> 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/operator-agent/skills/using-skills.md).

# Using Skills

The Skills page shows every skill in your project, and the Skill Library lets you add ready-made ones built by Lleverage. This page covers finding skills, turning them on and off, and running them in a session.

### Browsing Skills

The Skills page lists all skills in your project. Each skill card shows:

* **Name, icon, and description**: what the skill does
* **Badges**: a **Draft** badge when the skill has unpublished changes, and a **Disabled** badge when it is switched off
* **Actions**: **Use** starts an agent session with the skill; owners and builders also see **Test** on skills with a draft

You can search skills and switch between a grid view and a list view.

### The Skill Library

The Skill Library contains ready-made skills built by Lleverage that you can install into your project:

1. **Open the library**: click **Library** on the Skills page. The library is also offered as a card on the agent's home screen.
2. **Browse or search** the available skills to find ones relevant to your work.
3. **Install**: click **Install skill**. If the skill uses a connected app, you choose which account it should use: a **shared account** that everyone uses, or a **personal account** where each operator connects their own.

Installed skills become normal project skills: you can adapt their instructions and components just like a skill you created yourself.

> 💡 Installing a skill publishes it into your project straight away, so the agent can use it immediately.

### Enabling and Disabling Skills

Owners and builders can toggle skills on or off per project:

* **Enabling** a skill makes it immediately available to the agent, so it can be used in any session.
* **Disabling** a skill removes it from the agent's tool context. The agent can no longer use it, but the skill is not deleted and can be re-enabled at any time.

This is useful when:

* A skill is causing the agent to select it when it shouldn't
* You want to temporarily remove a capability without losing the skill configuration
* You're testing a new skill and want to limit its availability

> ⚠️ Disabling a skill takes effect immediately. Any active sessions where the agent was about to use that skill will no longer have access to it.

### How the Agent Chooses Skills

You don't need to tell the agent which skill to use. When you describe a task, the agent evaluates its available skills and selects the most relevant ones automatically.

For example, if you say *"Process the incoming order from this email"* and you have an order processing skill enabled, the agent will recognise the match and use it.

### Invoking a Skill Yourself

You don't have to wait for the agent to pick a skill:

* **In the message box**: type **/** and choose the skill from the list. It appears in your message as a reference, and the agent loads that skill when you send it.
* **From the Skills page**: click **Use** on a skill card to start a session with it.
* **From the Explore page**: the agent's Explore page lists your skills alongside suggested prompts and apps. Choosing a skill starts a session with it.

> 💡 You can bring a skill in mid-conversation too. Reference it at any point and the agent loads the skill's instructions and follows them in the same turn.

### Skills in the Chat

When the agent loads a skill, you'll see it in the chat stream, so it is always clear which skill is being used. As the agent works through the skill, you can follow its progress and the tools it calls.

Clicking a skill opens its detail panel beside the chat, showing the skill's instructions and components. Owners and builders can edit the skill from there without leaving the conversation.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.lleverage.ai/operator-agent/skills/using-skills.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.
