Polymarket Geopolitics Deadline Cascade Trader

Trades temporal inconsistencies across geopolitical markets with different deadlines. When P(event by later date) < P(event by earlier date), the later-deadl...

Security Scan

The skill's code, instructions, and required credential (SIMMER_API_KEY) line up with its stated purpose of scanning Polymarket-style markets and placing trades via the Simmer SDK; nothing in the package requests unrelated secrets or system access.

Purpose & Capability

Name/description claim arbitrage trading on geopolitical deadline markets. The package only requires a trading API key (SIMMER_API_KEY) and the simmer-sdk client and contains code to discover markets, parse deadlines/themes, compute signals, and place trades. These requirements are consistent with the trading purpose.

Instruction Scope

SKILL.md and trader.py focus on market discovery, parsing, sizing, and execution. The runtime instructions and code only read SIMMER_* tunables from environment variables and use the SimmerClient to interact with the trading venue. There are no instructions to read unrelated files, system credentials, or to transmit data to unexpected endpoints in the provided files.

Install Mechanism

No explicit installer script is included; clawhub.json declares a pip dependency on 'simmer-sdk' (PyPI). Installing third‑party packages from PyPI is expected for this use case but is a moderate-risk operation compared with instruction-only skills because the package code will run locally—verify the simmer-sdk package source and integrity before installing.

Credentials

The only required credential is SIMMER_API_KEY (trading authority). The script also reads a set of SIMMER_* tunables (MAX_POSITION, MIN_TRADE, etc.) which are declared in clawhub.json. The requested environment variables are proportional to a trading skill and are used as expected in the code.

Persistence & Privilege

The skill is not always-enabled (always: false), autostart and cron are disabled by default, and the code only attempts to apply its own skill config via SimmerClient.apply_skill_config (wrapped in a try/except). It does not modify other skills or system-wide settings. Live trading requires an explicit --live flag.

Assessment

This skill appears internally consistent for automated trading: it legitimately needs SIMMER_API_KEY and the simmer-sdk client. Before installing or running with real funds, do the following: (1) Run it in the default paper/sim mode to verify behavior. (2) Review the simmer-sdk package source (GitHub/PyPI) to ensure it’s the expected client and not malicious. (3) Treat SIMMER_API_KEY as high-value—use least-privilege credentials if possible and rotate/regenerate keys if you later revoke access. (4) Do not run with --live until you’ve tested signal logic, risk parameters, and limits in paper mode. (5) Note the publisher/homepage are absent—exercise caution and prefer packages with a known, audited upstream when handling real funds.

Geopolitics Deadline Cascade Trader

This is a template. The default signal detects temporal monotonicity violations and diplomacy-escalation inversions across geopolitical deadline markets — remix it with richer conflict ontologies, news feeds, or satellite-derived intelligence. The skill handles all the plumbing (market discovery, trade execution, safeguards). Your agent provides the alpha.

Strategy Overview

Geopolitical prediction markets frequently list the same conflict event across multiple deadlines: "Will Iran be struck by March 31?", "Will Iran be struck by December 31, 2026?", etc. By the laws of probability, the later-deadline market must always be at least as likely as the earlier one. When this relationship breaks, it is not a matter of opinion — the market is mathematically inconsistent.

This skill scans Polymarket for geopolitical markets, groups them by conflict theme and deadline, and identifies two classes of mispricing:

1. Temporal monotonicity violations — P(event by later date) < P(event by earlier date)
2. Diplomacy-escalation inversions — within the same conflict, both diplomatic and escalation events priced above 50%, which is logically strained

Edge Thesis

Individual geopolitical markets are priced by participants reacting to headlines. Few traders systematically compare related markets across deadlines. This creates pockets where the probability surface is not monotone — where buying the later deadline or selling the earlier one is structurally justified regardless of one's view on the conflict itself.

The edge is not in predicting wars. The edge is in enforcing calendar math.

Signal Logic

1. Temporal Monotonicity Check

1. Discover geopolitical markets using conflict-related keywords (Iran, Israel, Gaza, Lebanon, nuclear, sanctions, tariff, ceasefire, war, troops, etc.)
2. Parse each question to extract (conflict_theme, deadline_date, event_type)
3. Group by conflict_theme
4. Within each group, sort by deadline and check that probabilities are non-decreasing
5. When a violation exceeds MIN_VIOLATION, generate:
   • YES on the underpriced later-deadline market
   • NO on the overpriced earlier-deadline market

2. Diplomacy-Escalation Inversion Check

Within the same conflict theme, if both an escalation event (war, strike, attack) and a diplomatic event (meeting, deal, sanctions) are priced above 50%, one should constrain the other. The skill flags both as overpriced and generates NO signals.

3. Conviction-Based Sizing

All trades use the conviction formula from the standard framework:

• YES: conviction = (YES_THRESHOLD - p) / YES_THRESHOLD, boosted by violation magnitude
• NO: conviction = (p - NO_THRESHOLD) / (1 - NO_THRESHOLD), boosted by violation magnitude
• Size: max(MIN_TRADE, conviction * MAX_POSITION)

Trades are only placed when both the inconsistency exists AND the single-market threshold is satisfied.

Remix Ideas

• Add news sentiment scoring to weight violations that align with recent headlines
• Incorporate satellite imagery APIs for troop movement confirmation
• Extend conflict themes with country-pair graphs (e.g., US-China, Russia-Ukraine)
• Add cross-venue arbitrage against Kalshi or Metaculus geopolitical questions
• Weight violations by market liquidity depth, not just volume

Safety & Execution Mode

The skill defaults to paper trading (venue="sim"). Real trades only with --live flag.

Scenario	Mode	Financial risk
python trader.py	Paper (sim)	None
Cron / automaton	Paper (sim)	None
python trader.py --live	Live (polymarket)	Real USDC

autostart: false and cron: null mean nothing runs automatically until configured in Simmer UI.

Required Credentials

Variable	Required	Notes
SIMMER_API_KEY	Yes	Trading authority. Treat as a high-value credential.

Tunables (Risk Parameters)

All declared as tunables in clawhub.json and adjustable from the Simmer UI.

Variable	Default	Purpose
SIMMER_MAX_POSITION	40	Max USDC per trade at full conviction
SIMMER_MIN_TRADE	5	Floor for any trade
SIMMER_MIN_VOLUME	10000	Min market volume filter (USD)
SIMMER_MAX_SPREAD	0.07	Max bid-ask spread
SIMMER_MIN_DAYS	3	Min days until resolution
SIMMER_MAX_POSITIONS	6	Max concurrent open positions
SIMMER_YES_THRESHOLD	0.38	Buy YES only if market probability <= this value
SIMMER_NO_THRESHOLD	0.62	Sell NO only if market probability >= this value
SIMMER_MIN_VIOLATION	0.04	Min probability violation to trigger a signal

Dependency

simmer-sdk by Simmer Markets (SpartanLabsXyz)

• PyPI: https://pypi.org/project/simmer-sdk/
• GitHub: https://github.com/SpartanLabsXyz/simmer-sdk