- Home
- Skills
- Productivity
- portfolio tracker
portfolio tracker
Private, local-first portfolio tracker that extracts asset and debt data from screenshots and text statements.
Free
Works with the AI Agents you already use
portfolio tracker
Example session with this skill installed
I just got my monthly statement. My brokerage balance is now $12,450.50 (cost basis $10,000) and my Apple Card balance is $450.25. Update my portfolio.
- Read your context and instructions
- Compiled the portfolio tracker
- Generated the data export
I have parsed your statement and matched the items to your existing portfolio. Here is the proposed update for your approval:
Proposed Portfolio Update
| Product | Action | Field | Current | New |
|---|---|---|---|---|
| Brokerage Account | ~ update | balance | $11,200.00 | $12,450.50 |
invested | $10,000.00 | $10,000.00 | ||
| Apple Card | ~ update | balance | -$120.00 | -$450.25 |
kind | credit_card | credit_card |
Notes:
- The brokerage balance increased by $1,250.50.
- The Apple Card balance was automatically converted to a negative value representing debt.
- All other assets (Cash, Crypto) remain unchanged.
Next steps
- Would you like me to
applythese changes to yourassets.csv? - Shall I generate a new
summaryto show your updated net worth? - Do you need to update any
fx_ratesfor foreign holdings before the summary?
assets.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing personal finances across multiple brokerages, bank accounts, and crypto wallets usually requires sharing sensitive credentials with third-party aggregators or manually wrestling with complex spreadsheets. This skill provides a private, local-first alternative for developers to track net worth and asset performance without cloud API keys or account syncing.
What it does
- Multi-Asset Tracking manages bank balances, stocks, ETFs, mutual funds, bonds, crypto, and commodities in a local ledger.
- OCR Processing parses screenshots and PDF text to extract balances, quantities, and cost bases without manual entry.
- Liability Management tracks credit card debt, loans, and mortgages, automatically handling negative balances and due dates.
- Snapshot History maintains a time-series log of all updates to generate gain/loss reports and net worth trends.
- Currency Handling supports multi-currency portfolios with user-defined exchange rates for consolidated reporting.
How it works
- Initialize the ledger locally and configure your base currency and decimals using the
initcommand. - List existing assets to check current tracking status before proposing any updates.
- Analyze screenshots or text statements to generate an update proposal, matching products by name or ID.
- Apply changes only after a dry-run review, ensuring data integrity before writing to the CSV files.
- Summarize performance to view net worth, identify stale data, and check currency exposures.
Frameworks & tools
Built with Python for the CLI core, using CSV for transparent data storage. It operates entirely within a local directory, requiring no external database or internet connectivity.
Why this beats prompting it yourself
Writing a prompt to extract financial data often results in inconsistent formatting or hallucinated calculations. This skill enforces a strict schema for gains, cost basis, and coupon rates while maintaining a persistent local history that generic prompts cannot track over time.
Use cases
- Tracking net worth across fragmented platforms like Robinhood, Binance, and traditional banks.
- Auditing bond interest and maturity dates from brokerage PDF statements.
- Monitoring debt reduction progress for loans and credit cards.
- Maintaining a private, offline record of physical assets like gold or cash holdings.
Known limitations
Does not fetch real-time market prices or exchange rates; all values must be provided by the user or statement. Requires manual input of FX rates for multi-currency summaries.
Requires manual FX rate entry; no real-time price fetching. Local CLI setup needed. Only processes provided text/images.
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 any payment.
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 forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
Requires