This is a template. The default signal detects temporal monotonicity violations in Fed rate markets -- remix it with live yield curve data, Fed funds futures, or options-implied probabilities. The skill handles all the plumbing (market discovery, trade execution, safeguards). Your agent provides the alpha.
Fed rate cut/hike markets across different meeting dates must satisfy temporal monotonicity: the probability of a cut "by June" must be >= the probability of a cut "by April", since June includes April. When this invariant is violated, we have a pure structural arbitrage.
Key advantages:
conviction = min(violation_size / violation_threshold, 2.0) / 2.0size = max($1.00, conviction * MAX_POSITION_USD)ParameterDefaultNotesViolation threshold3%Min difference to trigger tradeExit threshold45%Sell when position price reaches thisMax position size$5.00 USDCPer marketMax trades per run3Rate limitingMax slippage15%Skip if slippage exceedsMin liquidity$0Disabled by default
bash
clawhub install kalshi-fed-temporal-mono-trader
Requires: SIMMER_API_KEY and SOLANA_PRIVATE_KEY environment variables.
Cron is set to null -- the skill does not run on a schedule until you configure it in the Simmer UI.
The skill defaults to dry-run mode. Real trades only execute when --live is passed explicitly.
ScenarioModeFinancial riskpython trader.pyDry runNoneCron / automatonDry runNonepython trader.py --liveLive (Kalshi via DFlow)Real USDC
VariableRequiredNotesSIMMER_API_KEYYesTrading authority. Treat as a high-value credential.SOLANA_PRIVATE_KEYYesBase58-encoded Solana private key for live trading.
VariableDefaultPurposeSIMMER_FED_TEMP_VIOLATION_THRESHOLD``0.03Min violation size to trigger tradeSIMMER_FED_TEMP_EXIT_THRESHOLD``0.45Sell position when price reaches this levelSIMMER_FED_TEMP_MAX_POSITION_USD``5.00Max USDC per tradeSIMMER_FED_TEMP_MAX_TRADES_PER_RUN``3Max trades per execution cycleSIMMER_FED_TEMP_SLIPPAGE_MAX``0.15Max slippage before skipping tradeSIMMER_FED_TEMP_MIN_LIQUIDITY``0Min market liquidity USD (0 = disabled)
simmer-sdk is published on PyPI by Simmer Markets.
Review the source before providing live credentials if you require full auditability.