Install
openclaw skills install cogdx-pre-trade-auditVerify trading reasoning with cognitive diagnostics before executing trades. Detects logical fallacies, calibration issues, and cognitive biases in your trade thesis.
openclaw skills install cogdx-pre-trade-auditCognitive verification layer for prediction market trades. Catches reasoning flaws before they become losses.
This is a template. The default signal is your agent's trade thesis — the skill audits the reasoning quality before execution. Remix it with stricter thresholds, additional bias checks, or custom fallacy detection. The skill handles all the plumbing (API calls, trade execution, safeguards). Your agent provides the reasoning to verify.
from cogdx_pre_trade_audit import audit_and_trade
result = audit_and_trade(
market_id="0x1234...",
side="yes",
amount=10.0,
reasoning="BTC ETF approval likely based on SEC meeting notes...",
confidence=0.85,
min_validity=0.7, # Minimum reasoning quality to proceed
live=False # Dry-run by default
)
if result["approved"]:
print(f"Trade executed: {result['trade_id']}")
else:
print(f"Trade blocked: {result['issues']}")
SIMMER_API_KEY - Required. Your Simmer API key.COGDX_WALLET - Optional. Wallet address for CogDx credits.| Parameter | Default | Description |
|---|---|---|
min_validity | 0.7 | Minimum reasoning quality score (0-1) |
block_on_error | True | Block trade if CogDx API unavailable |
Most trading losses come from bad reasoning, not bad data. This skill catches:
External verification you can't do yourself.
Built by Cerebratech — cognitive diagnostics for agents.