AI Blocks › Track your numbers
US Treasury data puller
Ask about US debt, spending or interest rates. Get the latest official numbers from Treasury, no key needed.
US Treasury data puller is a free AI skill for the job "Track your numbers". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by K-Dense · Level: beginner · Thinking: low
Made by K-Dense. See the original on GitHub; we copied it as it is, with its licence.
What it does
Ask a plain question about US debt, government spending or interest rates and get the latest official figure back, with the date it was published. The skill uses the Treasury's open Fiscal Data service. It picks the right data set for your question, such as total public debt to the penny, daily cash statements, monthly spending and revenue, bond auction results, interest rates, exchange rates or savings bonds. It then writes a short Python script that requests only the columns you need, filters by date, sorts newest first and loads the rows into a table. It tells you to check the data set's guide for the current address, because paths change. It needs Python with two common libraries.
You give it
- The question you want answered
- A date range (optional)
- The columns or countries you care about (optional)
- Python installed to run the script
You get
- The latest official figure with its date
- A Python script that pulls the data
- A table of rows ready for a spreadsheet
- The name of the data set used
Use it when
- You need today's national debt figure for a report.
- You want a year of Treasury auction results in a spreadsheet.
- You are tracking monthly federal spending against revenue.
- You need Treasury exchange rates for a set of currencies and dates.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can call public web APIs.