Skip to main content
skill CX Codex

market-mechanics-betting — Claude Code skill: science-backed bets

market-mechanics-betting is a Claude Code skill that converts probabilities into trading decisions by calculating market edge, sizing bets with Kelly, extremizing forecasts, and improving Brier Score calibration.

no license 179 installs ★ 203 updated 2026-09-01

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add lyndonkl/claude --skill market-mechanics-betting -a claude-code
Open on GitHub

What market-mechanics-betting does

The skill covers four workflows. First, you identify edge by comparing your probability estimate to the market price, then checking whether the gap meets your minimum threshold—typically 5–10% for prediction markets to account for fees. Next, you compute optimal bet size via Kelly formula, which maximizes long-term wealth growth, then apply it as a fraction (usually one-quarter or one-half) to reduce variance and model error sensitivity.

When aggregating forecasts from multiple forecasters, the skill extremizes the result—shifts the average away from 50%—because group predictions tend toward underconfidence. A separate routine refines Brier Score (forecast accuracy metric) by showing how to recalibrate. Each calculation unfolds step by step: data collection, threshold checks, decision rules, and final execution. The skill assumes comfort with probability and numerical work.

What it helps with

  • decide whether to bet based on edge over market odds
  • calculate bet size that maximizes growth without blowing up the bankroll
  • strengthen aggregated forecasts that are too close to 50–50
  • measure and improve forecast accuracy over time
  • manage correlated bets as a portfolio

Example prompts for the agent

  • I estimate 75% chance; the market shows 60%. What's my edge and how much should I bet using Kelly?
  • Five colleagues forecast 72%, 78%, 81%, 70%, 76%. Extremize this for me.
  • Here are my predictions from last month and actual outcomes. Calculate my Brier Score and tell me where I'm miscalibrated.

How to install market-mechanics-betting

1Skills CLI (Vercel)

npx skills add lyndonkl/claude --skill market-mechanics-betting -a claude-code

2Manually: put the files in place

~/.claude/skills/market-mechanics-betting/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/market-mechanics-betting/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about market-mechanics-betting

How do I install market-mechanics-betting in Claude Code?

Run npx skills add lyndonkl/claude --skill market-mechanics-betting -a claude-code, then locate ~/.claude/skills/market-mechanics-betting/SKILL.md and activate it in Claude Code.

What does market-mechanics-betting do?

It turns probability beliefs into action: computes edge versus market, sizes bets via Kelly Criterion, extremizes group forecasts, and measures forecast calibration through Brier Score.

What minimum edge should I require before betting?

For prediction markets like Polymarket, 5–10% to cover fees; for sports betting, 3–5%; for private bets, 2–3%. The skill helps you determine this threshold and check whether your edge clears it.

Similar skills

All skills for AI and ML →

From the same set49

The whole set →
chef-assistant chef-assistant teaches culinary techniques and food science principles instead of giving static recipes, helping balance flavors and fix errors. CX Codex +1 289installs communication-storytelling communication-storytelling is a Claude Code skill that shapes analysis and technical information into narratives for a defined audience. It supports findings, concept explanations, and announcements. CX Codex +1 246installs visual-storytelling-design visual-storytelling-design turns datasets into visual stories with narrative structure, chart annotations, scrollytelling, and clearer framing. Use it for reports, presentations, and infographics. CX Codex +1 235installs financial-unit-economics financial-unit-economics calculates unit economics, CAC, LTV, and payback metrics across business models. Useful when evaluating pricing viability and growth readiness. CX Codex +1 198installs decision-matrix decision-matrix compares alternatives against weighted criteria, calculates scores, checks sensitivity to weight changes, and delivers a recommendation with trade-off analysis. CX Codex +1 165installs bayesian-reasoning-calibration The bayesian-reasoning-calibration skill applies Bayes' theorem to systematically revise probability estimates as new evidence arrives. It helps you forecast more accurately, avoid overconfidence, and justify why your beliefs change. CX Codex +1 162installs chain-roleplay-debate-synthesis chain-roleplay-debate-synthesis — a skill for Claude Code, Cursor, Codex and other IDEs runs structured debate between roles with competing priorities and synthesizes a unified decision. CX Codex +1 161installs data-schema-knowledge-modeling The data-schema-knowledge-modeling skill builds rigorous models of entities, relationships, and constraints for databases, knowledge graphs, and ontologies. Use it to formalize your data structure before development. CX Codex +1 159installs

Project sponsors

Companies that keep this analytics open