- Home
- Skills
- Research & Analysis
- data analyst
data analyst
Audited U.S. government data analysis for economic, fiscal, and social statistics with full reproducibility.
$5
/moSubscription · cancel anytime
Secure checkout via Stripe
- Always the latest version
- Delivered live to your agent via MCP
- Cancel anytime, access ends at period end
Works with the AI Agents you already use
data analyst
Example session with this skill installed
What was the total federal debt as a percentage of GDP for the last fiscal year? Provide the CSV data and a short answer.
- Read your context and instructions
- Compiled the data analyst
I have retrieved the federal debt data from Treasury Fiscal Data and GDP figures from the Bureau of Economic Analysis. The analysis was performed in a dedicated environment to ensure units and fiscal year alignments are correct.
Federal Debt and GDP Analysis
The total debt held by the public at the end of Fiscal Year 2024 was $28.2 trillion, representing approximately 98.1% of GDP.
| Measure | Value | Unit | Source |
|---|---|---|---|
| Debt Held by the Public | 28,214,500 | $ Millions | Treasury Fiscal Data |
| Nominal GDP (FY2024) | 28,766,100 | $ Millions | BEA |
| Debt-to-GDP Ratio | 98.1 | Percent | Computed |
Next steps
- Review
analysis.pyto see the fiscal year alignment and normalization logic. - Inspect
data/treasury/for the raw daily treasury statement records. - Run the full report mode if you require a breakdown by debt instrument type.
Audit Status: AUDIT PASSED
Data retrieval date: 2025-05-20
Disclosures: Figures for the final quarter of the fiscal year reflect the BEA "Advance" estimate of GDP. All debt figures are nominal.
Subscription · always the latest version
- Secure checkout via Stripe
- Cancel anytime
- Delivered live via MCP
About this skill
Inaccurate data ruins technical analysis and public reporting. This skill provides a rigorous framework for answering questions using official U.S. government data, ensuring every number is audited, traced to a source, and computed via reproducible scripts.
What it does
- Multi-source retrieval fetches data from BEA, BLS, Census, Treasury, FRED, IPUMS, and other federal agencies.
- Automated data handling manages API keys, bulk downloads, and manual ingestion workflows for restricted environments.
- Statistical analysis computes weighted survey estimates, deflates nominal values, and handles fiscal-to-calendar year conversions.
- Automated auditing runs a verification gate that matches every cited number in a report to a registered fact in a JSON database.
- Sensitivity testing executes alternative models for judgment calls to document how assumptions impact headline figures.
How it works
- Frame & Route: Define the measures, universe, and period, then use
fetch.py --routeto identify the correct federal source packs. - Fetch & Ingest: Execute data retrieval based on the source's access rules, including handling API keys or generating manual download scripts.
- Analyze: Write a single
analysis.pyscript to process raw CSVs, compute exhibits, and register facts with provenance. - Audit: Run
audit_answer.pyoraudit_report.pyto ensure every claim in the final output is backed by the computed data.
Frameworks & tools
Built on a Python-based analysis stack including specialized libraries for survey microdata, Treasury yield curves, and BLS time-series statistics. It interfaces with federal APIs and uses a custom auditing engine to validate Markdown and HTML deliverables.
Why this beats prompting it yourself
LLMs frequently hallucinate statistics, conflate fiscal and calendar years, or use outdated data from training memory. This skill forces the agent to download fresh official data, perform the math in a visible script, and pass a programmatic audit before answering.
Use cases
- Economic research for tracking real wage growth or GDP components across different vintages.
- Fiscal analysis comparing federal spending, debt, and tax receipts against historical benchmarks.
- Demographic studies using IPUMS or Census ACS microdata to analyze specific population segments.
- Regulatory tracking synthesizing data from the Federal Register, Congress.gov, and agency dashboards.
Known limitations
Does not support real-time stock market data or private sector financials. Requires a Python environment for script execution and may require manual user steps for sources that block cloud IP ranges.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
Restricted to U.S. government/federal sources. Analysis requires a Python execution environment. Manual download steps required for sources behind interactive or blocked portals.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 11 days ago
- Accounts
Cdc
Example
Bea
Openxmlformats
Bls
Census
Cms
Data
House
Senate
Dol
Eia
Epa
Fda
Stlouisfed
Govinfo
Gpo
Huduser
Ipums
Doi
Atusdata
Nationsreportcard
Noaa
Opm
Sec
Worldbank
Treasury
Usaspending
Usda
Usgs
- Software
Python
Permissions
Allowed Hosts