← Back to Skills Marketplace
ghsmc

Kalshi Trading

by ghsmc · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
1631
Downloads
7
Stars
6
Active Installs
1
Versions
Install in OpenClaw
/install kalshi-trading
Description
Trade on Kalshi prediction markets: check portfolio, search markets, analyze orderbooks, place/cancel orders, and manage binary contract positions.
README (SKILL.md)

Kalshi

Trade on Kalshi prediction markets via a self-contained CLI script. Supports market search, portfolio tracking, and full order lifecycle (place/cancel/monitor).

Quick Start

All commands route through a single script. Output is JSON.

CLI

Primary script:

{baseDir}/scripts/kalshi-cli.mjs \x3Ccommand> [args...]

Helper script:

{baseDir}/scripts/quick-analysis.mjs \x3Cticker>

Combines market details + orderbook in a single call for fast analysis.

Commands

Command Description
balance Get account balance (cash + portfolio value)
portfolio Get balance + all open positions
trending Top markets by 24h volume
search \x3Cquery> Search markets by keyword
market \x3Cticker> Get details for a single market
orderbook \x3Cticker> Get bid/ask levels for a market
buy \x3Cticker> \x3Cyes|no> \x3Ccount> \x3Cprice> Place a buy order (price in cents 1-99)
sell \x3Cticker> \x3Cyes|no> \x3Ccount> \x3Cprice> Place a sell order (price in cents 1-99)
cancel \x3CorderId> Cancel a resting order
orders [resting|canceled|executed] List orders, optionally filtered by status
fills [ticker] List recent fills, optionally filtered by ticker

Examples

# Check balance
{baseDir}/scripts/kalshi-cli.mjs balance

# See what's trending
{baseDir}/scripts/kalshi-cli.mjs trending

# Search for markets about bitcoin
{baseDir}/scripts/kalshi-cli.mjs search "bitcoin"

# Get details on a specific market
{baseDir}/scripts/kalshi-cli.mjs market KXBTCD-26FEB14-B55500

# Check orderbook
{baseDir}/scripts/kalshi-cli.mjs orderbook KXBTCD-26FEB14-B55500

# Buy 5 YES contracts at 65 cents
{baseDir}/scripts/kalshi-cli.mjs buy KXBTCD-26FEB14-B55500 yes 5 65

# Sell 5 YES contracts at 70 cents
{baseDir}/scripts/kalshi-cli.mjs sell KXBTCD-26FEB14-B55500 yes 5 70

# Check open orders
{baseDir}/scripts/kalshi-cli.mjs orders resting

# Check recent fills
{baseDir}/scripts/kalshi-cli.mjs fills

Output

All commands output JSON to stdout. Parse the result to present it to the user.

Trading Rules

Critical: ALWAYS confirm with the user before placing any buy or sell order.

Before executing a trade, show the user:

  • Ticker
  • Side (YES or NO)
  • Count (number of contracts)
  • Price (in cents)
  • Total cost = count × price cents = $X.XX

Price format:

  • Prices are in cents (1-99)
  • 65 cents = $0.65 per contract
  • Minimum: 1 cent, Maximum: 99 cents

Payouts:

  • All contracts pay $1.00 (100 cents) if correct, $0 if wrong
  • YES at 65¢: costs 65¢, pays $1.00 if YES wins → 35¢ profit per contract
  • NO at 35¢: costs 35¢, pays $1.00 if NO wins → 65¢ profit per contract
  • YES price + NO price ≈ 100¢ (spreads cause small deviations)

Before selling: Verify the user holds the position by checking portfolio first

Reference Documentation

  • setup-guide.md - Getting API credentials, configuration, troubleshooting
  • trading-guide.md - Market mechanics, strategy tips, risk management
  • api-notes.md - Technical API details, data formats, common patterns

Environment Variables

Required:

  • KALSHI_API_KEY_ID — your Kalshi API key UUID
  • KALSHI_PRIVATE_KEY_PATH — absolute path to your RSA private key PEM file

See setup-guide.md for detailed configuration instructions.

Usage Guidance
This skill appears to be what it claims: a Node.js CLI for Kalshi that signs requests with an RSA private key. Before installing, (1) verify you trust the skill source and review the included scripts (they are bundled and runnable); (2) keep the private key file secure (chmod 600, store in a restricted path) because the CLI reads it to sign requests; (3) prefer using Kalshi's demo environment for testing (the script defaults to production); (4) confirm trades interactively — SKILL.md requires you to always confirm before placing orders, but the CLI can accept direct args, so your agent or UI must enforce confirmation; and (5) revoke or rotate API keys if you suspect misuse.
Capability Analysis
Type: OpenClaw Skill Name: kalshi-trading Version: 1.0.0 The skill bundle is designed to interact with the Kalshi API for trading prediction markets. It explicitly declares its need for sensitive environment variables (`KALSHI_API_KEY_ID`, `KALSHI_PRIVATE_KEY_PATH`) and uses them for RSA-PSS signing of requests to the legitimate Kalshi API endpoint (`https://api.elections.kalshi.com`). The `SKILL.md` file contains security-enhancing instructions for the AI agent, such as requiring user confirmation before placing trades and verifying positions before selling. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, or obfuscation. The `quick-analysis.mjs` script uses `node:child_process.spawn` to call `kalshi-cli.mjs` internally, passing arguments as an array, which prevents shell injection at that point, and `kalshi-cli.mjs` correctly uses `encodeURIComponent` for URL parameters, mitigating further injection risks.
Capability Assessment
Purpose & Capability
Name/description (Kalshi trading) align with required binaries (node), required env vars (API key ID and path to private key), and the code (signing requests, calling Kalshi endpoints). All declared requirements are expected for a signed-requests trading CLI.
Instruction Scope
SKILL.md and the scripts limit actions to Kalshi API usage (search, market, orderbook, portfolio, orders, place/cancel orders). The docs explicitly require user confirmation before trades. The runtime instructions do not ask the agent to read unrelated files or contact unexpected external endpoints.
Install Mechanism
No install spec (instruction-only / bundled scripts). No downloads or archive extraction are requested, so there is no high-risk installer activity.
Credentials
Requires two env vars: KALSHI_API_KEY_ID and KALSHI_PRIVATE_KEY_PATH. These are appropriate and necessary for RSA-PSS signing, but the private key file is highly sensitive—the skill reads it from disk to create signatures. Users should ensure the key file is stored with tight permissions and not shared; only provide keys you intend the CLI to sign requests with.
Persistence & Privilege
always is false and the skill does not request persistent or elevated system-wide privileges. It does spawn a child node process (quick-analysis) to call the bundled CLI — this is consistent with the helper script's purpose and not an unexplained privilege escalation.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install kalshi-trading
  3. After installation, invoke the skill by name or use /kalshi-trading
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release — full prediction market trading via CLI (search, buy, sell, portfolio, orderbook)
Metadata
Slug kalshi-trading
Version 1.0.0
License
All-time Installs 6
Active Installs 6
Total Versions 1
Frequently Asked Questions

What is Kalshi Trading?

Trade on Kalshi prediction markets: check portfolio, search markets, analyze orderbooks, place/cancel orders, and manage binary contract positions. It is an AI Agent Skill for Claude Code / OpenClaw, with 1631 downloads so far.

How do I install Kalshi Trading?

Run "/install kalshi-trading" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Kalshi Trading free?

Yes, Kalshi Trading is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Kalshi Trading support?

Kalshi Trading is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Kalshi Trading?

It is built and maintained by ghsmc (@ghsmc); the current version is v1.0.0.

💬 Comments