# Pm Agent Strategy Authoring

Turn an LLM- or tool-driven idea into AgentStrategy code and evaluate it with paper...

- Repository: https://github.com/YichengYang-Ethan/oracle3-prediction-market-agent (560 stars)
- Category: AI and agents
- License: Apache-2.0
- Last updated: 2026-10-12
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add YichengYang-Ethan/oracle3-prediction-market-agent --skill pm-agent-strategy-authoring -g -a claude-code -y`
Codex: `npx skills add YichengYang-Ethan/oracle3-prediction-market-agent --skill pm-agent-strategy-authoring -g -a codex -y`
Cursor: `npx skills add YichengYang-Ethan/oracle3-prediction-market-agent --skill pm-agent-strategy-authoring -g -a cursor -y`
Gemini CLI: `npx skills add YichengYang-Ethan/oracle3-prediction-market-agent --skill pm-agent-strategy-authoring -g -a gemini-cli -y`

## Description

Turn an LLM- or tool-driven idea into AgentStrategy code and evaluate it with paper trading.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# PM Agent Strategy Authoring

Use this skill when the user asks for a strategy that makes decisions with an LLM, MCP tools or external APIs.

## Goals

- A runnable strategy class (an `AgentStrategy` subclass).
- `strategy validate` and `paper run` both succeed.
- No parameter grid search: agent strategies cannot be auto-tuned.

## Code entry points

- Base class contract: `oracle3/strategy/agent_strategy.py` (`AgentStrategy`).
- LLM strategy reference: `oracle3/strategy/simple_strategy.py`.
- New strategies go in `strategies/`.

## Steps

1. Create the skeleton

- `oracle3 strategy create --output strategies/<name>.py --class-name <ClassName> --type agent`

2. Implement the strategy

- Call the LLM, MCP tools or external APIs inside `process_event`.
- Non-determinism is fine: results may differ between calls.
- Write the LLM output into the reasoning field with `self.record_decision(reasoning=...)` so it can be monitored.
- Call `trader.place_order(...)` to act.
- Guard every decision with `self.is_paused()` to respect the control plane.

3. Quick validation

- `oracle3 strategy validate --strategy-ref strategies/<name>.py:<ClassName> --dry-run --events 10 --json`

4. Evaluate with paper trading (the right way to evaluate agent strategies)

- `oracle3 paper run --strategy-ref strategies/<name>.py:<ClassName> --monitor`
- Watch decisions and positions with `oracle3 trade status --json`.
- Take a full snapshot with `oracle3 trade state --json`.

5. Intervene and adjust

- `oracle3 trade pause` / `oracle3 trade resume`
- Hot-swap the strategy with `oracle3 trade swap --strategy-ref strategies/<new>.py:<NewClass>`.

## Hard rules

The rest: https://github.com/YichengYang-Ethan/oracle3-prediction-market-agent/blob/HEAD/.claude/skills/pm-agent-strategy-authoring/SKILL.md