> For the complete documentation index, see [llms.txt](https://atlas.anywhere.now/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://atlas.anywhere.now/use/monitor-and-report/dialogue-workspace/skills.md).

# Monitor skills and queues in Dialogue Workspace

Monitor real-time queue health by skill in Dialogue Workspace.

The **Skills** page helps supervisors monitor real-time queue health per skill. Use it to identify skills with long wait times, low service level, or insufficient agent coverage.

Use the **Contact centers** selector to switch between one contact center and **All** contact centers.

![Dialogue Workspace skills](https://67037690-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkDTnqL8OqnJFQgFg9eQ6%2Fuploads%2Fgit-blob-ab977c8477160852d3bf5799a4222e377321453d%2Fdialogue-workspace-skills.png?alt=media)

## Summary cards

| Card                  | What it shows                                                                   |
| --------------------- | ------------------------------------------------------------------------------- |
| **Longest wait time** | Highest current wait time, including the skill where it occurs.                 |
| **Lowest SLA**        | Lowest current service-level percentage, including the skill where it occurs.   |
| **Total waiting**     | Total number of contacts currently waiting across the selected contact centers. |
| **Total handled**     | Total number of handled contacts in the current view.                           |

**Service level** is queued inbound dialogues answered within the service-level threshold, divided by queued inbound dialogues that were accepted or abandoned. If no threshold is available from the contact-center settings, Dialogue Workspace falls back to 20 seconds.

## Skill table

The skill table lists skills and their real-time operational metrics. Use the **Filter** field above the table to find a skill.

Select **Customize columns** to show or hide columns based on what you want to monitor.

| Column             | What it shows                                        |
| ------------------ | ---------------------------------------------------- |
| **Skill**          | Skill name.                                          |
| **SLA %**          | Current service-level percentage for the skill.      |
| **Waiting**        | Number of contacts currently waiting for this skill. |
| **LWT**            | Longest waiting time for this skill.                 |
| **Handled**        | Number of contacts handled in the current view.      |
| **Abandoned**      | Number of contacts abandoned in the current view.    |
| **Opted-in**       | Number of opted-in agents for the skill.             |
| **Assigned**       | Agents assigned to the skill.                        |
| **Available**      | Opted-in agents currently available.                 |
| **In a call**      | Opted-in agents currently in a call.                 |
| **Contact center** | Contact center associated with the skill or row.     |

## Tips

* Sort by **Waiting** or **LWT** to spot emerging queue issues quickly.
* If service level drops for a skill, check agent coverage, such as **Available** and **In a call**.


---

# 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://atlas.anywhere.now/use/monitor-and-report/dialogue-workspace/skills.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.