When designing distributed systems for scalability, reliability, and consistency.
Choose a 3D generation or reconstruction pipeline given input type, output format, and use case.
Build ChatGPT apps with MCP servers on Cloudflare Workers.
Creates a new git commit for all uncommitted changes with an atomic, conventionally-tagged message.
Generates Decorator pattern for PHP 8.4.
Builds and reviews SwiftUI views with modern MV architecture, state, composition, isolated previews, and migration guidance.
Comprehensive codebase assessment for agent and production readiness.
Three.js shaders - GLSL, ShaderMaterial, uniforms, custom effects.
Provides and generates complete CRUD workflows for Spring Boot 3 services.
Provides REST API design standards and best practices for Spring Boot projects.
Guide SpriteKit game implementation, repair, and maintenance.
OpenAPI documentation and REST API design patterns
Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository state.
Audit a proposed API change for breaking changes — classification and impact assessment.
Specialized guide for migrating Godot 3.x projects to Godot 4 (GDScript 2.0), covering syntax changes, Tweens, and exports.
Error handling patterns — try/catch, async errors, error boundaries, useAsyncCall, and toast messages.
OneKey monorepo architecture, project structure, package relationships, and import hierarchy rules.
Infuses Claude with the lightning-fast, reactive inner voice of a Disco Elysium character to handle sudden changes and verbal sparring.
Expert guide for writing efficient GLSL shaders (Vertex/Fragment) for web and game engines, covering syntax, uniforms, and common effects.
Provides Spring Boot MCP server patterns that create Model Context Protocol servers with Spring AI by defining tool handlers, exposing…
Convert Stitch HTML designs to React Native components, or syncs/updates existing native components to align with the latest Stitch…
Developer Tools & Repos agent skills on mcprush govern how an agent reviews, debugs and ships code: what a review comment is allowed to say, when a bug counts as reproduced, what a flaky test costs before it may be quarantined. The kinds are workflow, expertise, output format, voice & style and guardrail, and the one a skill belongs to, where its author declared it, 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 what it costs in context, which kind it is where its author declared one, 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.