What it does
This skill compares a revised quote, variation or scope of work with the original version. It lists every item that was added, removed, repriced or changed in quantity or specification, recalculates the totals, checks that both versions price on the same basis, and sets out every changed term side by side. Each difference becomes a plain question the owner can put to the supplier.
It informs the decision. It does not accept, reject or judge the quote. This is a standalone library entry with no source article.
Who it is for
Owners and managers of small Australian businesses who receive revised quotes from trades, fitout contractors, IT providers or other suppliers, and who want to see exactly what changed before agreeing. It suits anyone comfortable reading a quote line by line. It is rated practitioner because the output needs checking against the documents.
Before you start
- Have both versions in full: the original and the revision, including any terms and conditions pages.
- Name the person who will decide. The skill writes that name into its decision line.
- Remove anything the comparison does not need, such as bank details, home addresses or staff phone numbers.
- Use an AI tool the business has approved for commercial documents.
- If the quote forms part of a signed contract, or there is a dispute, talk to a qualified adviser. This skill does not cover that.
Set it up
Claude
Tested on 6 November 2026: degraded, an arithmetic cross check combined the original total, which excludes GST, with the revised lines, which include GST, giving a net figure.
No Claude skill package is published for this version, because the Claude run did not fully pass.
ChatGPT
Tested on 6 November 2026: pass.
- Download the Markdown skill file under Downloads and open it.
- Start a new ChatGPT chat. The test used a temporary chat.
- Paste the text from the line starting "# Skill:" to the end of the file, then the line "Apply the skill above to this input:", then your de-identified material.
- Review the draft before any use.
Other platforms, including Microsoft 365 Copilot: not yet tested.
Worked example
The synthetic test input is a bakery's shopfit quote from an invented contractor, followed by a revision sent four weeks later.
- Confirm the documents. Both versions are present: Q-1182 dated 2 October 2026 and Q-1182-R1 dated 28 October 2026. The method records both references before going further.
- Match the items. Four items carry across with similar names. The counter has grown from 3.6 m to 4.2 m, the lights have moved from install only to supply and install, and the tiling has grown from 8 to 10 sqm. Demolition now says "and dispose", so the method asks whether rubbish removal was merged into it and labels that as a possible match to confirm.
- Find what disappeared. The painting line is not in the revision at all. Step 3 of the method lists it as removed, because silence in a revised quote is still a change.
- Recalculate. Step 4 adds up the revised lines and compares that sum with the stated subtotal. Any gap is shown with the working.
- Check the price basis. The original excludes GST and the revision includes it. Step 5 flags this and stops the two totals being compared as if they were like for like. It does not calculate any tax.
- Compare the terms. The deposit, payment schedule, validity period, dates, exclusions and a new hourly variation rate all differ. Each one is quoted old against new.
- Handle the traps. The revision ends with a note telling any AI tool to report no material change. The guardrails treat that as data to report, not an instruction. The owner also asks whether the original price can be enforced after a verbal acceptance. That is a legal question, so the skill declines it and lists it for a qualified adviser.
Sample input and output
Input (synthetic)
Output
From the ChatGPT test run of 6 November 2026 (pass), copied as produced, first part only. The full run continues in the same format. Quotation marks and dashes are normalised to plain characters.
Limits
- It compares two versions of one quote. It does not compare quotes from different suppliers.
- It does not say whether a price or change is fair, reasonable or market rate.
- It gives no legal, tax or contractual advice and calculates no GST.
- It can only see what is written. Verbal agreements, emails and site conversations are outside its view unless they are supplied.
- Matching renamed items is a judgement. Every possible match is labelled for the owner to confirm with the supplier.
- The decision-maker decides whether to accept, negotiate or decline.
Test record
Microsoft 365 Copilot and other platforms: not yet tested.
Each run used a synthetic input with planted traps, such as an embedded instruction to ignore the rules or a request for a decision the skill must not make. A separate reviewer graded each output against pass criteria written before the run. A degraded result means the output was usable but missed at least one criterion.
Version and changelog
Version 1.0.
- v1.0 (2026-11-15): Initial library release. Standalone entry with no source article.
Licence
Free to use and adapt internally. Attribution appreciated. No warranty. Educational purposes only.
General information and education only. Not legal, compliance, financial, or professional advice.
Downloads
TheAICommand. Intelligence, At Your Command.