Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Decode a home renovation or repair quote — allowances that aren't prices, exclusions that become change orders, payment schedules that shift risk, and what a comparable-bids check should cover. Use when someone asks 'is this contractor quote fair', 'decode this renovation bid', 'what should be in a contractor contract', or 'why do these three bids differ so much'. Produces a section-by-section decode, the allowance and exclusion audit, payment-schedule risk analysis, and the questions that make
.claude/skills/mohitagw15856-home-contractor-quote-decoder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 52% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 132% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 63% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 34% | 0% |
The most expensive number in a renovation quote is usually one that isn't there: the allowance that runs out, the exclusion that becomes a change order, the "TBD" that becomes time-and-materials. This skill decodes the quote the way a construction manager reads a bid — hunting the gaps between what's written and what the finished job requires — and turns three incomparable bids into one comparable question set. It reads documents; it doesn't judge workmanship.
Ask for these only if they aren't already provided:
The core move is the finished-job reconciliation: list what the completed project requires end to end, then find each item in the quote — priced, allowanced, excluded, or silent. Silent items are the future change orders; price the gap.
1. The verdict — the real expected cost range (quote + likely allowance overages + silent items), in three sentences.
2. Section decode
| Section | What it says | What it means / what's missing | Severity | |---|---|---|---|
3. The allowance audit — each allowance vs. realistic cost at the homeowner's stated grade; the overage subtotal.
4. The silent-items list — required by the finished job, absent from the document; each one a future change order.
5. Payment schedule read — money vs. completed work over time; where the homeowner is exposed; the milestone-tied restructure to request.
6. Making bids comparable — the question set to send every bidder so the numbers finally mean the same thing.
End the artifact with, verbatim: "This is a plain-language reading, not legal/financial advice — laws vary by jurisdiction; confirm anything load-bearing with a qualified professional."
Owner-side bid review practice — finished-job reconciliation, allowance auditing, payment-risk sequencing, bid leveling.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,024 | 24,395 | +16% | 1 | 1 | 0% | 3,726 | 5,656 | +52% | 0 | 0 | — |
case-02 | fail→fail | 25,619 | 23,232 | -9% | 1 | 1 | 0% | 5,661 | 5,466 | -3% | 0 | 0 | — |
case-03 | pass→pass | 26,856 | 23,241 | -13% | 1 | 1 | 0% | 4,731 | 5,264 | +11% | 0 | 0 | — |
case-04 | pass→pass | 10,444 | 6,932 | -34% | 1 | 1 | 0% | 1,656 | 2,237 | +35% | 0 | 0 | — |
case-05 | pass→pass | 13,016 | 11,648 | -11% | 1 | 1 | 0% | 2,061 | 3,348 | +62% | 0 | 0 | — |
case-06 | fail→pass | 22,013 | 15,258 | -31% | 1 | 1 | 0% | 4,170 | 3,952 | -5% | 0 | 0 | — |
case-07 | pass→pass | 17,538 | 18,421 | +5% | 1 | 1 | 0% | 3,057 | 4,475 | +46% | 0 | 0 | — |
case-08 | pass→pass | 14,624 | 19,776 | +35% | 1 | 1 | 0% | 2,582 | 4,557 | +76% | 0 | 0 | — |
case-09 | fail→pass | 12,457 | 20,444 | +64% | 1 | 1 | 0% | 2,221 | 5,147 | +132% | 0 | 0 | — |
case-10 | pass→pass | 17,350 | 22,874 | +32% | 1 | 1 | 0% | 2,772 | 4,860 | +75% | 0 | 0 | — |
case-11 | fail→pass | 14,544 | 19,848 | +36% | 1 | 1 | 0% | 2,778 | 4,534 | +63% | 0 | 0 | — |
case-12 | pass→pass | 14,570 | 19,076 | +31% | 1 | 1 | 0% | 2,479 | 4,506 | +82% | 0 | 0 | — |
case-13 | pass→pass | 12,145 | 15,988 | +32% | 1 | 1 | 0% | 2,061 | 3,960 | +92% | 0 | 0 | — |
case-14 | fail→pass | 15,609 | 13,454 | -14% | 1 | 1 | 0% | 2,410 | 3,235 | +34% | 0 | 0 | — |
case-15 | fail→fail | 15,510 | 19,313 | +25% | 1 | 1 | 0% | 2,477 | 4,222 | +70% | 0 | 0 | — |
case-16 | pass→pass | 13,721 | 18,518 | +35% | 1 | 1 | 0% | 2,129 | 4,231 | +99% | 0 | 0 | — |
case-17 | fail→fail | 13,808 | 19,294 | +40% | 1 | 1 | 0% | 2,194 | 4,115 | +88% | 0 | 0 | — |
case-18 | pass→fail | 12,177 | 16,634 | +37% | 1 | 1 | 0% | 2,308 | 4,050 | +75% | 0 | 0 | — |
case-19 | pass→pass | 15,591 | 16,976 | +9% | 1 | 1 | 0% | 3,099 | 4,372 | +41% | 0 | 0 | — |
case-20 | pass→pass | 14,935 | 18,811 | +26% | 1 | 1 | 0% | 2,571 | 4,377 | +70% | 0 | 0 | — |
case-21 | pass→pass | 15,020 | 15,848 | +6% | 1 | 1 | 0% | 2,408 | 3,981 | +65% | 0 | 0 | — |
case-22 | pass→pass | 15,049 | 19,611 | +30% | 1 | 1 | 0% | 2,456 | 4,574 | +86% | 0 | 0 | — |
case-23 | pass→pass | 12,637 | 16,336 | +29% | 1 | 1 | 0% | 2,206 | 4,018 | +82% | 0 | 0 | — |
case-24 | fail→pass | 13,327 | 14,786 | +11% | 1 | 1 | 0% | 2,211 | 3,453 | +56% | 0 | 0 | — |
case-25 | pass→pass | 16,943 | 19,347 | +14% | 1 | 1 | 0% | 2,891 | 4,616 | +60% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted. The headline lift of +20 percentage points is the difference between those two pass rates over the 25 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.