probability-mean-reversion
GitHub针对Polymarket预测市场的概率均值回归策略，用于识别价格过度反应后的反转机会。通过计算滚动中位数和偏差阈值，在偏离时入场并在回归时离场，同时提供回测验证与风险控制建议。
触发场景
安装
npx skills add Superior-Trade/superior-skills --skill probability-mean-reversion -g -y
SKILL.md
Frontmatter
{
"name": "probability-mean-reversion",
"metadata": {
"updated": 1781654400,
"version": "0.1.0"
},
"description": "Use when a Polymarket outcome appears to overreact and then stall away from recent filled-price range."
}
Strategy: Polymarket · Probability Mean Reversion
When to use
Use this when someone asks for fade, overreaction, mean reversion, range trading, panic buy, euphoria selloff, or probability jumps with weak follow-through.
What the agent should look for
- Canonical Polymarket market from
GET /context/markets?venue=polymarket. - A stable market with enough historical fills.
- Probability significantly far from a rolling median.
- Weak follow-through after the jump.
- No fresh catalyst changing the thesis.
- Enough time before resolution to allow drift back.
Backtest fit with filled data
Moderate fit. Filled TradeTick history can test whether probability moves have a measurable reversion pattern, while using actual fills as the execution proxy.
Limit: backtests cannot validate resting liquidity, spread paid, or what is missed in the maker queue.
Strategy logic
Enter when the outcome trades below a lower band and exit near the rolling median. If your implementation permits, do the inverse for above-band conditions when downside overextension appears.
Nautilus strategy shape
- Keep a rolling window of trade prices.
- Compute median and deviation thresholds.
- Enter only after sufficient tick history is collected.
- Exit on median reversion or max holding ticks.
Example strategyConfig
{
"window_ticks": 40,
"entry_deviation": 0.08,
"exit_deviation": 0.02,
"order_size": 10,
"max_holding_ticks": 80
}
Iteration knobs
| Knob | Effect |
|---|---|
window_ticks |
Larger windows produce a smoother baseline. |
entry_deviation |
Higher values wait for stronger overreactions. |
exit_deviation |
Lower values demand tighter reversion before exit. |
max_holding_ticks |
Prevents stale positions through stale conditions. |
Failure modes
- Real information shocks rarely mean-revert.
- Markets near resolution can trend cleanly to 0 or 1.
- Low liquidity can create fake extremes.
- Backtests may look strong when spread and order-book pressure are ignored.
User-facing framing
"This is an overreaction fade. It works best in noisy markets without new decisive information. I’ll backtest it on filled prices first, then verify trade frequency and liquidity before suggesting live use."
版本历史
-
d6f188f
当前 2026-09-08 20:00
将市场查询 API 从 POST /v3/markets/search 迁移至 GET /context/markets?venue=polymarket，以适配 Unified API。
- 9333090 2026-08-16 16:12
