Finance query

Skill weklund/fiduciary/.claude/skills/finance-query

Answer questions about personal finances — balances, transactions, spending patterns, account status, recent purchases, merchant history, income tracking. Use when the user asks anything about their money, accounts, or transactions.From its SKILL.md

Install

npx -y skills add weklund/fiduciary --skill finance-query

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

10 stars10 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 3 commands, including `sqlite3 data/finance.db` and 2 more.

SKILL.md

3.0 KB, 668 tokens by cl100k_base, as published. Nobody here has run it

Instructions

Answer the user's financial question using the unified SQLite ledger.

Data source

Primary: data/finance.db (SQLite — unified ledger of all transactions from Plaid + CSVs)

Query with: sqlite3 data/finance.db "SELECT ..."

Fallback (if DB missing): data/latest/*.json

Schema

transactions (
  id TEXT PRIMARY KEY,
  date TEXT,           -- ISO format YYYY-MM-DD
  description TEXT,
  amount REAL,         -- POSITIVE = debit (money spent), NEGATIVE = credit (income/refund)
  merchant TEXT,
  category TEXT,       -- Plaid category (may be empty for CSV-sourced)
  account_name TEXT,
  account_mask TEXT,   -- last 4 digits
  account_type TEXT,   -- depository, credit, loan, investment
  institution TEXT,
  source TEXT,         -- 'plaid' or 'csv'
  source_file TEXT
);

accounts (
  account_id TEXT PRIMARY KEY,
  name TEXT,
  type TEXT,
  subtype TEXT,
  mask TEXT,
  institution_id TEXT,
  balance_current REAL,
  balance_available REAL,
  balance_limit REAL,
  last_updated TEXT
);

Steps

Check if data/finance.db exists. If not, suggest running python3 scripts/ingest.py first.
Query the database using sqlite3 to answer the user's question.
Present results clearly with specific numbers, dates, and merchant names.

Query patterns

# Date range spending
sqlite3 data/finance.db "SELECT description, amount, date FROM transactions WHERE date >= '2026-06-01' AND amount > 0 ORDER BY amount DESC LIMIT 20"

# Spending by merchant
sqlite3 data/finance.db "SELECT description, SUM(amount), COUNT(*) FROM transactions WHERE amount > 0 GROUP BY description ORDER BY SUM(amount) DESC LIMIT 20"

# Monthly totals
sqlite3 data/finance.db "SELECT substr(date,1,7) as month, SUM(CASE WHEN amount > 0 THEN amount ELSE 0 END) as spent, SUM(CASE WHEN amount < 0 THEN ABS(amount) ELSE 0 END) as income FROM transactions GROUP BY month ORDER BY month"

# Search by merchant
sqlite3 data/finance.db "SELECT date, description, amount FROM transactions WHERE LOWER(description) LIKE '%quills%' ORDER BY date DESC"

# Account balances
sqlite3 data/finance.db "SELECT name, mask, type, balance_current, balance_limit FROM accounts ORDER BY balance_current DESC"

# Income sources
sqlite3 data/finance.db "SELECT date, description, ABS(amount) FROM transactions WHERE amount < 0 AND ABS(amount) > 100 ORDER BY date DESC LIMIT 20"

Conventions

amount > 0 = money spent (debit)
amount < 0 = money received (credit/income)
Dates are ISO format (YYYY-MM-DD)
Always clarify the time period in your response
Round dollar amounts to 2 decimal places
Use -header -column for readable output: sqlite3 -header -column data/finance.db "..."

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most finance skills give in 668 tokens

Counted across 469 of the 469 authors here whose files we hold, read 2026-08-07

Extract date vendor amount and descriptionin 15 of 469, across 3 files
Scan folder for invoice filesin 14 of 469, across 2 files
Rename files to standard formatin 14 of 469, across 2 files
Show organization plan before movingin 14 of 469, across 2 files
Generate summary CSVin 14 of 469, across 2 files
Organize files by categoryin 13 of 469, across 1 file
Preserve original filesin 13 of 469, across 1 file
Flag files missing critical infoin 13 of 469, across 1 file
Produce the requested output filein 9 of 469, across 4 files
Build best, base, and worst case scenariosin 9 of 469, across 5 files
Implement backoff if rate limit errors occurin 8 of 469, across 3 files
Determine the weighted average cost of capitalin 8 of 469, across 4 files

Said here and by no other author read

check if database file exists
query the database using sqlite3
present results with specific numbers and dates
clarify the time period in response
use header and column flags for readable output
suggest ingest script if database is missing

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.