{"id":15937,"date":"2026-07-30T14:22:53","date_gmt":"2026-07-30T12:22:53","guid":{"rendered":"https:\/\/www.iese.fraunhofer.de\/blog\/?p=15937"},"modified":"2026-07-30T16:59:41","modified_gmt":"2026-07-30T14:59:41","slug":"agentic-skillsets-change-software-engineering","status":"publish","type":"post","link":"https:\/\/www.iese.fraunhofer.de\/blog\/agentic-skillsets-change-software-engineering\/","title":{"rendered":"From Prompts to Process: How Agentic Skillsets Change Software Engineering"},"content":{"rendered":"\n
\n

AI coding assistants rely more and more on agentic workflows. They can inspect repositories, plan changes, edit files, run tests, review their output, and call external tools. A growing part of this shift is the use of skillsets: reusable instruction packages that tell agents how to perform software engineering tasks.<\/p>\n\n\n\n

\n<\/div>\n\n\n\n

What skillsets are<\/h2>\n\n\n\n

A skillset can describe how an agent should plan work, write tests, review code, handle releases, or follow team conventions. In practice, these instructions typically take the form of Markdown files with YAML metadata (see Skills definitions<\/a>). They contain descriptions of tasks or workflows, definitions of useful commands or tools, and guidelines outlining how things should be done. Some stay purely textual. Others might include scripts, hooks, or even a local database.<\/p>\n\n\n\n

\n
\n
\n

\n info <\/p>\n<\/div>\n\n\n\n

\n

Definition: Agentic Skillset <\/strong>
Structured, reusable packages of procedural knowledge (often written in Markdown) that tell AI coding agents how to plan, execute, and review tasks without model fine-tuning.<\/p>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

Skillsets move part of the development process into the AI context. Team rules, review routines, testing habits, and architectural preferences become instructions that an agent reads and should follow. This makes skillsets a bridge between human engineering practice and AI-assisted execution.<\/p>\n\n\n\n

Most skillsets guide behavior. A skill can tell an agent to run tests before finishing a task. It cannot guarantee that the right tests were run, that failures were interpreted correctly, or that the agent did not skip a step.<\/p>\n\n\n\n

That distinction matters. A skillset is not a CI gate, a type checker, a permission system, or a branch protection rule. It belongs to the control layer of prompts and context. That layer can be useful. But it is not without uncertainty.<\/p>\n\n\n\n

Current skillsets come in different forms:<\/strong><\/p>\n\n\n\n