> For the complete documentation index, see [llms.txt](https://developer.emporix.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.emporix.io/agentic-commerce-intelligence/agentic-engineering/skill-library/emporix-docs-navigation.md).

# Emporix Docs Navigation

Use the emporix-docs-navigation skill to find and verify answers in Emporix documentation from primary sources.

Use the **emporix-docs-navigation** skill when an assistant must answer from published Emporix documentation, not from model memory. It picks the right surface for the question, then checks that the page is real and still current.

{% hint style="info" %}
This page explains when to use the skill and how to work with it. For the ingestion options themselves, see [Documentation Optimization for LLM Ingestion](/agentic-commerce-intelligence/agentic-engineering/docs-for-ai.md).
{% endhint %}

## Skill details

| Property     | Value                                                   |
| ------------ | ------------------------------------------------------- |
| Skill name   | `emporix-docs-navigation`                               |
| Package path | `skills/emporix-docs-navigation/` (contains `SKILL.md`) |

Install it once using [Installing skills](/agentic-commerce-intelligence/agentic-engineering/skill-library.md#installing-skills).

## When to use it

Use this skill when you need to:

* Answer a question about Emporix APIs or platform behavior from a primary source
* Locate the right documentation page or OpenAPI spec
* Check whether platform behavior changed recently
* Tell a real page from a "Page Not Found" response

{% hint style="info" %}
Calling tenant APIs still requires the [Emporix Auth](/agentic-commerce-intelligence/agentic-engineering/skill-library/emporix-auth.md) skill. The hosted commerce MCP at `api.emporix.io/mcp` is not a documentation source.
{% endhint %}

## How it works

All Emporix documentation is published at `https://developer.emporix.io`. The API reference on that portal is rendered from `emporix/api-references`, but the portal also contains Commerce Engine, Orchestration Engine, Agentic Commerce Intelligence, and storefront guides that are not in that repository.

| You need                             | Use                                                                                                    |
| ------------------------------------ | ------------------------------------------------------------------------------------------------------ |
| A map of pages                       | [`llms.txt`](https://developer.emporix.io/llms.txt) – titles, descriptions, and links, not page bodies |
| One page as Markdown                 | The page URL with `.md` appended                                                                       |
| A direct answer with sources         | The page `.md` URL plus an `ask` query                                                                 |
| Search from an agent                 | Documentation MCP at `https://developer.emporix.io/~gitbook/mcp`                                       |
| Exact endpoints, schemas, and scopes | The service `api.yml` in `emporix/api-references`                                                      |
| Whether something changed            | The [changelog](https://developer.emporix.io/changelog/changelog.md)                                   |

## Prerequisites

Before you use this skill, make sure you have:

* Outbound HTTPS from the agent – no tenant and no API credentials
* An MCP-capable agent, only if you want the documentation MCP route

## How to use it

After install, work in your AI tool with natural-language requests. Examples:

> Which page documents cart creation, and quote the required scopes from the OpenAPI spec?

> Has the availability endpoint path changed recently? Check the changelog before you answer.

> This URL says Page Not Found. Find the current page for the same topic.

## Usage notes

* A missing portal page can return HTTP 200. Treat a body that starts with "Page Not Found" as a miss, and do not cite it.
* `llms.txt` proves a page exists. Fetch the page, or the OpenAPI spec, before you state what it says.
* Do not conclude that a topic is undocumented because it is absent from `emporix/api-references`. Check the portal index.
* Prefer the changelog when a guide and a recent change disagree.


---

# 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://developer.emporix.io/agentic-commerce-intelligence/agentic-engineering/skill-library/emporix-docs-navigation.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.