Polymarket Temperature Event Follower

What it does

When your agent uses it

• Tasks that involve Agent memory

Example prompts

• “/polymarket-temperature-event-follower”

Requirements

• Python 3
• A credential in PRIVATE_KEY
• A credential in POLY_API_KEY

Workflow steps

10 steps, taken from the step headings in SKILL.md.

1. 1项目概述 / Project Overview
2. 2快速开始（5分钟）/ Quick Start (5 min)
3. 3准备工作 / Preparation
4. 4API 密钥获取教程 / API Key Tutorial
5. 5配置文件详解 / Configuration
6. 6代码参数详解（sniper.py 常量）
7. 7启动指南 / Launch Guide
8. 8安全建议 / Security Best Practices
9. 9故障排查 / Troubleshooting
10. 10FAQ 常见问题

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • pip
  • python3
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • gamma-api.polymarket.com
  • clob.polymarket.com
  • skillpay.me

  Also links to:

  • polymarket.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • PRIVATE_KEY
  • POLY_API_KEY
  • POLY_API_SECRET

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Polymarket Temperature Event Follower loads about 3.6k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 820 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~77

When it runs · the whole SKILL.md, loaded when a task matches

~3.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:24

  5. [配置文件详解 (.env)](#5)

• NoteMentions a .env fileSKILL.md:85

  copy .env.example .env

• NoteMentions a .env fileSKILL.md:86

  # 然后编辑 .env 文件，填入你的密钥（见第4节）

• NoteMentions a .env fileSKILL.md:210

  所有配置通过**环境变量**（`.env` 文件）管理。

• NoteMentions a .env fileSKILL.md:212

  ### 5.1 创建 `.env` 文件

• NoteMentions a .env fileSKILL.md:214

  在项目根目录创建文件 `.env`，内容如下：

• NoteMentions a .env fileSKILL.md:359

  除了 `.env` 配置，代码中还有一些**硬编码常量**需要了解：

• NoteMentions a .env fileSKILL.md:414

  # 1. 确保 .env 已配置

• NoteMentions a .env fileSKILL.md:491

  echo ".env" >> .gitignore

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 820 words, ~3,577 tokens.

name

polymarket-temperature-event-follower

description

Automated trader for Polymarket weather highest temperature markets. Scans global weather markets and executes buys during local morning window (9-10 AM) when YES price is favorable. Built for SkillPay billing integration with robust error handling and state persistence.

metadata.author

stefantaylor5

metadata.version

1.0.1

metadata.displayName

Polymarket Temperature Event Follower

metadata.difficulty

intermediate

metadata.tags

polymarket, weather, trading, sniper, event-driven

假设：每日最高温通常出现在下午14:00-15:00（气象学原理）
逻辑：
  1. 上午10:00后，官方气温预报已发布，市场不确定性降低
  2. 当 YES token 价格低于 0.35 时，认为市场低估了"高温"概率
  3. 以固定金额（默认 $1.0）买入，等待气温确定后价格上涨
  4. 可在价格上涨后卖出，或持有至结算（自动按 $1.0 或 $0.0 结算）

# 1. 克隆/进入项目目录（你已经在了）
cd C:\Users\19154\Desktop\skill

# 2. 安装依赖（全程约 2 分钟）
pip install -r requirements.txt

# 3. 复制环境变量模板
copy .env.example .env
# 然后编辑 .env 文件，填入你的密钥（见第4节）

# 4. 测试运行（模拟模式，不花钱）
python sniper.py --dry-run --once

# 5. 看到扫描输出后，说明安装成功！
# 6. 真实交易（谨慎！）
python sniper.py --live --once

# 检查 Python 版本（需要 3.9+）
python --version
# 预期输出: Python 3.10.x 或 3.11.x 或 3.12.x

# 检查 pip
pip --version

# Windows
python -m venv venv
venv\Scripts\activate

# macOS/Linux
python3 -m venv venv
source venv/bin/activate

python-dotenv>=1.0.0
requests>=2.31.0
aiohttp>=3.9.0
pytz>=2024.1
eth-account>=0.11.0
py-clob-client>=0.2.0  # Polymarket 官方客户端（实盘必需）

pip install -r requirements.txt

# ============================================
# 必填：Polymarket 认证
# ============================================
PRIVATE_KEY=0xsk_your_private_key_here_64_hex_chars
PROXY_WALLET=0x1234567890123456789012345678901234567890
POLY_API_KEY=pk_live_xxxxxxxxxxxxxxxxxxxx
POLY_API_SECRET=sk_live_xxxxxxxxxxxxxxxxxxxx
POLY_API_PASSPHRASE=your_passphrase_here
SIGNER_TYPE=1  # 1=邮箱账户, 2=metamask注册的polymarket账户

# ============================================
# 交易参数（建议保持默认）
# ============================================
TRADE_AMOUNT_USD=1.0          # 每笔下单金额（美元）
MIN_ORDERBOOK_SIZE=1.0        # 最小订单簿深度（流动性过滤）
SLIPPAGE_TOLERANCE=0.15       # 滑点容忍度（15%）
ENTRY_THRESHOLD=0.35          # 入场阈值（YES token 价格 < 0.35 才买入）
MAX_COST_PER_TRADE=1.2        # 单笔最大成本（超出则不买）

# ============================================
# 时间窗口（本地时间，UTC+8）
# ============================================
MONITOR_START_HOUR=9          # 监控开始时间（小时，小数形式）
MONITOR_END_HOUR=9.9167       # 监控结束时间（9:55 = 9 + 55/60 = 9.9167）
FALLBACK_START_HOUR=10        # Fallback 开始时间
FALLBACK_WINDOW_MINUTES=5     # Fallback 窗口长度（分钟）

# ============================================
# 执行频率（秒）
# ============================================
CHECK_INTERVAL=300            # 扫描间隔（300秒 = 5分钟）
REPORT_INTERVAL=240           # 报告间隔（240秒 = 4分钟）

# ============================================
# 缓存与重试
# ============================================
CACHE_TTL=3600                # 通用缓存时间（1小时）
GAMMA_CACHE_TTL=300           # Gamma API 缓存（5分钟）
CLOB_CACHE_TTL=30             # CLOB 订单簿缓存（30秒）
MAX_CONCURRENT_REQUESTS=50    # 最大并发请求数
REQUEST_DELAY=0.05            # 请求间延迟（秒）
MAX_RETRIES=3                 # 最大重试次数（网络失败时）
RETRY_DELAY=1.0               # 重试延迟（秒）

# ============================================
# 文件路径
# ============================================
STATE_FILE=state.json         # 状态文件（持仓、交易历史）
CACHE_DIR=cache               # 缓存目录

假设 TRADE_AMOUNT_USD = 1.0, best_ask = 0.5
目标 shares = 1.0 / 0.5 = 2.0 shares
实际 cost = 0.5 × 2.0 = $1.0 OK

假设 best_ask = 0.6, 但 max_price = 0.6 × 1.15 = 0.69
如果 0.6 < 0.69 → 仍可买入
如果 0.7 > 0.69 → 跳过（滑点过大）

# 城市列表（33个）
CITY_SLUGS = [
    "taipei", "seoul", "shanghai", "shenzhen", "wuhan", "beijing", "chongqing",
    "tokyo", "singapore", "hong-kong", "tel-aviv", "lucknow",
    "london", "warsaw", "paris", "milan", "madrid", "munich", "ankara",
    "atlanta", "nyc", "toronto", "miami", "chicago", "dallas", "seattle",
    "wellington", "buenos-aires", "sao-paulo",
    "denver", "houston", "austin", "san-francisco",
]

# 时区映射（自动将本地时间转为 UTC）
TIMEZONES = {
    "nyc": "America/New_York",
    "tokyo": "Asia/Tokyo",
    "london": "Europe/London",
    # ... 共 33 个时区定义
}

GAMMA_API_BASE = "https://gamma-api.polymarket.com"
CLOB_API_BASE = "https://clob.polymarket.com"
BILLING_URL = "https://skillpay.me/api/v1/billing"

python sniper.py [OPTIONS]

选项：
  --dry-run          扫描但不实际下单（默认模式）
  --once             只运行一次扫描后退出（调试用）
  --status           显示当前持仓和统计信息
  --live             启用真实交易（需要已配置所有 API 凭证）

# 1. 确保 .env 已配置
# 2. 运行模拟模式（不花钱、不下单）
python sniper.py --dry-run --once

# 预期输出：
# [AUTH] Loaded credentials...
# [SCAN] Starting scan...
# [SCAN] Tradeable in monitor window: X
# [BUY] Triggered: ... (如果触发条件满足)
# [DRY] Would buy 1 share @ $0.45 (max: $0.52)
# [OK] State saved, exiting.

python sniper.py --status

Positions:
  - tokyo_2026-03-26: entry_price=0.45, shares=2.22, PnL=$0.12
  - london_2026-03-26: entry_price=0.52, shares=1.92, PnL=-$0.08

Stats:
  Total trades: 5
  Total PnL: $0.45
  Billing cost: 0.05 USDT

# 方式 A：前台运行（用于测试）
python sniper.py --live --once

# 方式 B：后台持续运行（推荐）
# Windows (使用 start)
start /B python sniper.py --live

# macOS/Linux (使用 screen/tmux)
screen -S weather_sniper
python sniper.py --live
# 按 Ctrl+A, D  detached

# 实时查看
tail -f sniper.log  # 如果配置了日志文件
# 或在代码中添加 FileHandler

# ✅ 正确：.env 文件加入 .gitignore
echo ".env" >> .gitignore

# ❌ 错误：不要硬编码在代码里
PRIVATE_KEY="0x..."  # 不要这样！

# ✅ 正确：从环境变量读取
private_key = os.getenv('PRIVATE_KEY')

pip install py-clob-client

# 手动测试 API
curl "https://gamma-api.polymarket.com/markets?limit=10"
# 确认返回的数据中包含你感兴趣的城市和日期

import logging
logging.basicConfig(level=logging.DEBUG)  # 或 INFO, WARNING

del state.json
rmdir /S /Q cache
python sniper.py --dry-run --once

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files in skills/polymarket-temperature-event-follower of LeoYeAI/openclaw-master-skills.

• SKILL.md
• .env.txt
• SKILL-en.md
• _meta.json
• background-knowledge-CN.md
• background-knowledge-EN.md
• requirements.txt
• sniper-en.py
• sniper.py

Open the folder on GitHubat commit e5199b5