Get tasks doneBusiness size: Solo

A Singapore data lead had Claude Code take his monthly bank and miles admin from 2 to 3 hours to 4 minutes

Rory Tan · Singapore · Claude Code, YNAB, Python

Go to the skill

What the agent did

On top of his own Python pipeline, Claude Code loads bank statement files from several Singapore banks into YNAB, sorts transactions and asks him about unclear ones, learns new rules from his answers, and tracks each card's bonus cap per billing cycle.

Result, as claimed

Monthly work across his Singapore bank and card accounts (downloading statements, importing to YNAB, sorting 200+ transactions, checking card bonus caps) used to take 2 to 3 hours and now takes 4 minutes. A 45-minute manual import became a 30-second command. His categoriser matched 40% of transactions on its own at first and 85%+ after a month of his corrections.

This is the result as claimed in the public source linked below. It has not been checked and is not a typical outcome.

Proof

Read the write-up on his blog

Try it yourself

Track how close each credit card is to its bonus cap before the statement date, from your own transactions.

Difficulty: Intermediate

Prompt

Here are my card reward rules: [for each card, the bonus categories, monthly cap or minimum spend, and statement date, from the bank's own page]. Here are this cycle's transactions for each card: [attach statements or exports]. For each card, show spend so far in bonus categories, the cap or minimum, days left in the cycle, and whether my current pace will reach it. Mark any transaction whose category you are unsure of and ask me. Do not move money or change any card.

Tools

  • Claude Code Named in the post. He uses it with memory so it learns his categories
  • YNAB His budgeting app, which has an API

Steps

  1. Write down each card's reward rules from the bank's own pages.
  2. Export this cycle's transactions for each card.
  3. Run the prompt and answer its questions on unclear transactions.
  4. Run it again a week before each statement date.

Watch out: Banks label merchants in their own way, so one wrong category can cost you a month of bonus miles. Check unclear transactions yourself.

Starter version by Solopreneur Code

Skill: Bills and savings

Add this skill

Bills and savingsDifficulty: Intermediate

Card bonus cap tracker

Tracks how close each of your credit cards is to its bonus cap or minimum spend before the statement date, from your own transactions.

Works with
Claude, ChatGPT, Gemini Works with any AI that can read files you upload. Memory helps it learn your categories.
Tools in the story
Claude Code, YNAB, Python
Country
Singapore

How to use this: Copy the skill, paste it into Claude, ChatGPT or Gemini, and ask it to save it as a skill. If it cannot, it will still follow the steps.

Show skill

If the Copy button does not work, select this text and copy it.

Job: keep the books and catch errors

Other tools for this job

Tools used

Could also do this

  • Osome (Singapore) Not tested in a storySingapore firm. Says it pairs an accounting team with its own software for bookkeeping, invoicing, tax and filing deadlines.Page checked 2 November 2026. Vendor page: Osome (Singapore), opens in a new tab
  • Dext Not tested in a storyCaptures and categorises receipts, invoices and expenses and syncs them to your accounting software. The page does not mention checking prices against a list.Page checked 2 November 2026. Vendor page: Dext, opens in a new tab

Sign up for the newsletter

Get the next story from Solopreneur Code in your inbox.

Form not loading? Subscribe on Substack

Back to all stories

More like this

Browse all stories
Get tasks doneBusiness size: SoloIncludes prompt

A newsletter writer's Claude Code agent turned screenshots into 38 scheduled Substack Notes he did not write, with no engagement lift

Dheeraj Sharma @genaiunplugged · Country unknown · Claude Code, SubflowAI Substack connector, macOS scheduler, Substack Notes

Each morning a headless Claude Code run takes the oldest screenshot, classifies it, writes a 45 to 115 word Note in his voice, checks it against copy gates, uploads the image, schedules it for the next free day, reads the schedule back and archives the screenshot. Screenshots with emails, phone numbers or orders are set aside.

Result, as claimed

29 Notes scheduled by 23 Sep and 38 by 12 Oct with none written by him. 12 measured Notes had a median of 3.5 likes against 5 for his other Notes, which he reads as no lift.

Get tasks doneBusiness size: SoloIncludes prompt

A Fukuoka developer had Claude Code build a bookkeeping pipeline that reconciled 200 transactions and flagged its own doubts

Ken Imoto @kenimo49 · Japan · Claude Code, MCP connection to his accounting platform (platform not named)

Built a re-runnable pipeline that pulls the month's transactions over MCP, matches bank rows to receipts by amount and date, proposes a category with a one-line reason for each row and flags rows it isn't sure about.

Result, as claimed

200 transactions reconciled and 11 miscategorised, a 94.5% hit rate. Review shrank to 18 flagged rows plus a sample. 7 of the 11 errors were in the flagged pile and 4 were caught on the sample.

Get tasks doneBusiness size: CompanyIncludes prompt

A Malaysian point-of-sale company runs about 170 AI agents its co-founder built, and sales admin per lead fell from about 15 minutes to about 1

Fong Wai Hong · Malaysia · Claude Code, Salesforce

When someone books a demo, an agent researches the shop and briefs the caller. Other agents rank every open lead into a live call list that re-sorts about every 30 seconds, so a promised callback rises to the top. After each call the conversation is transcribed and the lead record is filled in. He also replaced a couple of hundred Zapier automations with his own stack in about four weeks.

Result, as claimed

Fong says the average time to close out a lead is now about 1 minute, down from about 15. He says reps make two times more calls a day and meetings booked per 100 leads went up about 25%, which he says shows up in the bottom line. He says the marketing team used to spend 30 to 40% of its time fixing broken Zaps.