Get tasks doneBusiness size: Solo

Solo Tested demonstrates a linked accounting evidence PDF using invented-company mock-ups, with reviewer byline Noa Lin unverified

Noa Lin (source reviewer byline, identity unverified) @solotested · Country unknown · Claude Code, PyMuPDF, Microsoft Excel

Go to the skill

What the agent did

The source describes document conversion and an accounting evidence PDF build. Public illustrations are invented-company mock-ups. Claimed private client inputs are not available for review. No completed client tax work or audit outcome is established.

Result, as claimed

Workflow demonstration, not an audited client result. The article illustrates the process with mock-ups whose company and figures are invented. Its claimed underlying client documents are not public. The source reports a first version of 91 pages with 15 accounts linked and a second of 164 pages with 20 accounts across 13 sections plus a five-document folio. It says trade-debtor and trade-creditor balances were flagged because they were absent from their reconciliation reports. The linked social post claims almost an hour saved, without independent timing evidence.

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 Solo Tested source account post

Try it yourself

Practise organising synthetic accounting evidence into a reviewer checklist before attempting any PDF build.

Difficulty: Intermediate

Prompt

For [synthetic ledger rows] and [a list of example documents], prepare an evidence register for a human reviewer. Assign a reference to each input. Record the entity, period and amount actually stated, then propose possible relationships with an explanation. Keep ambiguous or conflicting records separate. Return a register, unanswered questions and a suggested review order. Do not infer that matching amounts prove agreement. Do not produce tax conclusions, access accounts or change files.

Prompt: starter by Solopreneur Code

Tools

  • Claude Code Used to read the trial balance and folder and to build the linked PDF
  • PyMuPDF The Python PDF library she says Claude used for merging, header strips, links and bookmarks

Steps

  1. Create a tiny fictional test set, including a duplicate amount and a document from the wrong period.
  2. Give the assistant only the test inputs and ask for the evidence register.
  3. Check each proposed relationship yourself against entity, date and context. Reject unsupported matches.
  4. Record your decisions and remaining questions. Stop at the review table. Any document assembly is a separate, explicitly approved task.

Watch out: Two records can share an amount while referring to different events. Use synthetic examples first. Use real client material only under applicable engagement, privacy and firm policies.

Starter version by Solopreneur Code

Skill: Money and bookkeeping

Add this skill

Money and bookkeepingDifficulty: Intermediate

Accounting evidence inventory for review

Organises synthetic ledger and document examples into a traceable review register, leaving every match and accounting judgement to a person.

Works with
Claude, ChatGPT, Gemini Independent text-only starter, not the source author's prompts or installed PDF workflow. No live connectors or client data required.
Tools in the story
Claude Code
Country
Country unknown

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.

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.