Agent skill

Medusa

by alinaqi in alinaqi/maggy

Medusa headless commerce - modules, workflows, API routes, admin UI

MITAuto-check: notesSales & Support

Install Medusa

skills CLI
$ npx skills add alinaqi/maggy --skill medusa -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install alinaqi/maggy medusa --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/medusa .claude/skills/medusa && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
medusa
GitHub stars
707
Token cost
~4.1k tokens
SKILL.md length
309 words
Files
1
Skills in repo
71
Repo updated
First seen
Licence
MIT

At a glance

Medusa headless commerce - modules, workflows, API routes, admin UI

  • Works in 3 steps: Go to Settings → Regions → Add Stripe as payment provider → Configure for each region
  • Sales & Support work in your project
  • SKILL.md covers Why Medusa, Quick Start, Project Structure and Configuration, plus 6 more sections
  • Calls npm, npx and railway; needs JWT_SECRET and COOKIE_SECRET

What it does

Medusa is an agent skill from alinaqi/maggy. Medusa headless commerce - modules, workflows, API routes, admin UI

Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Sales & Support. The repository describes itself as: What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center. The licence is MIT.

When your agent uses it

  • Sales & Support work in your project

Example prompts

  • “/medusa”

Requirements

  • Node.js
  • A credential in JWT_SECRET
  • A credential in COOKIE_SECRET

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Go to Settings → Regions
  2. Add Stripe as payment provider
  3. Configure for each region

What it can do on your machine

Read from SKILL.md and the folder at commit 72a456e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • npx
    • railway
    • node
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • docs.medusajs.com
    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • JWT_SECRET
    • COOKIE_SECRET
    • STRIPE_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Medusa loads about 4.1k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 309 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
When it runs · the whole SKILL.md, loaded when a task matches
~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:133
    # .env

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from alinaqi/maggy at commit 72a456e, republished under its MIT licence (© alinaqi). 309 words, ~4,097 tokens.

Download SKILL.mdSave it as .claude/skills/medusa/SKILL.md (or your agent's skills folder).
name
medusa
description
Medusa headless commerce - modules, workflows, API routes, admin UI
when-to-use
When building with Medusa commerce platform
user-invocable
false
effort
medium

Medusa E-Commerce Skill

For building headless e-commerce with Medusa - open-source, Node.js native, fully customizable.

Sources: Medusa Docs | API Reference | GitHub


Why Medusa

FeatureBenefit
Open SourceSelf-host, no vendor lock-in, MIT license
Node.js NativeTypeScript, familiar stack, easy to customize
HeadlessAny frontend (Next.js, Remix, mobile)
ModularUse only what you need, extend anything
Built-in AdminDashboard included, customizable

Quick Start

Prerequisites
bash
# Required
node --version  # v20+ LTS
git --version
# PostgreSQL running locally or remote
Create New Project
bash
# Scaffold new Medusa application
npx create-medusa-app@latest my-store

# This creates:
# - Medusa backend
# - PostgreSQL database (auto-configured)
# - Admin dashboard
# - Optional: Next.js storefront

cd my-store
npm run dev
Access Points
URLPurpose
http://localhost:9000Backend API
http://localhost:9000/appAdmin dashboard
http://localhost:8000Storefront (if installed)
Create Admin User
bash
npx medusa user -e admin@example.com -p supersecret

Project Structure

medusa-store/
├── src/
│   ├── admin/                    # Admin UI customizations
│   │   ├── widgets/              # Dashboard widgets
│   │   └── routes/               # Custom admin pages
│   ├── api/                      # Custom API routes
│   │   ├── store/                # Public storefront APIs
│   │   │   └── custom/
│   │   │       └── route.ts
│   │   └── admin/                # Admin APIs
│   │       └── custom/
│   │           └── route.ts
│   ├── jobs/                     # Scheduled tasks
│   ├── modules/                  # Custom business logic
│   ├── workflows/                # Multi-step processes
│   ├── subscribers/              # Event listeners
│   └── links/                    # Module relationships
├── .medusa/                      # Auto-generated (don't edit)
├── medusa-config.ts              # Configuration
├── package.json
└── tsconfig.json

Configuration

medusa-config.ts
typescript
import { defineConfig, loadEnv } from "@medusajs/framework/utils";

loadEnv(process.env.NODE_ENV || "development", process.cwd());

export default defineConfig({
  projectConfig: {
    databaseUrl: process.env.DATABASE_URL,
    http: {
      storeCors: process.env.STORE_CORS || "http://localhost:8000",
      adminCors: process.env.ADMIN_CORS || "http://localhost:9000",
      authCors: process.env.AUTH_CORS || "http://localhost:9000",
    },
    redisUrl: process.env.REDIS_URL,
  },
  admin: {
    disable: false,
    backendUrl: process.env.MEDUSA_BACKEND_URL || "http://localhost:9000",
  },
  modules: [
    // Add custom modules here
  ],
});
Environment Variables
bash
# .env
DATABASE_URL=postgresql://user:pass@localhost:5432/medusa
REDIS_URL=redis://localhost:6379

# CORS (comma-separated for multiple origins)
STORE_CORS=http://localhost:8000
ADMIN_CORS=http://localhost:9000

# Backend URL
MEDUSA_BACKEND_URL=http://localhost:9000

# JWT Secrets
JWT_SECRET=your-super-secret-jwt-key
COOKIE_SECRET=your-super-secret-cookie-key

Custom API Routes

Store API (Public)
typescript
// src/api/store/hello/route.ts
import type { MedusaRequest, MedusaResponse } from "@medusajs/framework/http";

export async function GET(
  req: MedusaRequest,
  res: MedusaResponse
) {
  res.json({
    message: "Hello from custom store API!",
  });
}

// Accessible at: GET /store/hello
Admin API (Protected)
typescript
// src/api/admin/analytics/route.ts
import type { MedusaRequest, MedusaResponse } from "@medusajs/framework/http";
import { Modules } from "@medusajs/framework/utils";

export async function GET(
  req: MedusaRequest,
  res: MedusaResponse
) {
  const orderService = req.scope.resolve(Modules.ORDER);

  const orders = await orderService.listOrders({
    created_at: {
      $gte: new Date(Date.now() - 30 * 24 * 60 * 60 * 1000), // Last 30 days
    },
  });

  const totalRevenue = orders.reduce(
    (sum, order) => sum + (order.total || 0),
    0
  );

  res.json({
    orderCount: orders.length,
    totalRevenue,
  });
}

// Accessible at: GET /admin/analytics (requires auth)
Route with Parameters
typescript
// src/api/store/products/[id]/reviews/route.ts
import type { MedusaRequest, MedusaResponse } from "@medusajs/framework/http";

export async function GET(
  req: MedusaRequest,
  res: MedusaResponse
) {
  const { id } = req.params;

  // Fetch reviews for product
  const reviews = await getReviewsForProduct(id);

  res.json({ reviews });
}

export async function POST(
  req: MedusaRequest,
  res: MedusaResponse
) {
  const { id } = req.params;
  const { rating, comment, customerId } = req.body;

  const review = await createReview({
    productId: id,
    rating,
    comment,
    customerId,
  });

  res.status(201).json({ review });
}

// Accessible at:
// GET  /store/products/:id/reviews
// POST /store/products/:id/reviews
Middleware
typescript
// src/api/middlewares.ts
import { defineMiddlewares } from "@medusajs/framework/http";
import { authenticate } from "@medusajs/framework/http";

export default defineMiddlewares({
  routes: [
    {
      matcher: "/store/protected/*",
      middlewares: [authenticate("customer", ["session", "bearer"])],
    },
    {
      matcher: "/admin/*",
      middlewares: [authenticate("user", ["session", "bearer"])],
    },
  ],
});

Modules (Custom Business Logic)

Create Custom Module
typescript
// src/modules/reviews/index.ts
import { Module } from "@medusajs/framework/utils";
import ReviewModuleService from "./service";

export const REVIEW_MODULE = "reviewModuleService";

export default Module(REVIEW_MODULE, {
  service: ReviewModuleService,
});
typescript
// src/modules/reviews/service.ts
import { MedusaService } from "@medusajs/framework/utils";

class ReviewModuleService extends MedusaService({}) {
  async createReview(data: CreateReviewInput) {
    // Implementation
  }

  async getProductReviews(productId: string) {
    // Implementation
  }

  async getAverageRating(productId: string) {
    // Implementation
  }
}

export default ReviewModuleService;
Register Module
typescript
// medusa-config.ts
import { REVIEW_MODULE } from "./src/modules/reviews";

export default defineConfig({
  // ...
  modules: [
    {
      resolve: "./src/modules/reviews",
      options: {},
    },
  ],
});
Use Module in API
typescript
// src/api/store/products/[id]/reviews/route.ts
import { REVIEW_MODULE } from "../../../modules/reviews";

export async function GET(req: MedusaRequest, res: MedusaResponse) {
  const { id } = req.params;
  const reviewService = req.scope.resolve(REVIEW_MODULE);

  const reviews = await reviewService.getProductReviews(id);
  const averageRating = await reviewService.getAverageRating(id);

  res.json({ reviews, averageRating });
}

Workflows

Define Workflow
typescript
// src/workflows/create-order-with-notification/index.ts
import {
  createWorkflow,
  createStep,
  StepResponse,
} from "@medusajs/framework/workflows-sdk";
import { Modules } from "@medusajs/framework/utils";

const createOrderStep = createStep(
  "create-order",
  async (input: CreateOrderInput, { container }) => {
    const orderService = container.resolve(Modules.ORDER);

    const order = await orderService.createOrders(input);

    return new StepResponse(order, order.id);
  },
  // Compensation (rollback) function
  async (orderId, { container }) => {
    const orderService = container.resolve(Modules.ORDER);
    await orderService.deleteOrders([orderId]);
  }
);

const sendNotificationStep = createStep(
  "send-notification",
  async (order: Order, { container }) => {
    const notificationService = container.resolve("notificationService");

    await notificationService.send({
      to: order.email,
      template: "order-confirmation",
      data: { order },
    });

    return new StepResponse({ sent: true });
  }
);

export const createOrderWithNotificationWorkflow = createWorkflow(
  "create-order-with-notification",
  (input: CreateOrderInput) => {
    const order = createOrderStep(input);
    const notification = sendNotificationStep(order);

    return { order, notification };
  }
);
Execute Workflow
typescript
// In an API route
import { createOrderWithNotificationWorkflow } from "../../../workflows/create-order-with-notification";

export async function POST(req: MedusaRequest, res: MedusaResponse) {
  const { result } = await createOrderWithNotificationWorkflow(req.scope).run({
    input: req.body,
  });

  res.json(result);
}

Subscribers (Event Listeners)

Create Subscriber
typescript
// src/subscribers/order-placed.ts
import type { SubscriberArgs, SubscriberConfig } from "@medusajs/framework";

export default async function orderPlacedHandler({
  event,
  container,
}: SubscriberArgs<{ id: string }>) {
  const orderId = event.data.id;

  console.log(`Order placed: ${orderId}`);

  // Send notification, update analytics, etc.
  const notificationService = container.resolve("notificationService");
  await notificationService.sendOrderConfirmation(orderId);
}

export const config: SubscriberConfig = {
  event: "order.placed",
};
Common Events
EventTrigger
order.placedNew order created
order.updatedOrder modified
order.canceledOrder cancelled
order.completedOrder fulfilled
customer.createdNew customer registered
product.createdNew product added
product.updatedProduct modified
inventory.updatedStock changed

Scheduled Jobs

typescript
// src/jobs/sync-inventory.ts
import type { MedusaContainer } from "@medusajs/framework";

export default async function syncInventoryJob(container: MedusaContainer) {
  const inventoryService = container.resolve("inventoryService");

  console.log("Running inventory sync...");

  await inventoryService.syncFromExternalSource();

  console.log("Inventory sync complete");
}

export const config = {
  name: "sync-inventory",
  schedule: "0 */6 * * *", // Every 6 hours
};

Admin UI Customization

Custom Widget
tsx
// src/admin/widgets/sales-overview.tsx
import { defineWidgetConfig } from "@medusajs/admin-sdk";
import { Container, Heading, Text } from "@medusajs/ui";

const SalesOverviewWidget = () => {
  return (
    <Container>
      <Heading level="h2">Sales Overview</Heading>
      <Text>Your custom sales data here...</Text>
    </Container>
  );
};

export const config = defineWidgetConfig({
  zone: "order.list.before", // Where to show the widget
});

export default SalesOverviewWidget;
Widget Zones
ZoneLocation
order.list.beforeBefore order list
order.details.afterAfter order details
product.list.beforeBefore product list
product.details.afterAfter product details
customer.list.beforeBefore customer list
Custom Admin Route
tsx
// src/admin/routes/analytics/page.tsx
import { defineRouteConfig } from "@medusajs/admin-sdk";
import { Container, Heading } from "@medusajs/ui";
import { ChartBar } from "@medusajs/icons";

const AnalyticsPage = () => {
  return (
    <Container>
      <Heading level="h1">Analytics Dashboard</Heading>
      {/* Your analytics charts */}
    </Container>
  );
};

export const config = defineRouteConfig({
  label: "Analytics",
  icon: ChartBar,
});

export default AnalyticsPage;

Store API (Built-in)

Products
typescript
// Frontend: Fetch products
const response = await fetch("http://localhost:9000/store/products");
const { products } = await response.json();

// With filters
const response = await fetch(
  "http://localhost:9000/store/products?" +
  new URLSearchParams({
    category_id: "cat_123",
    limit: "20",
    offset: "0",
  })
);
Cart
typescript
// Create cart
const { cart } = await fetch("http://localhost:9000/store/carts", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    region_id: "reg_123",
  }),
}).then(r => r.json());

// Add item
await fetch(`http://localhost:9000/store/carts/${cart.id}/line-items`, {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    variant_id: "variant_123",
    quantity: 1,
  }),
});

// Complete cart (create order)
const { order } = await fetch(
  `http://localhost:9000/store/carts/${cart.id}/complete`,
  { method: "POST" }
).then(r => r.json());
Customer Authentication
typescript
// Register
await fetch("http://localhost:9000/store/customers", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    email: "customer@example.com",
    password: "password123",
    first_name: "John",
    last_name: "Doe",
  }),
});

// Login
const { token } = await fetch("http://localhost:9000/store/auth/token", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    email: "customer@example.com",
    password: "password123",
  }),
}).then(r => r.json());

// Authenticated request
await fetch("http://localhost:9000/store/customers/me", {
  headers: {
    Authorization: `Bearer ${token}`,
  },
});

Payment Integration

Stripe Setup
bash
npm install @medusajs/payment-stripe
typescript
// medusa-config.ts
export default defineConfig({
  modules: [
    {
      resolve: "@medusajs/payment-stripe",
      options: {
        apiKey: process.env.STRIPE_API_KEY,
      },
    },
  ],
});
In Admin
  1. Go to Settings → Regions
  2. Add Stripe as payment provider
  3. Configure for each region

Deployment

Railway
bash
# Install Railway CLI
npm install -g @railway/cli

# Login and deploy
railway login
railway init
railway up
Render
yaml
# render.yaml
services:
  - type: web
    name: medusa-backend
    runtime: node
    plan: starter
    buildCommand: npm install && npm run build
    startCommand: npm run start
    envVars:
      - key: NODE_ENV
        value: production
      - key: DATABASE_URL
        fromDatabase:
          name: medusa-db
          property: connectionString
      - key: JWT_SECRET
        generateValue: true
      - key: COOKIE_SECRET
        generateValue: true

databases:
  - name: medusa-db
    plan: starter
Docker
dockerfile
FROM node:20-alpine

WORKDIR /app

COPY package*.json ./
RUN npm ci --only=production

COPY . .
RUN npm run build

EXPOSE 9000
CMD ["npm", "run", "start"]

CLI Commands

bash
# Development
npm run dev                    # Start dev server

# Database
npx medusa db:migrate          # Run migrations
npx medusa db:sync             # Sync schema

# Users
npx medusa user -e email -p pass  # Create admin user

# Build
npm run build                  # Build for production
npm run start                  # Start production server

Checklist

Setup
  • PostgreSQL database configured
  • Redis configured (optional but recommended)
  • Admin user created
  • CORS origins configured
  • JWT/Cookie secrets set
Customization
  • Custom modules for business logic
  • Custom API routes for frontend
  • Subscribers for event handling
  • Workflows for complex operations
Deployment
  • Environment variables configured
  • Database migrations run
  • HTTPS enabled
  • Admin URL secured

Anti-Patterns

  • Editing .medusa folder - Auto-generated, will be overwritten
  • Direct database access - Use services and modules
  • Skipping workflows for complex ops - Workflows provide rollback
  • Hardcoding URLs - Use environment variables
  • Ignoring TypeScript errors - Framework relies on types

© alinaqi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/medusa of alinaqi/maggy.

Open the folder on GitHubat commit 72a456e

Compare with similar skills

Medusa next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Medusa compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Medusa this skillalinaqi/maggy707—~4.1kAutomated safety check: NotesMIT
Cold Outbound Optimizerericosiu/ai-marketing-skills3.6k1 repos~1.7kAutomated safety check: PassMIT
Doc Coauthoringaws-samples/sample-strands-agent-with-agentcore19540 repos~3.2kAutomated safety check: PassMIT
Amazon Buy Box Monitorbrowser-act/skills6.1k1 repos~1.6kAutomated safety check: PassMIT
Review Analysisliangdabiao/amazon-sorftime-research-MCP-skill9591 repos~2.5kAutomated safety check: PassNone
Deskcomm Extensaomelgarafael/DeskcommCRM4.5k—~2.7kAutomated safety check: PassMIT

Similar skills

  • Cold Outbound Optimizer

    ericosiu/ai-marketing-skills

    Design, analyze, and optimize cold outbound email campaigns for Instantly.

    3.6k GitHub starsUsed in 1 repo~1.7k tokens
    Sales & SupportAuto-check passed
  • Doc Coauthoring

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Guide users through a structured workflow for co-authoring documentation.

    195 GitHub starsUsed in 40 repos~3.2k tokens
    Sales & SupportAuto-check passed
  • Amazon Buy Box Monitor

    browser-act/skills

    Pulls Amazon product details, competing seller prices and seller ratings for a given ASIN through the BrowserAct API, without browser automation.

    6.1k GitHub starsUsed in 1 repo~1.6k tokens
    Sales & SupportAuto-check passed
  • Review Analysis

    liangdabiao/amazon-sorftime-research-MCP-skill

    对亚马逊商品评论进行深度分析,自动识别产品痛点、分析退货原因,生成改进建议和客服回复模板。Invoke when user uses /review-analysis command with a product ASIN.

    959 GitHub starsUsed in 1 repo~2.5k tokens
    Sales & SupportAuto-check passed
  • Deskcomm Extensao

    melgarafael/DeskcommCRM

    Guia para criar uma extensão do DeskcommCRM — o pacote declarativo — em vez de abrir um PR no núcleo.

    4.5k GitHub stars~2.7k tokensUpdated today
    Sales & SupportAuto-check passed
  • Tourmind Booking

    tourmind-com/Tourmind-Booking-Skills

    MUST USE for any hotel or accommodation intent in any language, including hotel search, hotel recommendations, nearby accommodation, hostels, guesthouses, resorts, where-to-stay questions, room…

    1.8k GitHub stars~13k tokensUpdated yesterday
    Sales & SupportAuto-check passed

More from alinaqi/maggy

All 71 skills in this repo
  • Aeo Optimization

    alinaqi/maggy

    AI Engine Optimization - semantic triples, page templates, content clusters for AI citations

    707 GitHub stars~3.7k tokensUpdated 17 days ago
    Auto-check passed
  • Agent Teams

    alinaqi/maggy

    Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement

    707 GitHub stars~5k tokensUpdated 17 days ago
    Auto-check: notes
  • AI Models

    alinaqi/maggy

    Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate

    707 GitHub stars~4.1k tokensUpdated 17 days ago
    Auto-check passed
  • Android Java

    alinaqi/maggy

    Android Java development with MVVM, ViewBinding, and Espresso testing

    707 GitHub stars~3.9k tokensUpdated 17 days ago
    Auto-check: notes
  • Android Kotlin

    alinaqi/maggy

    Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing

    707 GitHub stars~3k tokensUpdated 17 days ago
    Auto-check passed
  • Autonomous Testing

    alinaqi/maggy

    AI-driven testing agent that auto-discovers, generates, executes, evaluates, and fixes tests for any project type

    707 GitHub stars~1.1k tokensUpdated 17 days ago
    Auto-check passed

Categories

Questions about Medusa

What does Medusa do?

Medusa headless commerce - modules, workflows, API routes, admin UI. Medusa is an agent skill from alinaqi/maggy.

When should I use Medusa?

Medusa fits situations like: sales & Support work in your project.

How do I install Medusa in Claude Code?

Run `npx skills add alinaqi/maggy --skill medusa -a claude-code`. Or copy the skill folder (skills/medusa in alinaqi/maggy) into .claude/skills/medusa in your project. Claude Code loads it when a task matches its description.

How do I install Medusa in Codex?

Run `npx skills add alinaqi/maggy --skill medusa -a codex`. Or copy the skill folder (skills/medusa in alinaqi/maggy) into .agents/skills/medusa in your project. Codex loads it when a task matches its description.

Can I use Medusa in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alinaqi/maggy --skill medusa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/medusa, .gemini/skills/medusa, .github/skills/medusa and .opencode/skills/medusa in your project.

What does Medusa need to run?

Going by SKILL.md and its folder, Medusa needs the command-line tools its instructions call (npm, npx, railway, node and git) and credentials named JWT_SECRET, COOKIE_SECRET and STRIPE_API_KEY. Our summary lists: Node.js; A credential in JWT_SECRET; A credential in COOKIE_SECRET.

Does Medusa access the network?

SKILL.md names 2 domains. As links in the text: docs.medusajs.com and github.com. This is read from the text; nothing was executed.

Is Medusa safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Medusa use?

Medusa is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Medusa use?

About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Medusa?

Skills that share tags, products or a category with Medusa: Cold Outbound Optimizer (ericosiu/ai-marketing-skills, 3.6k stars), Doc Coauthoring (aws-samples/sample-strands-agent-with-agentcore, 195 stars), Amazon Buy Box Monitor (browser-act/skills, 6.1k stars) and Review Analysis (liangdabiao/amazon-sorftime-research-MCP-skill, 959 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Medusa?

alinaqi (a GitHub user) maintains it in alinaqi/maggy, which has 707 GitHub stars. The repository holds 71 skills in this directory. The repository was last updated on September 24, 2026.

Source: alinaqi/maggy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.