> For the complete documentation index, see [llms.txt](https://docs.edgetag.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.edgetag.io/mcp/skills/overview.md).

# Overview

Skills are curated instruction sets that teach AI assistants how to work with EdgeTag, ConsentIQ, and Edge Lake. They go beyond what MCP tools provide by giving the AI deep knowledge about implementation patterns, best practices, debugging strategies, and platform-specific guidance.

### Why we built skills

MCP tools give your AI assistant access to live data. Skills give it the knowledge to use that data effectively and help you build, debug, and optimize your EdgeTag implementation.

Without skills, an AI assistant can fetch your analytics data. With skills, it knows:

* How to implement EdgeTag on your specific platform (Shopify, WooCommerce, React, etc.)
* Best practices for event tracking and channel configuration
* How to debug common issues and interpret error messages
* The right SQL patterns for querying Edge Lake
* How consent management works across regions

### Who should use skills

Skills are most valuable for:

* **Developers** implementing EdgeTag on new sites or debugging existing implementations
* **Data analysts** querying Edge Lake for custom analytics and funnel analysis
* **Marketing teams** using AI assistants to understand their consent data and channel performance

### Available skills

Our skills are open source and available at [github.com/blotoutio/skills](https://github.com/blotoutio/skills).

| Skill                                                        | Description                                                                                              |
| ------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------- |
| [EdgeTag](https://docs.edgetag.io/mcp/skills/edgetag.md)     | Comprehensive implementation skill covering the SDK, events, channels, consent, and platform deployments |
| [ConsentIQ](https://docs.edgetag.io/mcp/skills/consentiq.md) | Consent analytics, opt-in/opt-out tracking, and regional compliance monitoring                           |
| [Edge Lake](https://docs.edgetag.io/mcp/skills/edge-lake.md) | Event data lake querying, funnel analysis, attribution reporting, and traffic analysis                   |

{% content-ref url="/pages/0tLAesETECncFs3FmbNy" %}
[Installation](https://docs.edgetag.io/mcp/skills/installation.md)
{% endcontent-ref %}


---

# 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.edgetag.io/mcp/skills/overview.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.
