Developer Overview

The developer side of Orien AI is built around two extension systems:

• Skills for strategy logic
• MCP servers for AI Chat tool extension

Skills are the strategy modules that power pipeline agents and integrated agents. MCP servers are the tool modules that power AI Chat.

Design Direction

The current product direction is code-first and execution-aware.

• Skills should be explicit about the tools they use
• Strategy logic should be inspectable and testable
• Prompting can assist authoring, but it is not the primary execution contract

Developer Model

Developers can contribute to the Orien ecosystem in two different ways:

Build a Skill

Use Skills when you want to define:

• trading logic
• factors and signal combinations
• risk-aware execution behavior
• reusable strategy packages
• AI-generated quantitative code or LLM-assisted pipeline scaffolding

Build an MCP Server

Use MCP when you want to define:

• chat-usable tools
• external data providers
• reusable operator capabilities for AI Chat
• tool-side marketplace modules

What’s in a Skill?

A Skill package is typically structured like this:

my-skill/
├── SKILL.md
├── orien.runtime.yaml
└── scripts/
    └── strategy.py

Strategy Models

Python Skills

Python is the primary path for authoring strategy logic. It gives direct access to market data, analysis libraries, and execution tools.

async def get_market_data(symbol: str) -> dict:
    """Fetch market state for the current cycle."""
    async with httpx.AsyncClient() as client:
        response = await client.get(f"https://api.exchange.com/ticker/{symbol}")
        return response.json()

Rust Components

Rust can be used where deterministic behavior, lower-level control, or performance-sensitive logic is needed.

Prompt-Assisted Authoring

Prompting is useful for scaffolding and refinement. In the current architecture, its role is to help generate strategy structure, not to replace inspectable execution logic.

Runtime Phases

Skills map tools into four runtime phases:

[!NOTE] The phase contract keeps analysis and execution separated. A tool used for observation or planning cannot silently become an execution path.

Product Fit

Well-designed Skills fit naturally into the broader product architecture:

• Operator layer — Surfaces the strategy through AI Chat or automation consoles
• Strategy layer — Runs the Skill inside a structured agent cycle
• Trading OS — Supplies data, execution, and wallet primitives

The same architectural logic applies to MCP servers on the AI Chat side: they extend the interface layer without creating a second execution core.

Next Steps

• Skill Structure — Detailed breakdown of the package format
• Build an MCP Server — MCP market and server model
• orien.runtime.yaml Reference — Runtime contract reference
• Tool Development — Writing tool functions
• Publishing — Submit to the Skills Market