> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/run-operations/agent/agent-context/skills.md). # Skills Understand how Skills give the Agent reusable ways of doing recurring work. A Skill is a reusable operating method the Agent can use for a recurring job. For example, a Skill might teach the Agent how your organisation checks a supplier confirmation, prepares a tender response, analyses a pricing round or creates a standard document. ## How Skills are used The Agent can select an available Skill automatically when it matches the task. You can also invoke a Skill deliberately when you want a specific method followed. When a Skill is used, it can draw on the Project capabilities available to the Agent, such as connected systems, files, Knowledge or Workflows. A Skill does not grant access by itself. ## Turn a useful method into a Skill After a useful task, you can ask the Agent to make the method reusable for the team. The Agent can propose a Skill for you to review before anything is saved or published. ## Skills can improve over time If the same correction keeps returning, a builder can update the Skill, test representative cases and publish a reviewed new version. Published Skills do not silently rewrite themselves because of one conversation. For operator guidance, see [Using Skills](/run-operations/agent/agent-context/skills/using-skills.md). For building and maintaining Skills, see [Skills and operating methods](/build-and-improve/overview/skills-and-operating-methods.md). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.lleverage.ai/run-operations/agent/agent-context/skills.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.