> For the complete documentation index, see [llms.txt](https://docs.deryve.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.deryve.xyz/ai-agent/models-and-skill-packs.md).

# Models and skill packs

A skill pack defines how a model evaluates Deryve context. It sets a trading style, preferred strategies, requested modules, and no-trade threshold.

### Recommended starting point

**Claude Sonnet 4.6** is the recommended general-purpose model. Its adaptive framework classifies the regime, selects a matching strategy, filters for confluence, then sizes proportionally to confidence.

### Choose by objective

| Objective                 | Model profile                                |
| ------------------------- | -------------------------------------------- |
| Fast signal screening     | Claude Haiku 4.5 or Gemini 2.5 Flash         |
| Conservative filtering    | Gemini 2.5 Flash Lite                        |
| General adaptive analysis | Claude Sonnet 4.6                            |
| Deep multi-factor review  | Claude Opus 4.8, o-series, or Gemini 2.5 Pro |
| Breakout focus            | Llama 4 Maverick                             |
| Mean reversion focus      | Qwen 2.5 72B                                 |
| Price-action focus        | Mistral Large                                |
| Technical confluence      | DeepSeek V3.2 or DeepSeek R1                 |

### Available providers

Deryve supports models from Anthropic, OpenAI, Google, DeepSeek, Meta, Mistral, Qwen, and xAI. Model availability, latency, and output quality can vary.

### Skill-pack behavior

A pack can prefer trend continuation, breakout confirmation, mean reversion, or multi-factor evaluation. It can also set a high no-trade threshold. That threshold encourages restraint when evidence is weak.

Switching models affects the next analysis cycle. It does not modify existing positions or bypass agent limits.

{% hint style="info" %}
Compare models over enough trades and comparable regimes. A single winning trade does not validate a model choice.
{% endhint %}


---

# 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://docs.deryve.xyz/ai-agent/models-and-skill-packs.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.