Polymarket Macro Weather Commodity Trader

Trades commodity markets based on extreme weather signals. When temperature markets show unusual readings (extreme heat or cold), it signals potential energy...

Security Scan

The skill's code and instructions match its stated trading purpose and only need a Simmer API key, but there are metadata inconsistencies (declared requirements vs files) and some small transparency gaps you should resolve before installing or giving it credentials.

Purpose & Capability

The skill's name/description (weather-driven commodity trading) aligns with the included code and the Simmer SDK usage. Requesting a SIMMER_API_KEY for a trading SDK is proportionate. However, the registry metadata at the top of the package claims 'Required env vars: none' and 'Primary credential: none' while clawhub.json and SKILL.md both require SIMMER_API_KEY — this mismatch is unexpected and should be clarified.

Instruction Scope

SKILL.md and trader.py limit behavior to: scan Polymarket weather markets, compute stress signals, check commodity markets, and place trades via the Simmer SDK. The skill defaults to paper trading unless explicitly run with --live. Instructions do not ask the agent to read unrelated system files or exfiltrate data beyond using the trading SDK.

Install Mechanism

There is no custom download/install script or archive. The package declares a pip dependency (simmer-sdk) in clawhub.json which is a normal registry dependency. This is a typical install mechanism for a Python-based trading skill and not disproportionate to its purpose. You should still verify the simmer-sdk package identity/reputation.

Credentials

Only a single sensitive credential is required (SIMMER_API_KEY) which is appropriate for a trading client. The skill also reads a set of non-secret tunables via environment variables (SIMMER_MAX_POSITION, SIMMER_MIN_TRADE, etc.) which are expected. The inconsistency is that the top-level registry metadata reported no required env vars; that contradicts clawhub.json and trader.py and should be corrected before trusting the package.

Persistence & Privilege

autostart is false and always:true is not set. The package includes an automaton entrypoint (managed=true, entrypoint=trader.py) but defaults to paper mode and does not auto-run. This is a moderate privilege (it can be executed by the platform when invoked) but not excessive given the skill's purpose.

What to consider before installing

This skill appears to implement what it claims and needs just one trading API key (SIMMER_API_KEY). Before installing: (1) Confirm the metadata mismatch — ensure the package actually requires SIMMER_API_KEY and that the registry listing is corrected; (2) Verify the simmer-sdk package on PyPI/GitHub is the legitimate project you expect; (3) Inspect the rest of trader.py (the truncated portion) for any hard-coded endpoints or unexpected network calls; (4) ONLY provide SIMMER_API_KEY if you trust the Simmer provider and rotate the key after testing; (5) Test thoroughly in paper mode (the default) and keep --live disabled until you are confident. If you want higher assurance, ask the author to fix the manifest inconsistency and supply a provenance link (homepage/repo) before granting credentials.

Weather-Commodity Trader

This is a template. The default signal maps extreme weather readings to commodity market mispricings -- remix it with NOAA API data, satellite crop imagery, or energy grid load forecasts. The skill handles all the plumbing (market discovery, trade execution, safeguards). Your agent provides the alpha.

Strategy Overview

Extreme weather is a leading indicator for commodity disruption, but the transmission from weather prediction markets to commodity prediction markets is slow. Weather specialists trade temperature markets. Commodity traders watch OPEC and inventory reports. Few participants systematically connect the two.

This skill bridges that gap:

1. Scan Polymarket temperature/weather markets for stress signals
2. Compute weather stress: are temperatures showing extremes that imply energy or crop disruption?
3. Check commodity markets: have they already priced in the weather stress?
4. Trade commodity markets that are lagging behind the weather signal

Edge Thesis

Weather-to-commodity transmission has a structural delay on prediction markets because:

• Different participant pools: Weather market traders are weather nerds; commodity traders watch financial news
• Indirect causation: "Dallas 84F+" does not directly say "oil up" -- it requires a mental model of AC demand, grid load, refinery stress
• Temporal mismatch: Weather markets resolve daily; commodity impacts play out over weeks

The edge is in connecting the dots faster than the market.

Signal Logic

1. Weather Stress Computation

For each weather/temperature market, extract:

• City (Dallas, Chicago, Miami, New York, Houston, Phoenix)
• Temperature threshold (e.g., 84F)
• Direction (above/below)
• Probability of the extreme outcome

City-specific stress models:

City	Hot Threshold	Cold Threshold	Stress Type
Dallas	84F+	35F-	Energy demand
Chicago	90F+	61F-	Crop risk + energy
Miami	92F+	40F-	Hurricane indicator
New York	88F+	30F-	Energy demand
Houston	90F+	35F-	Energy demand
Phoenix	100F+	40F-	Energy demand

Stress score = probability that the extreme outcome occurs. Only signals above WEATHER_STRESS_THRESHOLD (default 50%) trigger cascade analysis.

2. Commodity Impact Mapping

Weather Stress	Commodity Impact
Energy UP (extreme heat/cold)	Oil, gas, energy markets should rise
Crop risk (late spring cold)	Wheat, corn, soybean, agriculture markets should rise
Hurricane risk (Miami extreme heat)	Oil, energy, insurance/catastrophe markets should rise

3. Lag Detection & Trading

For each commodity market matching the stress type, check if it has already repriced. If the commodity market probability is still low (below YES_THRESHOLD) despite high weather stress, it is underpriced -- buy YES.

4. Conviction-Based Sizing

All trades use the standard conviction formula:

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

Remix Ideas

• Add NOAA API for real-time temperature confirmation beyond prediction markets
• Incorporate energy grid load data (ERCOT for Texas, PJM for East Coast)
• Weight stress by city population and industrial activity
• Add crop calendar: spring cold in April is far worse than in February
• Cross-reference with commodity futures (CME) for additional price signals
• Add satellite-based crop health indices (NDVI) for agriculture stress

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_WEATHER_STRESS_THRESHOLD	0.50	Min weather stress score to trigger commodity analysis

Dependency

simmer-sdk by Simmer Markets (SpartanLabsXyz)

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