Building a Portfolio with Anthropic Plugins

Anyone trying to show an employer that they can do forward deployed engineering work needs something concrete to point to. A résumé line saying you understand customer problems is easy to write and hard to verify. This article looks at one unusually direct way to produce evidence: building a plugin on Anthropic's platform. The source presents this route as especially current, because Anthropic's Code with Claude conference in 2026 introduced enterprise plugin templates.

Keep one question in mind as you read: what does a hiring reviewer need to see in order to judge the work without having to take your word for it? The rest of the article traces how a plugin is built, what it produces, and how that output becomes something a reviewer can check.

Anthropic plugin templates are enterprise templates introduced at Anthropic's Code with Claude conference in 2026. The source associates them with seven named areas, listed below. The source does not claim this list is exhaustive, so treat it as the set of areas named in the source rather than a complete catalogue.

The breadth is the point. The list includes internal business functions such as HR and engineering alongside client-facing financial domains such as equity research and wealth management. The templates are not confined to one kind of work, so a learner choosing a vertical has real range to pick from.

Each of the three parts has a distinct role. The prompts carry the instructions that tell the underlying model what to do for the task. The tools are the capabilities the plugin can call on while doing that work. The configuration holds the settings that shape how the package behaves. Because all three travel together, the plugin can be handed to someone else as one unit rather than as a set of loose files that only you know how to assemble.

The source describes making a well-built plugin as a sequence of decisions rather than a single act of writing. The order matters. The vertical comes first because it constrains every later choice. A job-to-be-done only makes sense inside a domain, and the packaging only makes sense once you know which task it serves.

Treating the plugin as a chain of decisions, rather than as a pile of prompts, is what turns a demo into something a reviewer can judge. Each stage gives a reviewer something to question: why this vertical, why this task, and why this packaging.

Building the package is only part of the work. The source states that a plugin produces three things: a trace, an eval set against the plugin's task, and wrapper logic that makes the plugin reliable. The source names the trace and the eval set without defining every detail of either, so treat them here as outputs you must be able to show, rather than as a fully specified format.

The wrapper logic is the piece the source ties to reliability. The emphasis on evidence is the source's central point: eval evidence that lets you defend each plugin matters more than simply having many plugins in a portfolio.

The source's claim is specific: the plugin and Skills surface is presented as the cleanest route to a portfolio piece for an aspiring FDE, because the piece can be immediately evaluated by hiring managers at Anthropic and across its partner ecosystem. Immediate evaluation is a statement about review. It means the work can be judged directly, without a separate presentation or an indirect proxy. It is not the same as being hired.

The source describes a strong candidate as one who has shipped two or three plugins, in a vertical they understand, with the eval evidence to defend each one. The important phrase is eval evidence to defend each one. A plugin without that evidence can still be installed and demonstrated, but the candidate has less to point to when a reviewer asks why it should be trusted.