Agent skills for HTTP / API

When to activate: general Swift code, value types, enums, pattern matching, optionals, result types, property wrappers

When to activate: Swift Testing framework, XCTest, unit tests, async tests, test macros, parameterized tests, Swift mocking

When to activate: SwiftUI views, layouts, state management, view modifiers, navigation, lists, animations in SwiftUI

When to activate: tRPC, end-to-end type safety, RPC, routers, procedures, middleware, subscriptions, React Query integration

When to activate: async/await, Promise patterns, concurrency, AbortController, error handling in async code, streams, async iterators

When to activate: user stories, as a user I want, acceptance criteria, story splitting, story mapping, epic, backlog, agile

When to activate: vendor selection, RFP process, contract negotiation, SLA monitoring, vendor risk assessment, supplier relationship…

When to activate: Vite, vite.config.ts, plugins, HMR, build optimization, code splitting, environment variables, vitest

When to activate: weekly review, GTD review, horizon planning, weekly planning, end of week, Friday review, weekly reset

Use when implementing 2D physics interactions with Matter.js, including Engine/World setup, Render/Runner configuration, adding bodies and…

Compact the current conversation into a handoff document for another agent to pick up.

Develop, test, and automate Unreal Engine 5.x projects (WIP).

Cleans up and improves existing code without changing behavior.

A relentless interview to sharpen a plan or design.

Use this skill when an agent is managing its own micro.blog identity with mb.

Use this skill whenever you are using the mb CLI to read, post, manage follows, or build pipelines against micro.blog.

Use this skill when acting on behalf of a human user with mb.

Shape and simplify decision-heavy control flow while writing, extending, reviewing, or refactoring code.

Use this skill when the user wants to create a new MCP (Model Context Protocol) server.

Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources.

Use when reviewing the source code of an MCP server or client implementation — not just its runtime config — for authentication, session…