A Claude Code skill is a SKILL.md file plus optional supporting files that teach Claude a repeatable procedure. Kept in ~/.claude/skills/ or a project’s .claude/skills/, a skill is personal or project-local. To hand one to a teammate, ship it across every project, or publish it to the community, you wrap it in a plugin and list that plugin in a marketplace that others can add with one command. This tutorial builds a real skill, packages it as a plugin, catalogs it in a marketplace, validates the manifests with the claude CLI, tests it locally, and distributes it through GitHub. The end result is a repository anyone can install with /plugin marketplace add your-org/your-repo followed by /plugin install. ...

The previous tutorial built a uv workspace with a single packages/ folder holding a library and a CLI. That layout mixes reusable libraries and runnable programs in one directory. A common convention is to split them: packages/ for importable libraries, apps/ for deployable programs. This tutorial builds a workspace with both, where a shared greetings library in packages/ is consumed by two apps in apps/: a simple command-line app and a FastAPI web app. A root Makefile runs, serves, and tests every member. ...

A uv workspace lets several related Python packages live in one repository, share a single lockfile and virtual environment, and depend on each other by name without publishing to a registry. This tutorial builds a two-package workspace: a greetings library and a cli application that imports it. A root Makefile drives sync, run, test, and inspection across every member with one command each. By the end you will have a reproducible layout where editing the library is immediately visible to the application, and make test runs every package’s tests in one pass. ...

Most of the MCP articles in this repo connect an agent downward to tools: an agent is a client, and a server exposes functions it can call. That is the vertical axis. The Agent2Agent (A2A) protocol covers the horizontal axis, where one agent talks to another agent as a peer. Instead of “call this function,” the message is “here is a task, you handle it and report back.” The two protocols are complementary: an agent can be an MCP client (reaching down to tools) and an A2A server (answering peers sideways) at the same time. ...

Build a Hugo static site whose /premium/ section is locked behind a Stripe subscription, with the access decision made by a Cloudflare Worker at the edge. Free posts stay cached and public. A request for a premium page runs the Worker first: it checks a signed session cookie and confirms the subscription is still active in KV before it hands back the file. Payment, activation, and cancellation flow through Stripe Checkout and a webhook. ...

There are two ways to structure a UGC video ad in Higgsfield’s Marketing Studio. The hooks and settings path lets you assemble a concept from building blocks. The ad reference path does the opposite: you hand Marketing Studio a video of an ad that already works, it analyzes the whole scenario — scene composition, pacing, hook, narration — and rebuilds that structure around your product. It is the “make a video like this one” path. ...

When you generate a UGC-style ad video in Higgsfield’s Marketing Studio, the preset picks the genre — Unboxing, Tutorial, Selfie Testimonial — but two optional levers control the specifics of the shot: the hook (how the ad opens and grabs attention) and the setting (where it happens and the vibe). Most people leave them on default and miss the biggest lever they have over whether an ad stops the scroll. This deep-dive covers what each is, the real catalogue behind them, how they combine, and when to reach for which. ...

Marketing Studio is the one part of Higgsfield built around a commercial goal rather than a raw generation. You point it at a product — or a whole website — and it produces scroll-ready ad images and short ad videos, styled to your brand and optionally presented by an avatar. Instead of writing prompts, you assemble a small library (a product, a brand kit, an avatar) and then pick an ad format or a UGC preset. ...

AI image models reinvent a face every time you generate. The moment you want the same person or character to appear across many images and clips, you need an avatar: a reusable identity you attach to a generation so the result looks consistent. Higgsfield gives you two ways to make one, and choosing the right one is the whole skill. This article explains both — Soul training and Reference Elements — when to use each, and how avatars carry through the rest of the platform. ...

Higgsfield’s standalone audio is about one thing: voice. It turns text into spoken audio, lets you clone a voice from a sample, and lets you revoice an existing clip with a different speaker. That is the whole audio surface for a normal user, and it is worth saying plainly up front: there is no standalone music or sound-effects generator here. Higgsfield does have music and SFX models, but they exist only inside its game-generation pipeline and are not meant for general use. If you want a soundtrack, you either use a video model’s built-in native audio or bring your own. ...