> For the complete documentation index, see [llms.txt](https://docs.usepylon.com/pylon-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.usepylon.com/pylon-docs/agents/skills.md).
# Skills
Reusable instructions that define how agents handle specific scenarios and take action.
{% hint style="info" %}
Skills are available to workspaces with Agentic features or Skills access. Availability depends on your workspace's plan — contact your account team if you don't see them.
{% endhint %}
Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.
### Creating Skills
The easiest way to create a Skill is with Assist Agent:
1. Work through a real issue or workflow.
2. Refine the investigation steps and desired output.
3. Ask Assist Agent to **turn this into a Skill**.
4. Review the generated instructions.
5. Attach the Skill to the agents that should use it.
You can also create a Skill from the [Skills page](https://app.usepylon.com/settings/ai-controls/skills) or import an existing skill markdown file from another AI tool.
### Using Skills
Once created, Skills can be used across all of Pylon's agents:
* [Assist Agent](https://support.usepylon.com/articles/8245939244-how-does-the-assist-agent-work?lang=en) — invoke a Skill on-demand by typing `/` followed by the Skill name, or just ask the Assist Agent to run it.
* Automations — run Skills automatically when specific events happen or on a recurring schedule.
Agents can also invoke Skills automatically when they detect a matching scenario. Within each agent, you can control which Skills are available.
#### Visibility & Permissions
Skills can be scoped to the entire org or specific teams or team members.
#### Examples
{% hint style="info" %}
Keep Skills small and scenario-specific. Several focused Skills are easier to select, test, and maintain than one large Skill covering unrelated workflows.
{% endhint %}
* A Skill to escalate an issue to engineering by summarizing reproduction instructions and post into a Slack channel or creating a Linear issue
* A Skill to call certain [Connectors](/pylon-docs/agents/connectors.md) to do a deeper investigate for a specific kind of issue
* A Skill to summarize whether a certain feature request got shipped and what the changes included in it were
---
# 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.usepylon.com/pylon-docs/agents/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.
