Kelly Criterion Bet Sizer

Calculate optimal bet sizes using Kelly Criterion. Supports single bets, fractional Kelly (quarter/half/three-quarter), multi-bet portfolio sizing, and max-b...

Security Scan

The skill is mostly coherent for computing Kelly bet sizes, but there are small inconsistencies and instruction-level risks (ambiguous input formats and use of a shell-invoked python -c snippet that could be misused if inputs aren't sanitized).

Purpose & Capability

The name/description align with required bits (only python3) and the SKILL.md implements Kelly calculations. Minor inconsistency: SKILL.md claims 'Built by AgentBets' with tutorial links, while the registry metadata lists source as unknown and homepage as none — this mismatch is unexplained but not by itself dangerous.

Instruction Scope

SKILL.md runs a python3 -c command with user-supplied BANKROLL, ODDS, TRUE_PROB arguments. The doc does not precisely specify expected formats (is TRUE_PROB 0.40 or 40?) and the example relies on shell substitution; if an agent inserts unsanitized user text into that shell command it could lead to command/argument injection or mis-parsing. Aside from that, instructions do not request unrelated files, env vars, or external endpoints.

Install Mechanism

Instruction-only skill with no install spec. Requires python3 on PATH — low-risk and proportionate for the stated calculations.

Credentials

No environment variables, credentials, or config paths requested. The level of access requested is minimal and appropriate for the task.

Persistence & Privilege

Skill is not always-loaded and does not request persistence or system-level changes. Autonomous invocation is allowed (platform default) but not combined with other privilege concerns here.

What to consider before installing

This skill appears to implement Kelly calculations correctly and only needs python3, but take these precautions before installing: (1) Verify the publisher/source — SKILL.md references AgentBets but registry metadata lacks a homepage. If provenance matters to you, ask the publisher for a source repo or contact info. (2) Confirm input formats: use true probability as a fraction (e.g., 0.40) unless the skill runner documents otherwise to avoid large errors. (3) Be cautious about how your agent substitutes user values into the provided python3 -c command: unsanitized inputs could cause shell/argument injection. Prefer a runner that passes arguments safely (argv) rather than interpolating into a shell string. (4) Remember this is financial advice: double-check results independently and consider regulatory/legal implications for betting in your jurisdiction.

Calculate mathematically optimal bet sizes based on your edge and bankroll.

When to Use

Use this skill when the user asks about:

• How much to bet on a specific wager
• Kelly Criterion or optimal bet sizing
• Position sizing for a bet with known edge
• Fractional Kelly or conservative bet sizing
• Sizing multiple simultaneous bets
• Maximum bet limits or bankroll allocation

Odds Conversion Reference

Before computing Kelly, convert all odds to decimal probability format:

Format	Example	To Decimal Odds	To Implied Prob
American (+)	+150	1 + odds/100 = 2.50	100/(odds+100)
American (-)	-200	1 + 100/	odds
Decimal	2.50	Already decimal	1/decimal
Probability	40%	1/prob	Already prob

Operations

1. Single Bet — Full Kelly

Calculate the optimal Kelly stake for a single bet. User must provide: bankroll, odds (any format), and their estimated true probability.

python3 -c "
import sys
bankroll = float(sys.argv[1])
odds_input = sys.argv[2]
true_prob = float(sys.argv[3])

# Convert odds to decimal
if odds_input.startswith('+'):
    decimal_odds = 1 + int(odds_input[1:]) / 100
elif odds_input.startswith('-'):
    decimal_odds = 1 + 100 / abs(int(odds_input[1:]))
else:
    decimal_odds = float(odds_input)

b = decimal_odds - 1  # net odds
p = true_prob
q = 1 - p

# Kelly fraction
kelly_f = (b * p - q) / b if b > 0 else 0
kelly_f = max(kelly_f, 0)  # never negative

implied_prob = 1 / decimal_odds
edge = true_prob - implied_prob

print(f'Odds: {odds_input} (decimal: {decimal_odds:.4f})')
print(f'Implied prob: {implied_prob:.2%} | Your estimate: {true_prob:.2%} | Edge: {edge:.2%}')
print(f'Kelly fraction: {kelly_f:.4f} ({kelly_f:.2%} of bankroll)')
print(f'Recommended stake: \${kelly_f * bankroll:.2f} of \${bankroll:.2f} bankroll')
if kelly_f <= 0:
    print('⚠️  No edge detected — Kelly says do not bet')
elif kelly_f > 0.10:
    print('⚠️  Kelly > 10% — consider fractional Kelly to reduce variance')
" BANKROLL ODDS TRUE_PROB

## About

Built by [AgentBets](https://agentbets.ai) — full tutorial at [agentbets.ai/guides/openclaw-kelly-sizer-skill/](https://agentbets.ai/guides/openclaw-kelly-sizer-skill/).

Part of the [OpenClaw Skills series](https://agentbets.ai/guides/#openclaw-skills) for the [Agent Betting Stack](https://agentbets.ai/guides/agent-betting-stack/).