AI coding clients like Cursor, Claude, VS Code, and more using an interactive or automated command-line interface.

vertesia-plugin

Framework for building Vertesia plugins with a dual tool-server and UI architecture, featuring Hot Module Replacement, build-tools, and asset management.

asana

Asana project management integration. Manage tasks, projects, workspaces, and team workflows directly via the Membrane CLI.

open-source-maintainer

End-to-end GitHub repository maintenance agent. Automates triage, PR review, issue analysis, and maintenance reporting to ensure long-term repository health, stability, and growth.

plan-writing

Structured task planning framework for AI agents to break down complex features, refactors, and bugs into actionable, verifiable steps.