> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/advanced-basic/capability-map.md).

# Advanced Capability Map

Choose the current capability based on your goal

Advanced tutorials are not listed item by item in the Settings menu; they start from “what do you want to accomplish?” First choose the closest goal, then enter the corresponding tutorial.

<figure><img src="https://1658303467-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0Ut5BptC3t8CtSU1UWpM%2Fuploads%2FkgpNuyo8gZCICnyN4DG5%2Fclipboard.png?alt=media&amp;token=fc5ef897-8cd1-4bb9-ba84-de7e4b3943e0" alt="从目标选择 Cherry Studio 工作入口的流程图"><figcaption><p>First use the main entry point to complete the smallest task; after the result is stable, add the knowledge base, skills, MCP, channels, or scheduled tasks.</p></figcaption></figure>

{% hint style="success" %}
When you need to configure a tutorial, channel, scheduled task, or extension capability, first tell the Agent your goal in \[Work]. The Agent can help determine what is missing and guide you through common setup steps; when you need to verify accounts, keys, or exact parameters, then go to \[Settings] to adjust them manually.
{% endhint %}

<figure><img src="https://1658303467-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0Ut5BptC3t8CtSU1UWpM%2Fuploads%2FB0qRf90ZD688LtBFhLrp%2Fclipboard.png?alt=media&amp;token=c35d2332-f56d-46dd-925d-eff1b182a66f" alt="Cherry Studio 启动台的九个主要入口"><figcaption><p>The launcher on the left provides nine main entry points; choose the one closest to your task to get started.</p></figcaption></figure>

Diagram explanation: first choose the main entry point based on your goal, then add skills, MCP, channels, or scheduled tasks after the workflow is stable.

### Choose an entry point by goal

| What do you want to accomplish                         | Recommended entry                                                | Capabilities you will use                                            |
| ------------------------------------------------------ | ---------------------------------------------------------------- | -------------------------------------------------------------------- |
| Compare multiple answers, organize long discussions    | \[Chat]                                                          | Multiple models, message branches, context, citations, and artifacts |
| Process files or complete multi-step tasks             | \[Work]                                                          | Agent, working directory, tools, permissions, and status panel       |
| Ask questions reliably using your own materials        | \[Knowledge Base] → run a retrieval test, then bind the Agent    | Files/web pages/notes, RAG, retrieval scope                          |
| Generate illustrations from articles or edit images    | \[Drawing], or enable \[Generate Image] in the Agent             | Templates, reference images, local editing, enhancement              |
| Translate text, screenshots, or long documents         | \[Translation]                                                   | OCR, document processing, history, and favorites                     |
| Capture drafts and continue refining them              | \[Notes]                                                         | Markdown, search, export, add to knowledge base                      |
| Capture the interface, annotate it, and copy text      | \[Settings] → \[Screenshot]; use global shortcuts after enabling | Region screenshots, annotations, mosaic blur, OCR                    |
| Open commonly used web apps                            | \[Mini Programs]                                                 | Built-in web tools and added websites                                |
| Browse, preview, and organize local files              | \[Files]                                                         | File list, preview, and follow-up processing                         |
| Connect external tools or fix a working method         | Let the Agent judge first, then verify in \[Settings]            | Skills, MCP, built-in tools                                          |
| Use the Agent from an external platform                | First let the Agent guide the setup in \[Work]                   | Channels, allowed scope, permission mode                             |
| Generate daily reports or reminders on a schedule      | Get the Agent working first, then create \[Scheduled Tasks]      | Agent, working directory, channels, run logs                         |
| View materials and tasks at the same time              | Right-click the tab → \[Open in New Window]                      | Multiple windows, pinned tabs, global search                         |
| Manage programming command line tools                  | Launchpad \[Coding Partner]                                      | Code CLI, model connection, directory, and terminal                  |
| Let a local program call models or troubleshoot issues | \[Settings] → \[API Gateway] / \[General]                        | Compatible APIs, call chain, developer mode                          |

### Recommended learning order

{% stepper %}
{% step %}

#### 1. First master the Agent workspace

Learn how to create Agents, choose a working directory, and understand model roles and permissions. The later extensions, automation, and project examples are all built on this.
{% endstep %}

{% step %}

#### 2. Then connect materials and capabilities

Use the knowledge base for long-term materials, skills for repeatable methods, and MCP for external systems. Add only one capability at a time and verify it with a small task.
{% endstep %}

{% step %}

#### 3. Finally automate or connect externally

After manual results are stable, configure channels, scheduled tasks, Code CLI, or external APIs. This makes it easier to find which link is causing problems when issues occur.
{% endstep %}
{% endstepper %}

### Read by module

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Advanced chat</strong></td><td>Multiple models, branches, context, and artifacts</td><td></td></tr><tr><td><strong>Agent workspace</strong></td><td>From configuration and execution to file delivery</td><td></td></tr><tr><td><strong>Knowledge and content workflow</strong></td><td>Knowledge base, notes, drawing, and translation</td><td></td></tr><tr><td><strong>Extend the Agent's capabilities</strong></td><td>Skills and MCP</td><td></td></tr><tr><td><strong>Automation and external reach</strong></td><td>Channels, scheduled tasks, and heartbeats</td><td></td></tr><tr><td><strong>Efficient workspace</strong></td><td>Multi-window, productivity tools, and search</td><td></td></tr><tr><td><strong>Development and diagnostics</strong></td><td>Code CLI, API Gateway, and call chain</td><td></td></tr><tr><td><strong>Application examples</strong></td><td>Nine complete workflows</td><td></td></tr></tbody></table>

{% hint style="warning" %}
The working directory, MCP, channels, and high-privilege mode all expand the range of data the Agent can access. Only provide the directories, tools, and accounts needed for the current task, and do not place API keys, bot secrets, or private information into public conversations or screenshots.
{% endhint %}


---

# 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.cherryai.com.cn/docs/en-us/advanced-basic/capability-map.md?ask=<question>&goal=<user_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.