Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Access Prediction Market Data

ASecurity

Grants the agent real-time access to prediction markets (Polymarket, Kalshi, Limitless) for fact-checking, probability analysis, and order execution.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgoapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill access-prediction-market-data --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Access Prediction Market Data?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Access Prediction Market Data
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-access-prediction-market-data/badge)](https://www.skillsdirectory.com/skills/rondoflow-access-prediction-market-data)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: access-prediction-market-data
description: "Grants the agent real-time access to prediction markets (Polymarket, Kalshi, Limitless) for fact-checking, probability analysis, and order execution."
category: "Finance & Crypto"
author: community
version: "1.1.0"
icon: coins
---

# User Guide & System Instructions

## ⚙️ Setup & Configuration

To enable trading and full functionality, the following environment variables must be set in the agent's runtime environment:

### Polymarket
- `POLYMARKET_PRIVATE_KEY`: Your wallet's private key.
- `POLYMARKET_PROXY_ADDRESS`: Proxy wallet address.

### Kalshi
- `KALSHI_API_KEY`: Your Kalshi API key.
- `KALSHI_PRIVATE_KEY`: Your RSA private key.

### Limitless
- `LIMITLESS_API_KEY`: Limitless exchange API key.
- `LIMITLESS_PRIVATE_KEY`: Private key for EIP-712 order signing.


## 🧠 Core Capabilities

### 1. `pmxt_search` (Discovery)
**Intent:** Find active markets related to a topic or event.
- **Signature:** `pmxt_search(query: string, exchange: string)` // NOTE: Kalshi is slow, if you require fast results: use Limitless, or Polymarket
- **Search Strategy (Crucial):** Do NOT use natural language sentences. Use **broad keywords**. 
    - *Bad:* `pmxt_search("Who will win the next presidential election?")`
    - *Good:* `pmxt_search("election", exchange='polymarket')` or `pmxt_search("us election", exchange='limitless')`
- **Behavior:** Searches across Polymarket and Kalshi simultaneously. Returns market IDs, titles, and current volumes.
- **Pro Tip:** If the user asks about a general topic (e.g. "Crypto"), search for high-volume markets to see what is trending.

### 2. `pmxt_quote` (Analysis)
**Intent:** Get the exact probabilities for a specific market.
- **Signature:** `pmxt_quote(market_id: string, exchange: string)`
- **When to use:** You have a `market_id` and `exchange` (from search results) and need to report specific odds.
- **Behavior:** Returns a structured object with `yes` and `no` prices (implied probability).
- **Presentation:** Always convert the float prices (e.g., `yes: 0.34, no: 0.66`) into percentages (34% and 66%) when speaking to the user.

### 3. `pmxt_order` (Execution)
**Intent:** Place a real-money market order on a market.
- **Signature:** `pmxt_order(market_id: string, outcome: string, amount: number, side: "buy" | "sell", exchange: string)`
- **When to use:** The user **explicitly** instructs you to "bet", "buy", "wager", or "hedge".
- **Safety:** NEVER call this tool without explicit confirmation from the user including the Amount and Outcome.

---

## 🤖 Agent Behavior Guidelines

### Rule 1: Don't Hallucinate, Calculate.
If a user asks "Is X likely to happen?", do NOT rely on your internal training data.
1.  Call `pmxt_search` with a broad keyword for "X".
2.  Call `pmxt_quote` relevant markets.
3.  Reply with: "The market implies a **[Price]%** chance."

### Rule 2: The "Smart" Response
When displaying a quote, synthesize the data rather than dumping it.
- *Bad:* "Gavin is 0.30."
- *Good:* "The market is currently pricing Gavin Newsom's victory at **30%** (No: 71%). This suggests a skeptical outlook compared to last week."

### Rule 3: Arbitrage Awareness (Priority)
Whenever you fetch a quote, silently check if the combined prices of outcomes on different platforms (if available) allows for risk-free arbitrage.
- If you detect a spread (e.g. Poly Yes 0.40 + Kalshi No 0.55 = 0.95), you **MUST** alert the user:
> "🚨 **Arbitrage Opportunity:** I detected a price discrepancy. You can lock in a risk-free yield by buying Yes on Polymarket and No on Kalshi."

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →