Agent skill

Moonpay Scout

by moonpay in moonpay/skills

Prediction market arbitrage & alpha scout. An agent skill from moonpay/skills.

MITAuto-check passedBusiness, Finance & HR

Install Moonpay Scout

skills CLI
$ npx skills add moonpay/skills --skill moonpay-scout -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install moonpay/skills moonpay-scout --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/moonpay/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/moonpay-scout .claude/skills/moonpay-scout && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
moonpay-scout
GitHub stars
113
Token cost
~1.7k tokens
SKILL.md length
521 words
Files
1
Skills in repo
39
Repo updated
First seen
Licence
MIT

At a glance

Prediction market arbitrage & alpha scout. An agent skill from moonpay/skills.

  • Works in 6 steps: SCAN both platforms in parallel → FIND MATCHES → RUN THE ARB MATH → …
  • Asked to find arb
  • SKILL.md covers Step 1 — SCAN both platforms…, Step 2 — FIND MATCHES, Step 3 — RUN THE ARB MATH and Step 4 — RANK OPPORTUNITIES, plus 6 more sections
  • Calls npm

What it does

Moonpay Scout is an agent skill from moonpay/skills. Prediction market arbitrage & alpha scout. Searches Polymarket and Kalshi for the same event, runs cross-platform arb math (including fees), and ranks opportunities by profitability. Use when asked to "find arb", "scout markets", "find edge", or scan a specific topic across prediction markets.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR. It works with Kalshi and Polymarket. The repository describes itself as: Skills for AI agents to move money — on-ramps, swaps, wallets, deposits, and more via the MoonPay CLI. The licence is MIT.

When your agent uses it

  • Asked to find arb
  • Scan a specific topic across prediction markets

Example prompts

  • “find arb”
  • “scout markets”
  • “find edge”
  • “/moonpay-scout”

Requirements

  • Node.js

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. SCAN both platforms in parallel
  2. FIND MATCHES
  3. RUN THE ARB MATH
  4. RANK OPPORTUNITIES
  5. EXECUTE BEST OPPORTUNITY
  6. FINAL REPORT

What it can do on your machine

Read from SKILL.md and the folder at commit aa672ab. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Moonpay Scout loads about 1.7k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 521 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from moonpay/skills at commit aa672ab, republished under its MIT licence (© moonpay). 521 words, ~1,716 tokens.

Download SKILL.mdSave it as .claude/skills/moonpay-scout/SKILL.md (or your agent's skills folder).
name
moonpay-scout
description
Prediction market arbitrage & alpha scout. Searches Polymarket and Kalshi for the same event, runs cross-platform arb math (including fees), and ranks opportunities by profitability. Use when asked to "find arb", "scout markets", "find edge", or scan a specific topic across prediction markets.
tags
prediction-markets, polymarket, kalshi, arbitrage, trading

Prediction Market Arbitrage & Alpha Scout

You are a cross-platform prediction market arbitrage agent. Your job is to find mathematically provable edge — either pure arbitrage (risk-free profit) or high-conviction alpha (structural mispricing) — across Polymarket and Kalshi.

Topic to scout: {{args}} (if empty, scan trending on both platforms)


Step 1 — SCAN both platforms in parallel

If a topic is given, search both Polymarket and Kalshi for {{args}} simultaneously. If no topic, pull trending from both platforms (limit 8 each).

Print:

🔍 SCANNING Polymarket + Kalshi for "{{args}}"...

Step 2 — FIND MATCHES

Look for markets on both platforms betting on the same underlying event — even if worded differently. For each candidate pair, extract:

  • The Yes price on Polymarket (bid and ask)
  • The Yes price on Kalshi (bid and ask)
  • Liquidity on both sides
  • Resolution date on both sides

Print each match found:

🔗 MATCH: [Event Name]
   Polymarket: [question]  Yes bid/ask @ [X]/[Y]¢  liq: $[Z]  ends: [date]
   Kalshi:     [question]  Yes bid/ask @ [X]/[Y]¢  liq: $[Z]  ends: [date]

Step 3 — RUN THE ARB MATH

For each matched pair, calculate both arb directions. This is the core of the agent.

Pure Arbitrage Check
Direction A: Buy Yes Poly + Buy No Kalshi
  Cost = P_yes_poly_ask + (1 - P_yes_kalshi_bid)
  Payout = 0.98  (Polymarket charges 2% on winning positions)
  Edge = Payout - Cost

Direction B: Buy No Poly + Buy Yes Kalshi
  Cost = (1 - P_yes_poly_bid) + P_yes_kalshi_ask
  Payout = 1.00  (Kalshi no fee on payout)
  Edge = Payout - Cost

Always use bid/ask prices, not mid — mid prices are not executable. If only mid is available, assume 1¢ spread each side.

If either direction has positive Edge after fees, flag it loudly:

🚨 ARB FOUND: [event]
   Direction [A/B]: buy [side] Poly @ [X]¢ + buy [side] Kalshi @ [Y]¢ = [total]¢
   Guaranteed profit: [Z]¢ per share (~[Z]% return, after fees)
   ⚠️  Verify: same resolution criteria? same timeframe?
Resolution Date Adjustment

If markets resolve at different dates:

⏱️  DATE MISMATCH: Poly ends [date1], Kalshi ends [date2]  (gap: [N] days)
   Treating as SOFT arb — risk window is [date1]–[date2]
If No Pure Arb — Find Alpha Instead

Calculate the gap and identify which platform is mispriced:

📐 GAP ANALYSIS: [event]
   Poly Yes: [X]¢  Kalshi Yes: [Y]¢  Raw gap: [Z]¢
   Best direction cost: [C]¢  (need <98¢ for profit after Poly fee)
   Distance from arb: [98 - C]¢

Reason about informational edge:

  • Kalshi edge: US domestic events (Fed, elections, policy), sports
  • Polymarket edge: Geopolitics, crypto prices, international news, fast-moving events
  • Volume signal: Higher volume = more informed price. When Kalshi volume >> Polymarket on the same event, fade Polymarket toward Kalshi
  • Momentum: Use 1-week price history on the top Polymarket outcome — is it moving toward or away from Kalshi?

Output the alpha thesis:

💡 ALPHA: [event]
   Mispriced side: [Poly/Kalshi] has [X]¢ vs counterpart [Y]¢
   Who has edge: [which user base knows this better, and why]
   Momentum: [rising/falling/stable on Polymarket this week]
   Trade: Buy [Yes/No] on [platform] @ [price]¢
   Edge: ~[Z]¢ if thesis correct | Risk: [Z]¢ if wrong
   Conviction: [HIGH/MEDIUM/LOW] — [one sentence why]

Step 4 — RANK OPPORTUNITIES

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
RANK  TYPE         EVENT                         EDGE    CONVICTION
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 1    PURE ARB     [event]                        +5¢    RISK-FREE
 2    SOFT ARB     [event]                        +8¢    HIGH
 3    ALPHA        [event]                       +12¢    MEDIUM
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Rank by:

  1. Pure arb (risk-free, same resolution date) — always trade these
  2. Soft arb (positive math, date gap ≤30 days) — trade with caution
  3. High-conviction alpha (gap ≥5¢, clear informational edge, liq >$10K)
  4. Low-conviction alpha — flag only
Show full SKILL.md (202 more words)Show less

Step 5 — EXECUTE BEST OPPORTUNITY

We can only execute the Polymarket leg directly. Kalshi legs must be placed manually.

If pure arb:

🚨 PURE ARB — executing Polymarket leg now
   Manual Kalshi leg: Buy [Yes/No] on "[market]" @ [price]¢

If alpha:

💡 ALPHA TRADE
   Buy [Yes/No] on "[market question]"
   Price: [X]¢ | Size: $10 | Shares: ~[N] | Wallet: main

Ask: Execute Polymarket leg? (yes to proceed)

If yes, place the position using the tokenId and main wallet via:

bash
mp prediction-market position buy \
  --wallet main \
  --provider polymarket \
  --tokenId <token-id> \
  --price <price> \
  --size <shares>

Step 6 — FINAL REPORT

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎯 SCOUT REPORT — [topic] — [date]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Markets scanned:   [N] Polymarket  |  [N] Kalshi
Matches found:     [N]
Pure arbs found:   [N]
Best opportunity:  [type] on [event]  →  [edge]¢
Position taken:    [yes: details] / [no: why skipped]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Agent Rules

  • Always do the math first — full arb check (both directions, both fees) before qualitative reasoning
  • Use bid/ask, not mid — mid prices are not executable
  • Polymarket fee = 2% on winning positions → payout is 0.98, not 1.00
  • Minimum liquidity to trade: $10K on Polymarket side
  • Flag date mismatches >30 days — not a true arb
  • Pull price history only for top 1–2 candidates
  • Show all math explicitly — no black-box conclusions

Prerequisites

  • MoonPay CLI installed: npm i -g @moonpay/cli
  • Authenticated: mp login → mp verify
  • Wallet funded with USDC.e on Polygon (for Polymarket trades)
  • Wallet registered with Polymarket: mp prediction-market user create --provider polymarket --wallet <evm-address>

MoonPay Integration

Uses mp prediction-market commands for all market search, price history, and position execution on Polymarket. The MoonPay wallet handles USDC.e signing and submission on Polygon.

  • moonpay-prediction-market — Core prediction market commands (search, buy, sell, PnL)
  • moonpay-fund-polymarket — Fund wallet with USDC.e and POL for gas
  • moonpay-check-wallet — Verify balances before trading

© moonpay, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/moonpay-scout of moonpay/skills.

Open the folder on GitHubat commit aa672ab

Compare with similar skills

Moonpay Scout next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Moonpay Scout compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Moonpay Scout this skillmoonpay/skills113—~1.7kAutomated safety check: PassMIT
Digital Oraclekomako-workshop/digital-oracle870—~5.9kAutomated safety check: PassMIT
Dr Manhattanguzus/dr-manhattan204—~2kAutomated safety check: PassApache-2.0
Polymarket Tennislivetennisapi/livetennisapi-mcp152—~3kAutomated safety check: PassMIT
Marketsmachina-sports/sports-skills2421 repos~2.2kAutomated safety check: PassMIT
Feedsalsk1992/CloddsBot2.9k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Digital Oracle

    komako-workshop/digital-oracle

    Answer prediction questions using market trading data, not opinions.

    870 GitHub stars~5.9k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Dr Manhattan

    guzus/dr-manhattan

    Trade prediction markets (Polymarket, Kalshi, Opinion, Limitless, Predict.fun) using a unified CCXT-style API.

    204 GitHub stars~2k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Polymarket Tennis

    livetennisapi/livetennisapi-mcp

    Build observe-only Polymarket and Kalshi tennis market tooling on the polymarket-tennis Python package (MIT) plus the Live Tennis API free tier.

    152 GitHub stars~3k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed
  • Markets

    machina-sports/sports-skills

    Markets orchestration — connects ESPN live schedules with Kalshi and Polymarket prediction markets.

    242 GitHub starsUsed in 1 repo~2.2k tokens
    Business, Finance & HRAuto-check passed
  • Feeds

    alsk1992/CloddsBot

    Real-time market data feeds from 8 prediction market platforms

    2.9k GitHub stars~1.8k tokensUpdated 6 days ago
    Business, Finance & HRAuto-check passed
  • Portfolio Sync

    alsk1992/CloddsBot

    Sync portfolio positions from Polymarket, Kalshi, and Manifold

    2.9k GitHub stars~3.6k tokensUpdated 6 days ago
    Business, Finance & HRAuto-check passed

More from moonpay/skills

All 39 skills in this repo
  • A skill your agent uses when accessing Alchemy APIs for RPC calls, token balances, NFT metadata, asset transfers, transaction simulation, or Alchemy-specific features.

    113 GitHub stars~2.1k tokensUpdated 28 days ago
    Auto-check: notes
  • Alchemy API

    moonpay/skills

    Integrates Alchemy blockchain APIs using an API key. An agent skill from moonpay/skills.

    113 GitHub stars~2.1k tokensUpdated 28 days ago
    Auto-check passed
  • Allium Onchain Data

    moonpay/skills

    Query blockchain data via Allium APIs. An agent skill from moonpay/skills.

    113 GitHub stars~1.9k tokensUpdated 28 days ago
    Auto-check passed
  • Corbits Marketplace

    moonpay/skills

    Paid API marketplace for AI agents via Corbits. An agent skill from moonpay/skills.

    113 GitHub stars~1.5k tokensUpdated 28 days ago
    Auto-check passed
  • Dune Analytics

    moonpay/skills

    Blockchain analytics via Dune REST API — execute DuneSQL queries against live on-chain data, discover decoded contract tables, and monitor credit usage.

    113 GitHub stars~1.3k tokensUpdated 28 days ago
    Auto-check passed
  • Moonpay Auth

    moonpay/skills

    Set up the MoonPay CLI, authenticate, and manage local wallets.

    113 GitHub stars~1.2k tokensUpdated 28 days ago
    Auto-check passed

Questions about Moonpay Scout

What does Moonpay Scout do?

Prediction market arbitrage & alpha scout. An agent skill from moonpay/skills. Moonpay Scout is an agent skill from moonpay/skills. Prediction market arbitrage & alpha scout.

When should I use Moonpay Scout?

Moonpay Scout fits situations like: asked to find arb; scan a specific topic across prediction markets.

How do I install Moonpay Scout in Claude Code?

Run `npx skills add moonpay/skills --skill moonpay-scout -a claude-code`. Or copy the skill folder (skills/moonpay-scout in moonpay/skills) into .claude/skills/moonpay-scout in your project. Claude Code loads it when a task matches its description.

How do I install Moonpay Scout in Codex?

Run `npx skills add moonpay/skills --skill moonpay-scout -a codex`. Or copy the skill folder (skills/moonpay-scout in moonpay/skills) into .agents/skills/moonpay-scout in your project. Codex loads it when a task matches its description.

Can I use Moonpay Scout in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add moonpay/skills --skill moonpay-scout -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/moonpay-scout, .gemini/skills/moonpay-scout, .github/skills/moonpay-scout and .opencode/skills/moonpay-scout in your project.

What does Moonpay Scout need to run?

Going by SKILL.md and its folder, Moonpay Scout needs the command-line tools its instructions call (npm). Our summary lists: Node.js.

Does Moonpay Scout access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Moonpay Scout safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Moonpay Scout use?

Moonpay Scout is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Moonpay Scout use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Moonpay Scout?

Skills that share tags, products or a category with Moonpay Scout: Digital Oracle (komako-workshop/digital-oracle, 870 stars), Dr Manhattan (guzus/dr-manhattan, 204 stars), Polymarket Tennis (livetennisapi/livetennisapi-mcp, 152 stars) and Markets (machina-sports/sports-skills, 242 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Moonpay Scout?

moonpay (a GitHub organization) maintains it in moonpay/skills, which has 113 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on September 10, 2026.

Source: moonpay/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.