Answer prediction questions using market trading data, not opinions.
NewMaintained
Automatic
◆Finance & Accounting pack
Last verified 9/8/2026
What it changes
Passed 5 of 13 test cases with the skill, and 7 of 13 without it.
Without skill55%
With skill41%
Checks it passed that the model alone missed
Calls get_futures_term_structure() on the derivatives provider rather than invalid names like get_futures_curve().
Combines parallel asynchronous provider calls using a single gathering helper function rather than sequential execution loops.
Queries FearGreedProvider to obtain a composite 0-100 score synthesized from market price sub-signals without supplying API keys.
and 1 more in the full report
3 fixed6 passed either way7 still failing6 broke
Pass-rate lift
-14 pp
Tokens
+166%
Agent turns
0%
Response time
+5%
Model gemini-3.6-flashMeasured 9/8/2026v19 of 22 cases passed with skill · 13 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
Write a Python code snippet using a crypto derivatives provider to fetch the term structure of Bitcoin futures contracts across expiration dates to gauge risk appetite. Make sure to call the exact official provider method name.
What was checked, without and with the skill
Checked
Without skill
With skill
Calls get_futures_term_structure() on the derivatives provider rather than invalid names like get_futures_curve().
Missed
Passed
case-11 · gemini-3.6-flash · 9/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md345 lines9 filesincludes scripts
digital-oracle
Markets are efficient. Price contains all public information. Reading price = reading market consensus.
Methodology
Answer questions using only market trading data — no news, opinions, or statistical reports as causal evidence. If something is true, some market has already priced it in.
Five iron rules:
Trading data only — prices, volume, open interest, spreads, premiums. Never cite analyst opinions.
Explicit reasoning from price to judgment — explain clearly "why this price answers this question."
Multi-signal cross-validation — never conclude from a single signal. At least 3 independent dimensions.
Label the time horizon of each signal — options price 3 months, equipment orders price 3 years — don't mix them in the same vote.
Structured output — the final report must follow the Step 5 template: layered signal tables → contradiction analysis → probability scenarios → signal consistency assessment. Do not substitute prose for structured reporting.
Workflow
Step 1: Understand the question
Decompose the user's question into:
Core variable: What event or trend?
Time window: Is the user asking about 3 months, 1 year, or 5 years?
Priceability: Is there real money being traded on this outcome?
Step 2: Select signals
Based on question type, select from the signal menu below. Don't use just one category — cover at least 3.
Geopolitical conflict / War risk
Polymarket: Search for related event contracts (ceasefire, invasion, regime change, declaration of war)
Kalshi: Search for related binary contracts
Safe-haven assets: Gold (GC=F), silver (SI=F), Swiss franc (USDCHF=X)