← Back to Skills Marketplace
antonelli182

Kalshi

by André Antonelli · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
97
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install sports-skills-kalshi
Description
Kalshi prediction markets — events, series, markets, trades, and candlestick data. Public API, no auth required for reads. US-regulated exchange (CFTC). Cove...
Usage Guidance
This skill appears coherent and read-only: it documents Kalshi API endpoints, sport codes, and CLI/Python usage and includes a small benign shell validator. Before installing, confirm your agent runtime provides the referenced 'sports-skills' CLI or Python SDK if you expect the examples to work; also verify the API base URL (references/api.md) matches the official Kalshi endpoint you intend to use. No credentials or installs are requested by this skill.
Capability Analysis
Type: OpenClaw Skill Name: sports-skills-kalshi Version: 1.0.0 The skill bundle provides a legitimate interface for interacting with the Kalshi prediction market API. It includes comprehensive documentation (SKILL.md, references/api-reference.md) and a simple parameter validation script (scripts/validate_params.sh) that contains no malicious logic. There is no evidence of data exfiltration, unauthorized execution, or harmful prompt injection; the instructions are focused on ensuring the AI agent uses the correct parameters and interprets market data accurately.
Capability Assessment
Purpose & Capability
The name/description (Kalshi prediction markets) match the provided commands, sport codes, and API references. Nothing in the manifest requests unrelated credentials, binaries, or config paths.
Instruction Scope
SKILL.md is instruction-only and documents CLI/Python usage and API endpoints for read-only queries. It does not instruct reading unrelated files or accessing secrets. Note: it assumes a 'sports-skills' CLI or Python SDK is available in the runtime environment (no install provided).
Install Mechanism
No install spec is present (instruction-only). No downloads or archive extracts are performed. This is the lowest-risk install posture.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. That is proportionate for a read-only market data skill.
Persistence & Privilege
always:false and model invocation is allowed (platform default). The skill does not request persistent system presence or modify other skills/configs.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install sports-skills-kalshi
  3. After installation, invoke the skill by name or use /sports-skills-kalshi
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Kalshi prediction markets skill. - Access prediction markets, events, series, trades, and candlestick data for US sports and major soccer leagues. - Search open markets by sport and keyword; retrieve today's events and market price history. - Provides clear guidance on parameters: always specify sport and use status="open" for live markets. - Includes command reference, usage examples, and troubleshooting for common issues.
Metadata
Slug sports-skills-kalshi
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Kalshi?

Kalshi prediction markets — events, series, markets, trades, and candlestick data. Public API, no auth required for reads. US-regulated exchange (CFTC). Cove... It is an AI Agent Skill for Claude Code / OpenClaw, with 97 downloads so far.

How do I install Kalshi?

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

Is Kalshi free?

Yes, Kalshi is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Kalshi support?

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

Who created Kalshi?

It is built and maintained by André Antonelli (@antonelli182); the current version is v1.0.0.

💬 Comments