> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/ai-workbench-qore/platform-resources/skill-library/document-skills.md).
# Document skills
The built-in Document skills every agent has, and how to choose between them.
The **Document** group holds 11 built-in skills for working with the files a user uploads. Enable one from the **Pre-attached Skills** tab of **Add Skill**, and see which are active in the agent's **Skills** panel. See [Enable a built-in skill](/ai-workbench-qore/platform-resources/skill-library.md#enable-a-built-in-skill). In the Skills panel, the group header shows how many are active, for example **2/11 active**.
## Extract data
| Skill | What it does |
| ------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- |
| **Extract Document Data (Flash)** | Extracts data from files in a structured format, using Gemini Flash. |
| **Extract Document Data (Legacy)** | Extracts structured data, such as key fields or tables, from PDFs, Excel sheets, or images, using AI. |
| **Multi Document Extraction (UPTIQ)** | Extracts structured data from one merged file that holds several source documents, such as combined PDFs or a multi-section upload. |
## Classify documents
| Skill | What it does |
| ----------------------------------------- | -------------------------------------------------------------------------------------------------- |
| **Classify Document** | Classifies a document into a high-level category and a specific document type. |
| **Smart Document Classification** | Classifies a document into a high-level category and a specific document type, using Gemini Flash. |
| **Multi Document Classification (UPTIQ)** | Classifies one file that may hold several distinct document types, and processes them in parallel. |
## Understand and create documents
| Skill | What it does |
| ------------------------------- | ---------------------------------------------------------------------------------------------------------- |
| **Analyze Documents** | Uses AI-powered semantic search to extract insights and answer questions directly from uploaded documents. |
| **Summarize Document** | Creates a short summary that highlights a document's main points and key insights. |
| **Document Generation (UPTIQ)** | Generates new documents, such as reports and summaries, from prompts and existing content. |
## Show results to the user
| Skill | What it does |
| --------------------------- | --------------------------------------------------------- |
| **Show Extraction Results** | Shows an interactive view of document extraction results. |
| **Display Document** | Shows a document with formatted content and navigation. |
{% hint style="info" %}
**Which extraction skill?** Use **Multi Document Extraction (UPTIQ)** when one uploaded file actually combines several documents, such as a loan package merged into one PDF. For a single document, use **Extract Document Data (Flash)**. **Extract Document Data (Legacy)** is the earlier version.
{% endhint %}
{% hint style="info" %}
**Which classification skill?** Use **Multi Document Classification (UPTIQ)** when one file may hold several document types. For a single document, **Classify Document** and **Smart Document Classification** return the same result: a category and a document type. Smart Document Classification uses Gemini Flash.
{% endhint %}
{% hint style="info" %}
**Pair an extraction skill with Show Extraction Results.** Extraction returns data to the agent. Turn on **Show Extraction Results** too if the user should review what was extracted.
{% endhint %}
## Related pages
* [General skills](/ai-workbench-qore/platform-resources/skill-library/general-skills.md): reasoning, search, code, files, and messages.
* [Skills & Capabilities](/ai-workbench-qore/console/agent-builder/build/skills-and-capabilities.md): every skill on one agent.
***
{% columns %}
{% column width="83.33333333333334%" %}
Maintained by Abhishek Paul
AI-assisted, human-approved
{% endcolumn %}
{% column width="16.666666666666664%" %}
{% endcolumn %}
{% endcolumns %}
---
# 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.uptiq.ai/ai-workbench-qore/platform-resources/skill-library/document-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.
