Spending audit

Skill weklund/fiduciary/.claude/skills/spending-audit

A personal financial advisor that runs locally. Plaid CLI + SQLite + Claude Code skills. Fiduciary-grade advice grounded in your real data.

Install

npx -y skills add weklund/fiduciary --skill spending-audit

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

One thing to look at

9 stars9 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.

What its author says it does

Copied from the file, not written here

Audit spending for waste, unused subscriptions, and overspending by category. Use when the user asks to find waste, cut spending, review subscriptions, check for recurring charges they forgot about, or do a financial audit.

SKILL.md

2.9 KB, as published. Nobody here has run it

Instructions

Perform a spending audit using the unified SQLite ledger.

Data source

Primary: data/finance.db (SQLite)

Analysis to perform

1. Recurring charges / Subscriptions

-- Find merchants that appear monthly with consistent amounts
SELECT description, 
       ROUND(AVG(amount),2) as avg_amount,
       COUNT(*) as occurrences,
       MIN(date) as first_seen,
       MAX(date) as last_seen
FROM transactions 
WHERE amount > 0 AND amount < 500
GROUP BY description 
HAVING COUNT(*) >= 2 
   AND (MAX(date) > date('now', '-60 days'))
ORDER BY avg_amount * 12 DESC;

2. Category spending breakdown

-- Monthly spending by category
SELECT substr(date,1,7) as month,
       SUM(amount) as total_spent,
       COUNT(*) as txn_count
FROM transactions 
WHERE amount > 0
GROUP BY month
ORDER BY month;

3. Dining & delivery analysis

-- Find all dining/delivery/coffee (common national chains + generic patterns)
SELECT date, description, amount 
FROM transactions 
WHERE amount > 0 
  AND (LOWER(description) LIKE '%restaurant%'
    OR LOWER(description) LIKE '%coffee%'
    OR LOWER(description) LIKE '%doordash%'
    OR LOWER(description) LIKE '%uber eats%'
    OR LOWER(description) LIKE '%grubhub%'
    OR LOWER(description) LIKE '%chipotle%'
    OR LOWER(description) LIKE '%starbucks%'
    OR LOWER(description) LIKE '%mcdonald%'
    OR LOWER(description) LIKE '%bar %'
    OR LOWER(description) LIKE '%grill%'
    OR LOWER(description) LIKE '%brewing%'
    OR LOWER(description) LIKE '%tavern%'
    OR LOWER(description) LIKE '%pizza%'
    OR LOWER(description) LIKE '%taqueria%'
    OR LOWER(description) LIKE '%sushi%'
    OR LOWER(description) LIKE '%cafe%'
    OR LOWER(description) LIKE '%pub %'
    OR LOWER(description) LIKE '%bistro%')
ORDER BY date DESC;

Note: This query catches common patterns but will miss local restaurants. Supplement by checking the Plaid category field if available, or look at merchants with amounts in the $8-$80 range that appear on evenings/weekends.

4. High-frequency merchants

SELECT description, COUNT(*) as times, SUM(amount) as total
FROM transactions WHERE amount > 0
GROUP BY description
ORDER BY total DESC LIMIT 30;

Output format

Subscriptions to review — list with monthly cost, annual cost, last charge date
Category red flags — categories with unusually high spend
Quick wins — specific, actionable cuts with estimated monthly savings
Dining/delivery score — dining-to-grocery ratio with a recommendation

Be direct and specific. Name exact dollar amounts and merchants.