agentleFS
Sign inStart free
baofeng-techbaofeng-tech/agent-skills-so/prediction-market-data-zh/SKILL.md

prediction-market-data-zh

Skill0 starsChanged 7 months agoMITView on GitHub

通过 AIsa API 查询跨平台预测市场数据。支持 Polymarket 和 Kalshi 的市场行情、价格、订单簿、K线、持仓和交易记录。适用场景：查询预测市场赔率、选举博彩、事件概率、市场情绪、Polymarket 价格、Kalshi 价格、体育博彩赔率、钱包盈亏、跨平台市场对比。 Use when: the user needs market data, stock analysis, watchlists, or portfolio workflows.

  • Reads credentials

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

Create a free account to mount
Files
SKILL.md

预测市场数据

通过 AIsa API 查询 Polymarket 和 Kalshi 预测市场。

配置

export AISA_API_KEY="your-key"

在 aisa.one 获取 Key（$0.01/次查询，按量付费）。

工作流程

查询预测市场数据的步骤：

  1. 搜索市场获取 ID（必须从这一步开始）
  2. 从返回结果中提取 ID（token_id、condition_id 或 market_ticker）
  3. 用 ID 查询详情（价格、订单簿、K线等）

快速示例

Polymarket：搜索 → 获取价格

# 第一步：搜索市场，提取 token_id（side_a.id 或 side_b.id）
python3 scripts/prediction_market_client.py polymarket markets --search "election" --status open --limit 5

# 第二步：用第一步的 token_id 获取价格
python3 scripts/prediction_market_client.py polymarket price <token_id>

Kalshi：搜索 → 获取价格

# 第一步：搜索市场，提取 market_ticker
python3 scripts/prediction_market_client.py kalshi markets --search "fed rate" --status open --limit 5

# 第二步：用第一步的 market_ticker 获取价格
python3 scripts/prediction_market_client.py kalshi price <market_ticker>

跨平台体育市场

python3 scripts/prediction_market_client.py sports by-date nba --date 2025-04-01

ID 参考

大多数命令需要从 markets 返回中获取 ID，务必先搜索。

平台ID 字段获取位置
Polymarkettoken_idmarkets 输出中的 side_a.id 或 side_b.id
Polymarketcondition_idmarkets 输出中的 condition_id
Kalshimarket_tickermarkets 输出中的 market_ticker

命令参考

Polymarket

python3 scripts/prediction_market_client.py polymarket markets [--search <关键词>] [--status open|closed] [--min-volume <数值>] [--limit <数值>]
python3 scripts/prediction_market_client.py polymarket price <token_id> [--at-time <unix时间戳>]
python3 scripts/prediction_market_client.py polymarket activity --user <钱包地址> [--market-slug <slug>] [--limit <数值>]
python3 scripts/prediction_market_client.py polymarket orders [--market-slug <slug>] [--token-id <id>] [--user <钱包地址>] [--limit <数值>]
python3 scripts/prediction_market_client.py polymarket orderbooks --token-id <id> [--start <毫秒>] [--end <毫秒>] [--limit <数值>]
python3 scripts/prediction_market_client.py polymarket candlesticks <condition_id> --start <unix时间戳> --end <unix时间戳> [--interval 1|60|1440]
python3 scripts/prediction_market_client.py polymarket positions <钱包地址> [--limit <数值>]
python3 scripts/prediction_market_client.py polymarket wallet (--eoa <地址> | --proxy <地址>) [--with-metrics]
python3 scripts/prediction_market_client.py polymarket pnl <钱包地址> --granularity <day|week|month>

Kalshi

python3 scripts/prediction_market_client.py kalshi markets [--search <关键词>] [--status open|closed] [--min-volume <数值>] [--limit <数值>]
python3 scripts/prediction_market_client.py kalshi price <market_ticker> [--at-time <unix时间戳>]
python3 scripts/prediction_market_client.py kalshi trades [--ticker <ticker>] [--start <unix时间戳>] [--end <unix时间戳>] [--limit <数值>]
python3 scripts/prediction_market_client.py kalshi orderbooks --ticker <ticker> [--start <毫秒>] [--end <毫秒>] [--limit <数值>]

跨平台体育市场

python3 scripts/prediction_market_client.py sports matching (--polymarket-slug <slug> | --kalshi-ticker <ticker>)
python3 scripts/prediction_market_client.py sports by-date <运动类型> --date <YYYY-MM-DD>

支持：nfl、mlb、cfb、nba、nhl、cbb、pga、tennis。

理解赔率

价格为小数：0.65 = 65% 隐含概率。"Yes" 价格 = 事件发生的概率。交易量越高 = 流动性越强。

安全与权限

需要： AISA_API_KEY 环境变量。

所有操作均为只读，通过 HTTPS GET 请求 api.aisa.one。不执行交易、不连接钱包、除 API Key 外不发送个人数据。每个响应包含 usage.cost 和 usage.credits_remaining。

完整文档：AIsa API 参考。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free