Digital Oracle
A skill that answers probability questions from market data: prediction markets, rates, yields and derivatives
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- The skill runs Python scripts and reaches external financial data sources
- It produces probability estimates that must not be taken as investment advice
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/digital-oracleDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run in a terminal in the project folder
npx skills add komako-workshop/digital-oracle --skill digital-oracle -a claude-code -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add komako-workshop/digital-oracle --skill digital-oracle -a cursor -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add komako-workshop/digital-oracle --skill digital-oracle -a github-copilot -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add komako-workshop/digital-oracle --skill digital-oracle -a codex -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add komako-workshop/digital-oracle --skill digital-oracle -a gemini-cli -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add komako-workshop/digital-oracle --skill digital-oracle -a cline -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add komako-workshop/digital-oracle --skill digital-oracle -a roo -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
A fork of Roo Code, same .roo folders.
Run in a terminal in the project folder
npx skills add komako-workshop/digital-oracle --skill digital-oracle -a opencode -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Install uv, then clone the digital-oracle repository and read its SKILL.md as your working instruction. For options chain analysis run uv pip install yfinance. In OpenClaw the install is clawhub install digital-oracle.
Other ways from the author
git clone https://github.com/komako-workshop/digital-oracle.git
uv pip install yfinanceClone the repository and ask the agent to read SKILL.md as its instruction. uv must be installed; yfinance is only needed for options chains.
This is third-party code. Review the repository files before installing.
What it does
The skill gives the agent a method for estimating event probabilities from trading data rather than opinions and news. It connects to several open financial data sources: the Polymarket and Kalshi prediction markets, equity and commodity prices, crypto derivatives, the Treasury yield curve, CFTC positioning reports, SEC insider trades, central bank rates and options chains. For a question such as the odds of a recession or a price reversal, the agent picks at least three independent signals, pulls them in parallel, looks for disagreements between markets and returns a structured report with signal tables, a contradiction analysis and probability estimates. It runs on Python via uv, most sources need no keys, and options chains require the yfinance library.
Who it is for. For analysts, market researchers and curious users who want event probabilities from trading data rather than social media forecasts.
Good fit when
- You need an event probability estimate from trading data
- You want to compare signals from different markets on one question
- You need a structured report with probabilities and a reasoning chain
Not a fit when
- You want a personal investment recommendation: the skill gives analysis, not advice on what to buy or sell
- The event is not traded on any market, so there is no priced signal to read
Example request
Estimate the probability of a US recession within the next year from market data and show the signalsLimitations
The skill estimates probabilities from market data and is not investment advice; decisions stay with the user. It needs uv installed, and yfinance for options chains. Some sources are foreign financial services whose availability from Russia without a VPN is not guaranteed, and if a source is unreachable its signal is skipped. Answer quality depends on whether the event is actually traded on a market.
How to disable. Remove the skill folder from the agent's skills directory, and if installed via clawhub, remove the digital-oracle package.
Security check
- The skill runs Python scripts and reaches external financial data sources
- It produces probability estimates that must not be taken as investment advice
README in short
The README describes an open skill that answers probability questions from trading data rather than news and opinions. It lists thirteen data sources, from the Polymarket and Kalshi prediction markets to the Treasury yield curve, CFTC positioning, SEC insider trades and options chains, and stresses that nearly all of them are free and keyless. The workflow has steps: understand the question, pick at least three signals, pull them in parallel, analyze contradictions and produce a structured probability report. The skill is written in Python, runs via uv, needs yfinance for options, and is built around zero dependencies, dependency injection and snapshot tests. It installs in OpenClaw via clawhub or in other agents by reading SKILL.md, and is MIT licensed.
SKILL.md
--- name: digital-oracle version: 1.0.3 description: "Answer prediction questions using market trading data, not opinions. Use when the user asks probability questions about geopolitics, economics, markets, industries, or any topic where real money is being traded on the outcome. The skill reads prices from prediction markets, commodities, equities, options chains, derivatives, yield curves, and currencies, then cross-validates multiple signals to produce a structured probability report." --- # 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: 1. Trading data only: prices, volume, open interest, spreads, premiums. Never cite analyst opinions. 2. Explicit reasoning from price to judgment: explain clearly why this price answers this question. 3. Multi-signal cross-validation: never conclude from a single signal. At least 3 independent dimensions. 4. Label the time horizon of each signal. 5. Structured output: layered signal tables, contradiction analysis, probability scenarios, signal consistency assessment.
FAQ
Is this advice on where to invest?
No. The skill gives probability estimates from trading data and a reasoning chain. It is not investment advice; the user makes the decisions.
Do I need paid API keys?
Most of the connected sources are open and need no keys. Options chain analysis requires the yfinance library.
Related
A set of investment research skills for Claude Code and Codex built on four investors' methodologies. It is a research tool, not investment advice
Stripe's official MCP server, plugins and skills: the agent searches the API and docs, reads and changes account data
Alpaca's official MCP server: orders for stocks, ETFs, crypto and options, position management and market data in plain language
inn-check-ru: counterparty risk traffic light
inn-check-ru
An open-source skill that checks a Russian company by tax ID across EGRUL, bailiffs, courts, bankruptcy and sanctions, and returns a dated risk verdict