Advises on API versioning strategies, designs deprecation flows, generates migration guides, and classifies breaking vs non-breaking…
Generates complete, production-ready REST API endpoint specifications for any system or domain the user describes.
Guide for authoring Apollo Federation subgraph schemas: entities with @key, @shareable, federation directives and composition error…
Designs GraphQL schemas, resolvers, query/mutation/subscription patterns, and protobuf definitions for gRPC services.
Guide for writing GraphQL operations (queries, mutations, fragments) following best practices, including type generation and linting.
Guide for designing GraphQL schemas following industry best practices: type structure, nullability, pagination, error patterns and schema…
Use consistent OpenAPI terminology and definitions when writing documentation, educational material, and tooling guidance.
Redocly CLI usage for OpenAPI, AsyncAPI, Arazzo and Overlay descriptions: linting, bundling, splitting, joining, decorators, docs preview…
Build, customize, and troubleshoot OpenAPI mock servers with @scalar/mock-server, including x-handler, x-seed, authentication, and Docker.
Create a vanilla tRPC client with createTRPCClient
Generate an OpenAPI 3.1 spec from a tRPC router with @trpc/openapi (CLI or programmatic) and a typed REST client with @hey-api/openapi-ts.
Initialize tRPC with initTRPC.create(), define routers with t.router(), create procedures with .query()/.mutation()/.subscription()…
Generate complete, production-ready OpenAPI 3.x and Swagger 2.0 specifications from natural language descriptions, code, or partial specs.
Entry point for all tRPC skills: decision-tree routing by task across initTRPC.create(), t.router(), t.procedure, createTRPCClient…
Reviews REST API designs during the planning phase against security, resilience, design, and operational best practices.
Guide for building GraphQL servers with Apollo Server 5.x: resolvers, schema definitions, authentication, plugins, data sources and…
API Development agent skills on mcprush, filed under one heading so the shelf can be read in one pass. The kinds are workflow, expertise, output format, voice & style and guardrail, and the one a skill belongs to is the fastest way to guess what it will do to your prompt.
What to look at before installing one is what it costs in context and what it takes away: a guardrail that refuses an action and a voice that rewrites a sentence are both skills, and only one of them will stop the agent doing something. Every skill here says which kind it is, what it costs in context, what it needs beside it to work and the licence it is published under, next to the publisher it came from and whether that publisher has been verified. The filters on the left narrow it further and the sort at the top decides what comes first.
A skill is not connected to anything: there is no endpoint to authorise and nothing routed through the gateway. Installing one drops a folder of instructions into the client’s own skill folder, and uninstalling it is deleting that folder. The exact line for each client is on the skill’s own page, because it differs by client rather than by skill.