> For the complete documentation index, see [llms.txt](https://coldbox.ortusbooks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://coldbox.ortusbooks.com/getting-started/agentic-development/skills-and-guidelines.md).

# Skills & Guidelines

AI guidelines and 200+ skills from skills.boxlang.io — on-demand knowledge for your coding agents.

ColdBox's AI integration splits agent knowledge into two complementary pieces: **guidelines** (always-relevant conventions) and **skills** (on-demand task cookbooks). Both live in your project's `.agents/` directory.

## Guidelines

Guidelines teach agents framework conventions and architectural patterns. Three core guidelines ship with the CLI:

| Guideline | Covers                                                   |
| --------- | -------------------------------------------------------- |
| `coldbox` | ColdBox architecture, handlers, routing, DI, conventions |
| `boxlang` | BoxLang syntax, classes, lambdas, BIFs                   |
| `cfml`    | CFML fundamentals for Adobe/Lucee projects               |

Module-provided guidelines are auto-discovered: install `qb` or `cbsecurity` and their guidelines appear in `.agents/guidelines/modules/` after `coldbox ai refresh`.

```bash
coldbox ai guidelines list --verbose    # What's installed
coldbox ai guidelines add qb cbsecurity # Add specific guidelines
coldbox ai guidelines override coldbox  # Customize a core guideline locally
```

## Skills

Skills are step-by-step implementation cookbooks sourced from the central registry at [**skills.boxlang.io**](https://skills.boxlang.io) — 200+ skills covering ColdBox, BoxLang, CommandBox, TestBox, and the module ecosystem.

Unlike guidelines, skills are **inventoried, not loaded**: your agent sees a catalog of skill names and descriptions, and reads a skill's `SKILL.md` only when the task calls for it. That keeps base context lean while deep knowledge stays one `read_file` away.

```bash
coldbox ai skills list --verbose   # Browse installed skills
coldbox ai skills find <term>      # Search the registry
coldbox ai skills install <slug>   # Install from the registry
coldbox ai skills refresh          # Sync with installed modules
```

Examples of what agents can pull on demand: building CRUD handlers, REST APIs, integration tests, scheduled tasks, migrations, validation constraints, and BoxLang runtime deployment recipes.

## For Module Authors

Bundle AI resources in your own module by adding `.agents/guidelines/` and `.agents/skills/` to it — the CLI auto-discovers them for every consumer of your module. Scaffold them with:

```bash
coldbox create module myModule --ai
```

Full authoring workflow: [Agentic ColdBox](/ai/agentic-coldbox.md).

## See Also

* [ColdBox CLI AI Setup](/getting-started/agentic-development/coldbox-cli-ai-setup.md)
* [BoxLang IDE](/getting-started/agentic-development/boxlang-ide.md)


---

# 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://coldbox.ortusbooks.com/getting-started/agentic-development/skills-and-guidelines.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.