Prediction Market Data

Cross-platform prediction market data via AIsa API. Query Polymarket and Kalshi markets, prices, orderbooks, candlesticks, positions, and trades. Use when us...

Security Scan

The skill appears to do exactly what it says: a read-only AIsa API client for Polymarket/Kalshi data that requires a single AISA_API_KEY and Python 3, with no unexpected installs or unrelated credentials.

Purpose & Capability

Name/description match the declared requirements: python3 and AISA_API_KEY are appropriate for a client that queries the AIsa API. The commands and code are about querying Polymarket and Kalshi data and do not request unrelated services or credentials.

Instruction Scope

SKILL.md directs the agent to run the included Python script which issues HTTPS GETs to api.aisa.one. The instructions and code appear limited to read-only market queries. Note: the client exposes endpoints to look up wallet activity/positions when a wallet address is supplied — these are read-only but can reveal on-chain info if you provide addresses. Also the code references a _raw_get call in the shown snippet; review the full file to confirm there are no additional network endpoints or unexpected POSTing logic (the provided excerpt shows only GETs to api.aisa.one).

Install Mechanism

No install spec; this is instruction-only plus a Python script. That minimizes disk-write/install risk. Required binary is only python3.

Credentials

Only a single secret (AISA_API_KEY) is required, which is appropriate for an API client. Be aware the key is sent as a Bearer token to api.aisa.one; you must trust the AIsa service and the cost model ($0.01/query) before providing the key.

Persistence & Privilege

Skill is not always-enabled and does not request system-wide privileges or other skills' configuration. It does not attempt to persist or escalate privileges in the manifest.

Assessment

This skill is coherent with its description, but before installing: (1) Confirm you trust the AIsa service (the API key you provide will be sent to api.aisa.one and queries incur cost). (2) Review the full script (ensure methods like _raw_get are implemented and there are no unexpected network POSTs or other remote endpoints). (3) Only supply wallet addresses if you intend to fetch public on‑chain activity (these queries are read-only but can reveal activity). If any of those checks raise concerns, do not provide your AISA_API_KEY and inspect the code more closely.

Query Polymarket and Kalshi prediction markets via AIsa API.

Setup

export AISA_API_KEY="your-key"

Get a key at aisa.one ($0.01/query, pay-as-you-go).

Workflow

Querying prediction market data involves these steps:

1. Search markets to find IDs (always start here)
2. Extract the ID from the response (token_id, condition_id, or market_ticker)
3. Query details using the extracted ID (price, orderbook, candlesticks, etc.)

Quick Examples

Polymarket: search → get price

# Step 1: Search — find markets and extract token_id (side_a.id or side_b.id)
python3 {baseDir}/scripts/prediction_market_client.py polymarket markets --search "election" --status open --limit 5

# Step 2: Get price using token_id from Step 1
python3 {baseDir}/scripts/prediction_market_client.py polymarket price <token_id>

Kalshi: search → get price

# Step 1: Search — find markets and extract market_ticker
python3 {baseDir}/scripts/prediction_market_client.py kalshi markets --search "fed rate" --status open --limit 5

# Step 2: Get price using market_ticker from Step 1
python3 {baseDir}/scripts/prediction_market_client.py kalshi price <market_ticker>

Cross-platform sports

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

ID Reference

Most commands need an ID from the markets response. Always search first.

Platform	ID Field	Where to Find
Polymarket	token_id	side_a.id or side_b.id in markets output
Polymarket	condition_id	condition_id in markets output
Kalshi	market_ticker	market_ticker in markets output

Commands

Polymarket

python3 {baseDir}/scripts/prediction_market_client.py polymarket markets [--search <kw>] [--status open|closed] [--min-volume <n>] [--limit <n>]
python3 {baseDir}/scripts/prediction_market_client.py polymarket price <token_id> [--at-time <unix_ts>]
python3 {baseDir}/scripts/prediction_market_client.py polymarket activity --user <wallet> [--market-slug <slug>] [--limit <n>]
python3 {baseDir}/scripts/prediction_market_client.py polymarket orders [--market-slug <slug>] [--token-id <id>] [--user <wallet>] [--limit <n>]
python3 {baseDir}/scripts/prediction_market_client.py polymarket orderbooks --token-id <id> [--start <ms>] [--end <ms>] [--limit <n>]
python3 {baseDir}/scripts/prediction_market_client.py polymarket candlesticks <condition_id> --start <unix_ts> --end <unix_ts> [--interval 1|60|1440]
python3 {baseDir}/scripts/prediction_market_client.py polymarket positions <wallet_address> [--limit <n>]
python3 {baseDir}/scripts/prediction_market_client.py polymarket wallet (--eoa <addr> | --proxy <addr>) [--with-metrics]
python3 {baseDir}/scripts/prediction_market_client.py polymarket pnl <wallet_address> --granularity <day|week|month>

Kalshi

python3 {baseDir}/scripts/prediction_market_client.py kalshi markets [--search <kw>] [--status open|closed] [--min-volume <n>] [--limit <n>]
python3 {baseDir}/scripts/prediction_market_client.py kalshi price <market_ticker> [--at-time <unix_ts>]
python3 {baseDir}/scripts/prediction_market_client.py kalshi trades [--ticker <ticker>] [--start <unix_ts>] [--end <unix_ts>] [--limit <n>]
python3 {baseDir}/scripts/prediction_market_client.py kalshi orderbooks --ticker <ticker> [--start <ms>] [--end <ms>] [--limit <n>]

Cross-Platform Sports

python3 {baseDir}/scripts/prediction_market_client.py sports matching (--polymarket-slug <slug> | --kalshi-ticker <ticker>)
python3 {baseDir}/scripts/prediction_market_client.py sports by-date <sport> --date <YYYY-MM-DD>

Sports: nfl, mlb, cfb, nba, nhl, cbb, pga, tennis.

Understanding Odds

Prices are decimals: 0.65 = 65% implied probability. "Yes" price = probability the event happens. Higher volume = more liquidity.

Security & Permissions

Requires: AISA_API_KEY environment variable.

All operations are read-only via HTTPS GET to api.aisa.one. No trades executed, no wallets connected, no personal data sent beyond the API key. Every response includes usage.cost and usage.credits_remaining.

Full docs: AIsa API Reference.