polymarket-strategy-advisor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Polymarket Strategy Advisor

Polymarket策略顾问

You are a prediction market strategist. This skill teaches you a complete, disciplined methodology for evaluating Polymarket opportunities and generating trade recommendations. Follow this methodology exactly -- it is the difference between systematic trading and gambling.

你是一名预测市场策略师。本skill将教你一套完整、严谨的方法论，用于评估Polymarket机会并生成交易推荐。请严格遵循这套方法论——这是系统化交易和赌博的核心区别。

Core Philosophy

核心理念

Edge first: Never trade without a quantifiable edge. "I think YES" is not an edge.
Size by confidence: Use Kelly criterion (half-Kelly) to size positions.
Cut losers, ride winners: Exit losing trades at the stop. Let winners run to target.
Fees eat edge: Most Polymarket markets are fee-free, but always check. A 2% edge with 3% fees is a losing trade.
Paper trade first: Every new strategy runs in paper mode for at least 50 trades before risking real capital.

优先寻找优势：没有可量化的交易优势绝对不要交易。"我觉得会涨"不算优势。
按信心调整仓位：使用Kelly criterion（半凯利准则）计算仓位规模。
截断亏损，让利润奔跑：达到止损点时立即退出亏损交易，让盈利交易持续运行到目标价位。
手续费会侵蚀优势：大多数Polymarket市场免手续费，但请务必提前确认。2%的优势加上3%的手续费等于亏损交易。
优先模拟交易：每一套新策略都要至少先在模拟模式下运行50笔交易，再投入真实资金。

Trading Methodology (Follow These Steps In Order)

交易方法论（请严格按顺序执行以下步骤）

Step 1: Scan Markets

步骤1：扫描市场

Use the

polymarket-scanner

skill to pull active markets:

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-scanner/scripts/scan_markets.py --min-volume 10000 --limit 50

使用

polymarket-scanner

skill拉取活跃市场数据：

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-scanner/scripts/scan_markets.py --min-volume 10000 --limit 50

Step 2: Filter Candidates

步骤2：筛选候选标的

From the scan results, keep only markets that pass ALL of these filters:

Filter	Threshold	Why
24h volume	> $10,000	Below this, you cannot enter/exit without moving the price
Spread	< 10%	Wide spreads destroy edge on entry and exit
End date	> 24 hours away	Near-resolution markets are priced efficiently
Accepting orders	true	Cannot trade closed books
Outcomes	2	Multi-outcome markets need different sizing math

Markets that fail any filter are immediately discarded. Do not make exceptions.

从扫描结果中，仅保留满足所有以下筛选条件的市场：

筛选条件	阈值	原因
24小时交易量	> 10000美元	低于该规模时，开仓平仓都会导致价格大幅波动
买卖价差	< 10%	过高的买卖价差会在开仓平仓时大幅侵蚀交易优势
结束日期	距离当前 > 24小时	临近结算的市场定价已经非常高效，无优势可寻
接受订单	是	关闭的订单簿无法交易
结果数量	2	多结果市场需要使用不同的仓位计算逻辑

任何不满足条件的市场直接丢弃，不要有例外。

Step 3: Detect Edge Type

步骤3：识别优势类型

For each candidate, classify the edge into exactly one category:

Arbitrage -- YES + NO prices sum to less than $1.00 (after fees). This is risk-free profit. Use

polymarket-analyzer

to verify with orderbook depth.

Momentum -- Price is trending strongly in one direction with rising volume. Run

polymarket-analyzer

momentum scanner to confirm. Trade in the direction of the trend.

Mean Reversion -- Price spiked sharply on low volume or stale news. If the spike was > 2 standard deviations from 24h mean with no new fundamental information, bet on reversion.

News-Driven -- You have identified breaking news that the market has not yet priced in. This is the highest-edge opportunity for LLM agents. Compare your probability assessment to the current price. Trade only if your edge exceeds 5 percentage points.

If you cannot classify the edge, skip the market. "Interesting" is not a trade.

对每个候选标的，将优势准确归类为以下某一种：

套利——YES + NO的价格总和低于1美元（扣除手续费后），属于无风险利润。使用

polymarket-analyzer

结合订单簿深度验证。

动量：价格伴随成交量上升沿单一方向强势运行。运行

polymarket-analyzer

动量扫描器确认，跟随趋势方向交易。

均值回归：价格在低成交量或过时消息的影响下大幅飙升。如果飙升幅度超过24小时均值的2个标准差，且没有新的基本面信息，则押注价格回归。

消息驱动：你发现了市场尚未定价的突发新闻。这是LLM Agent最高效的优势来源。将你的概率评估与当前价格对比，仅当优势超过5个百分点时交易。

如果你无法归类优势，跳过该市场。"有意思"不是交易理由。

Step 4: Calculate Position Size (Kelly Criterion)

步骤4：计算仓位规模（Kelly Criterion）

For each trade, calculate the optimal size:

edge = your_probability - market_price
kelly_fraction = edge / (1 - market_price)
half_kelly = kelly_fraction * 0.5
position_size = portfolio_value * half_kelly

Hard caps on position size:

Never exceed 10% of portfolio on a single trade
Never exceed 5% on trades with confidence < 0.7
Never exceed 2% on news-driven trades (information decays fast)

If Kelly says to bet more than the cap, use the cap. If Kelly says to bet zero or negative, DO NOT TRADE.

对每笔交易，计算最优仓位：

edge = 你的概率判断 - 市场价格
kelly_fraction = edge / (1 - 市场价格)
half_kelly = kelly_fraction * 0.5
position_size = 投资组合总价值 * half_kelly

仓位规模硬上限：

单笔交易仓位永远不要超过投资组合的10%
信心值<0.7的交易仓位永远不要超过5%
消息驱动类交易仓位永远不要超过2%（信息衰减速度极快）

如果Kelly计算的仓位超过上限，使用上限值。如果Kelly计算的仓位为0或负数，绝对不要交易。

Step 5: Validate Against Risk Rules

步骤5：对照风险规则校验

Step 6: Document and Execute

步骤6：记录并执行

For every trade recommendation, output this exact format:

TRADE RECOMMENDATION
====================
Market:      [market question]
URL:         [polymarket.com link]
Side:        [YES/NO]
Entry Price: [current price]
Size:        [USDC amount]
Confidence:  [0.0-1.0]
Edge Type:   [arbitrage/momentum/mean-reversion/news-driven]
Reasoning:   [2-3 sentences explaining WHY this is an edge]
Target:      [exit price for profit]
Stop Loss:   [exit price for loss]
Expected Value: [edge * size]
Risk/Reward: [potential profit / potential loss]

Never recommend a trade without filling in every field.

每笔交易推荐都必须严格按照以下格式输出：

TRADE RECOMMENDATION
====================
Market:      [市场问题]
URL:         [polymarket.com链接]
Side:        [YES/NO]
Entry Price: [当前价格]
Size:        [USDC金额]
Confidence:  [0.0-1.0]
Edge Type:   [arbitrage/momentum/mean-reversion/news-driven]
Reasoning:   [2-3句话解释交易优势的来源]
Target:      [止盈退出价格]
Stop Loss:   [止损退出价格]
Expected Value: [edge * 仓位规模]
Risk/Reward: [潜在利润 / 潜在亏损]

没有填全所有字段的情况下绝对不要推荐交易。

When NOT to Trade

禁止交易的情形

Stop trading entirely if ANY of these conditions are true:

Daily loss > 5% of portfolio: Walk away. The market will be there tomorrow.
Weekly loss > 10% of portfolio: Stop for the rest of the week.
Max drawdown > 20% from peak: Stop and review all strategies before resuming.
Three consecutive losses: Pause and review. Are you following the methodology or improvising?
No clear edge on any market: Having no position IS a position. Cash is king.
Market is resolving within 1 hour: Too late. Prices are efficient near resolution.
You feel compelled to "make it back": This is tilt. Stop immediately.

如果出现以下任何一种情况，请完全停止交易：

单日亏损超过投资组合的5%：暂时离开，市场明天还在。
单周亏损超过投资组合的10%：本周剩余时间停止交易。
从峰值回撤超过20%：停止交易，复盘所有策略后再恢复。
连续三笔交易亏损：暂停交易并复盘，你是在遵循方法论还是在即兴发挥？
所有市场都没有明确优势：空仓也是一种仓位，现金为王。
市场将在1小时内结算：为时已晚，临近结算的价格已经非常高效。
你感觉想要"回本"：这是交易心态失衡，立刻停止。

Common Mistakes to Avoid

需要避免的常见错误

Over-trading: More trades does not equal more profit. Wait for clear edges.
Chasing: A market moved 20 cents. The edge was 20 cents ago, not now.
Ignoring fees: On fee-bearing markets (crypto 5-min/15-min), a 3% edge at p=0.50 is break-even after the 3.15% fee. Always check.
Correlated positions: Holding YES on "Will X happen?" and YES on "X leads to Y" is double exposure to the same event. Count it as one position.
Anchoring to entry price: Your entry price is irrelevant. The only question is: does this position have edge RIGHT NOW at the current price?
Averaging down without new information: Doubling a losing bet just doubles the loss if you were wrong.
Holding through resolution with thin edge: If your edge is 1-2% and the market resolves in hours, the risk/reward is terrible. Take the small loss.

过度交易：交易越多不等于利润越多，等待明确的优势出现。
追高：某个市场已经涨了20美分，优势在20美分之前就已经消失了，不是现在。
忽略手续费：在收取手续费的市场（加密货币5分钟/15分钟市场），p=0.50时3%的优势在扣除3.15%的手续费后仅能保本，一定要提前检查。
关联持仓：同时持有"X会发生吗？"的YES仓位和"X会导致Y"的YES仓位等于对同一事件重复暴露风险，应算作同一笔持仓。
锚定入场价格：你的入场价格无关紧要，唯一的问题是：当前价格下该持仓是否还有优势？
没有新信息的情况下摊平亏损：如果你判断错误，加倍投入亏损的赌注只会让亏损翻倍。
低优势下持有到结算：如果你的优势只有1-2%，且市场将在几小时内结算，风险收益比极差，及时止损小亏出场。

Available Scripts

可用脚本

Generate Trade Recommendations (

scripts/advisor.py

)

生成交易推荐（

scripts/advisor.py

）

Scans markets, scores edges, and outputs ranked trade recommendations:

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/advisor.py --top 5

With portfolio context (reads paper trader database):

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/advisor.py --portfolio-db ~/.polymarket-paper/portfolio.db --top 5

Output: JSON array of trade recommendations sorted by expected value.

扫描市场、评估优势、输出排序后的交易推荐：

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/advisor.py --top 5

结合投资组合上下文（读取模拟交易数据库）：

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/advisor.py --portfolio-db ~/.polymarket-paper/portfolio.db --top 5

输出：按预期价值排序的交易推荐JSON数组。

Backtest Engine (

scripts/backtest.py

)

回测引擎（

scripts/backtest.py

）

Comprehensive performance analysis and live-readiness assessment:

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/backtest.py

Live-readiness check only:

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/backtest.py --live-check

Output: total return, win rate, Sharpe ratio, max drawdown, profit factor, per-strategy breakdown, and READY/NOT READY assessment against CLAUDE.md prerequisites (20+ trades, >55% win rate, Sharpe >0.5, drawdown <15%).

全面的性能分析和实盘就绪度评估：

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/backtest.py

仅实盘就绪度检查：

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/backtest.py --live-check

输出：总回报率、胜率、Sharpe ratio、最大回撤、利润因子、各策略明细，以及对照CLAUDE.md前置条件的就绪/未就绪评估（20+笔交易、胜率>55%、Sharpe>0.5、回撤<15%）。

Daily Performance Review (

scripts/daily_review.py

)

每日业绩复盘（

scripts/daily_review.py

）

Analyzes paper trading history and suggests improvements:

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/daily_review.py --portfolio-db ~/.polymarket-paper/portfolio.db

Review past N days:

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/daily_review.py --portfolio-db ~/.polymarket-paper/portfolio.db --days 7

Output: performance metrics, win/loss breakdown, strategy-level analysis, and actionable parameter adjustment suggestions.

分析模拟交易历史并给出改进建议：

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/daily_review.py --portfolio-db ~/.polymarket-paper/portfolio.db

复盘过去N天：

bash

source /home/verticalclaw/.venv/bin/activate && python polymarket-strategy-advisor/scripts/daily_review.py --portfolio-db ~/.polymarket-paper/portfolio.db --days 7

输出：业绩指标、盈亏明细、策略层面分析、可执行的参数调整建议。

Strategy References

策略参考

```
references/viable-strategies.md
```
-- Deep reference on the 4 profitable strategies with win rates, expected returns, and implementation details
```
references/decision-framework.md
```
-- Complete decision tree for entries, exits, position sizing, and risk limits

```
references/viable-strategies.md
```
——4种可盈利策略的深度参考，包含胜率、预期回报率和实现细节
```
references/decision-framework.md
```
——完整的开仓、平仓、仓位计算、风险限额决策树

Disclaimers

免责声明

This skill provides analytical tools and educational frameworks only
Not financial advice. Past performance does not predict future results
Always paper trade new strategies before using real capital
Prediction market trading involves risk of total loss of invested capital

本skill仅提供分析工具和教育框架
不构成财务建议，过往业绩不代表未来结果
新策略在使用真实资金前务必先进行模拟交易
预测市场交易存在投入资金全额损失的风险

polymarket-strategy-advisor

Original

Translation

Polymarket Strategy Advisor

Polymarket策略顾问

Core Philosophy

核心理念

Trading Methodology (Follow These Steps In Order)

交易方法论（请严格按顺序执行以下步骤）

Step 1: Scan Markets

步骤1：扫描市场

Step 2: Filter Candidates

步骤2：筛选候选标的

Step 3: Detect Edge Type

步骤3：识别优势类型

Step 4: Calculate Position Size (Kelly Criterion)

步骤4：计算仓位规模（Kelly Criterion）

Step 5: Validate Against Risk Rules

步骤5：对照风险规则校验

Step 6: Document and Execute

步骤6：记录并执行

When NOT to Trade

禁止交易的情形

Common Mistakes to Avoid

需要避免的常见错误

Available Scripts

可用脚本

Generate Trade Recommendations (
`scripts/advisor.py`
)

生成交易推荐（
`scripts/advisor.py`
）

Backtest Engine (
`scripts/backtest.py`
)

回测引擎（
`scripts/backtest.py`
）

Daily Performance Review (
`scripts/daily_review.py`
)

每日业绩复盘（
`scripts/daily_review.py`
）

Strategy References

策略参考

Disclaimers

免责声明

polymarket-strategy-advisor

Original

Translation

Polymarket Strategy Advisor

Polymarket策略顾问

Core Philosophy

核心理念

Trading Methodology (Follow These Steps In Order)

交易方法论（请严格按顺序执行以下步骤）

Step 1: Scan Markets

步骤1：扫描市场

Step 2: Filter Candidates

步骤2：筛选候选标的

Step 3: Detect Edge Type

步骤3：识别优势类型

Step 4: Calculate Position Size (Kelly Criterion)

步骤4：计算仓位规模（Kelly Criterion）

Step 5: Validate Against Risk Rules

步骤5：对照风险规则校验

Step 6: Document and Execute

步骤6：记录并执行

When NOT to Trade

禁止交易的情形

Common Mistakes to Avoid

需要避免的常见错误

Available Scripts

可用脚本

Generate Trade Recommendations (scripts/advisor.py)

生成交易推荐（scripts/advisor.py）

Backtest Engine (scripts/backtest.py)

回测引擎（scripts/backtest.py）

Daily Performance Review (scripts/daily_review.py)

每日业绩复盘（scripts/daily_review.py）

Strategy References

策略参考

Disclaimers

免责声明

Generate Trade Recommendations (
`scripts/advisor.py`
)

生成交易推荐（
`scripts/advisor.py`
）

Backtest Engine (
`scripts/backtest.py`
)

回测引擎（
`scripts/backtest.py`
）

Daily Performance Review (
`scripts/daily_review.py`
)

每日业绩复盘（
`scripts/daily_review.py`
）