Sponsor Suno AI Music arrow_forward
Slash Command

Build Graphql Server

Build a GraphQL server with schema-first design

Type
Slash Command
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026

What Build Graphql Server is

Build Graphql Server is a slash command published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Build Graphql Server gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Build Graphql Server

Claude Code

  1. Download build-graphql-server.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/api-development/graphql-server-builder/commands/build-graphql-server.md, shared under the repository's MIT license. Read the full file on GitHub.

Create a production-ready GraphQL server with type-safe schemas, optimized resolvers, real-time subscriptions, authentication, and comprehensive tooling using schema-first design principles.

When to Use This Command

Use /build-graphql-server when you need to:

  • Build flexible APIs with client-specified queries
  • Implement real-time features with subscriptions
  • Reduce over-fetching and under-fetching of data
  • Create strongly-typed API contracts
  • Support multiple client applications with different data needs
  • Build microservices with federation support

DON'T use this when:

  • Building simple CRUD APIs (REST may be simpler)
  • Clients have limited GraphQL knowledge (learning curve)
  • Caching is critical and simple (REST caching is more straightforward)

Design Decisions

This command implements Apollo Server with DataLoader as the primary approach because:

  • Most mature GraphQL server implementation
  • Excellent TypeScript support
  • Built-in performance optimizations
  • Rich ecosystem of tools and plugins
  • Production-proven at scale
  • Comprehensive monitoring with Apollo Studio

Alternative considered: GraphQL Yoga

  • More lightweight and modular
  • Better for serverless deployments
  • Newer with smaller ecosystem
  • Recommended for edge computing

Alternative considered: Mercurius (Fastify)

  • Fastest GraphQL server
  • Better for high-performance requirements
  • Less mature ecosystem
  • Recommended when performance is critical

Prerequisites

Before running this command:

  1. Define your domain models and relationships
  2. Choose database and ORM/ODM
  3. Plan authentication strategy
  4. Determine subscription requirements
  5. Identify performance requirements

Implementation Process

Step 1: Design GraphQL Schema

Create comprehensive type definitions with proper nullability and relationships.

Step 2: Implement Resolvers

Build efficient resolvers with DataLoader for batching and caching.

Step 3: Add Authentication & Authorization

Implement context-based auth with field-level permissions.

Step 4: Set Up Subscriptions

Configure WebSocket server for real-time updates.

Step 5: Optimize Performance

Add query complexity analysis, depth limiting, and caching.

Output Format

The command generates:

  • schema/ - GraphQL schema definitions
  • resolvers/ - Resolver implementations
  • dataloaders/ - DataLoader configurations
  • directives/ - Custom schema directives
  • server.js - Apollo Server setup
  • generated/types.ts - TypeScript definitions
  • tests/ - Integration and unit tests

Code Examples

Example 1: Complete GraphQL Server with Apollo Server

// schema/schema.graphql
scalar DateTime
scalar Upload

directive @auth(requires: Role = USER) on FIELD_DEFINITION
directive @rateLimit(max: Int, window: String) on FIELD_DEFINITION
directive @deprecated(reason: String) on FIELD_DEFINITION | ENUM_VALUE

enum Role {
  USER
  MODERATOR
  ADMIN
}

type User {
  id: ID!
  username: String!
  email: String!
…

Example 2: Optimized Resolvers with DataLoader

// resolvers/index.js
const { GraphQLScalarType } = require('graphql');
const { PubSub, withFilter } = require('graphql-subscriptions');
const DataLoader = require('dataloader');

const pubsub = new PubSub();

const resolvers = {
  // Custom scalar for DateTime
  DateTime: new GraphQLScalarType({
    name: 'DateTime',
    serialize: (value) => value.toISOString(),
    parseValue: (value) => new Date(value),
    parseLiteral: (ast) => new Date(ast.value)
  }),

  Query: {
    me: async (_, __, { user, loaders }) => {
…

Example 3: Custom Directives and Performance Optimization

// directives/auth.js
const { mapSchema, getDirective, MapperKind } = require('@graphql-tools/utils');
const { defaultFieldResolver } = require('graphql');

function authDirective(schema, directiveName) {
  return mapSchema(schema, {
    [MapperKind.OBJECT_FIELD]: (fieldConfig) => {
      const authDirective = getDirective(schema, fieldConfig, directiveName)?.[0];

      if (authDirective) {
        const { requires } = authDirective;
        const { resolve = defaultFieldResolver } = fieldConfig;

        fieldConfig.resolve = async function (source, args, context, info) {
          // Check if user is authenticated
          if (!context.user) {
            throw new Error('Not authenticated');
          }
…

Error Handling

Configuration Options

Server Options

  • introspection: Enable schema introspection (disable in production)
  • playground: Enable GraphQL Playground
  • cors: CORS configuration
  • uploads: File upload support
  • subscriptions: WebSocket configuration

Performance Options

  • depthLimit: Maximum query depth (default: 10)

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Build Graphql Server?

Build Graphql Server is a slash command for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Build a GraphQL server with schema-first design

How do I install Build Graphql Server in Claude Code?

Download build-graphql-server.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Build Graphql Server in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Build Graphql Server safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.