Expense Snap

Capture receipt details, categorize spending, and generate monthly reports from a local SQLite ledger.

Security Scan

The skill's code, runtime instructions, and requirements are consistent with a local receipt/expense tracker that writes a SQLite DB and CSV exports; it does not request credentials or perform network calls.

Purpose & Capability

Name/description match the included Python script and CLI: recording receipts, categorizing, monthly reports, and CSV export. Required binary is only python and no unrelated credentials, binaries, or config paths are requested.

Instruction Scope

SKILL.md instructs running the included Python CLI against {baseDir}; the CLI only reads/writes a local SQLite DB under {baseDir}/.runtime and CSV export files. There are no instructions to read unrelated system files, access environment secrets, or transmit data externally.

Install Mechanism

There is no install spec or remote download; the skill ships code files and expects a local python to run them. No external packages or network retrievals are performed at install time.

Credentials

The skill declares no required environment variables or credentials. The code does not access environment secrets or external auth tokens.

Persistence & Privilege

always is false and the skill does not request persistent platform privileges. It creates and updates files only within the provided base_dir (.runtime DB and any explicit export paths), which is appropriate for its purpose.

Assessment

This skill appears to do what it says: run the included Python script to store receipts in a local SQLite DB at {baseDir}/.runtime/expense-snap.db and export CSVs. It does not request credentials or perform network access. Before installing, consider: run it in a safe/isolated base_dir if you have sensitive receipts (it will write files there), review the small Python source yourself if you want assurance, and ensure your agent substitutes {baseDir} to a directory you control. Note: SKILL.md mentions images/OCR, but the script only stores an image_path string and does not perform OCR or read image files. If you need encryption/backups or stricter access controls for financial data, add those protections outside this skill.

Use this skill when the user wants to turn a receipt or spending note into structured expense data, review spending by month, or export records to CSV.

When to Use

• Logging a new receipt from text or an image transcription.
• Categorizing spending into consistent buckets.
• Producing monthly summaries with budget comparisons.
• Exporting receipts for spreadsheets or reimbursement.

Commands

The helper script stores state in {baseDir}/.runtime/expense-snap.db.

Record a receipt

python {baseDir}/scripts/expense_snap.py record --merchant "Cafe Luna" --date 2026-03-22 --total 18.40 --currency EUR --category meals --line-item "Latte|4.50|1|beverages" --line-item "Sandwich|13.90|1|meals"

List receipts

python {baseDir}/scripts/expense_snap.py list --month 2026-03 --category meals

Monthly report

python {baseDir}/scripts/expense_snap.py monthly-report --month 2026-03

Export to CSV

python {baseDir}/scripts/expense_snap.py export-csv --month 2026-03 --output {baseDir}/.runtime/march-expenses.csv

Safety Boundaries

• Never claim receipt OCR is perfect. Mark ambiguous fields as inferred.
• Do not fabricate line items that are not visible or provided.
• Keep currency and totals consistent with the source receipt.
• If an image is unreadable, explain the uncertainty instead of inventing data.