Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Decode a moving company estimate — binding vs non-binding, the weight and cubic-feet games, valuation vs insurance, and the red flags that precede hostage-load stories. Use when someone asks 'is this moving quote legit', 'decode my moving estimate', 'binding vs non-binding estimate', or 'how do I avoid moving scams'. Produces an estimate-type decode with what-you'll-actually-pay scenarios, ranked red flags, the valuation decode, and the questions that separate real movers from brokers.
.claude/skills/mohitagw15856-moving-company-estimate-decoder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 898% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 242% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 131% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 62% | 0% |
The moving industry has a specialty: quotes that grow between signing and delivery, enforced by the fact that they have your stuff. The whole game is in three distinctions most customers never learn — binding vs. non-binding estimates, mover vs. broker, and "valuation" vs. insurance. This skill decodes the estimate against those three, prices the realistic worst case, and flags the patterns (lowball-then-reweigh, cubic-feet pricing, big deposits) that show up in every hostage-load story.
Ask for these only if they aren't already provided:
Always compute the valuation reality: released value on their heaviest-cheap and lightest-expensive items (the sofa is overprotected; the laptop is worth $6), and the full-value-protection premium as the actual insurance decision. Verification checklist regardless of severity: regulator registration lookup for interstate movers (name the type of lookup, flag as jurisdiction-specific), the same-company-name check across quote/contract/truck, and recent reviews under the exact legal name.
1. The verdict — estimate type, the realistic total range, and the single most important fix (usually: convert to binding-not-to-exceed or walk).
2. The scenarios — quoted / likely / worst-case, each with the mechanism that gets the bill there.
3. Decode table
| Term | What the document says | What it means at delivery | Severity | |---|---|---|---|
4. 🚩 Red flags, ranked — quoted text, the scam-pattern it matches, the fix or the walk-away call.
5. The valuation decision — released value computed on their goods vs. full-value protection cost; framed as the one genuine insurance choice in the document.
6. Verification checklist + questions — registration lookup, name-match check, survey request, deposit terms, accessorial pricing in writing.
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."
Consumer-side moving-contract review — estimate-type triage, scam-pattern matching, valuation math, verification sequencing.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 22,887 | 29,051 | +27% | 1 | 1 | 0% | 4,088 | 6,642 | +62% | 0 | 0 | — |
case-02 | pass→pass | 22,359 | 20,788 | -7% | 1 | 1 | 0% | 4,327 | 5,154 | +19% | 0 | 0 | — |
case-03 | fail→pass | 3,837 | 30,678 | +700% | 1 | 1 | 0% | 726 | 7,243 | +898% | 0 | 0 | — |
case-04 | fail→pass | 16,234 | 19,400 | +20% | 1 | 1 | 0% | 2,699 | 4,209 | +56% | 0 | 0 | — |
case-05 | pass→pass | 12,679 | 13,605 | +7% | 1 | 1 | 0% | 2,118 | 3,815 | +80% | 0 | 0 | — |
case-06 | pass→pass | 12,032 | 14,142 | +18% | 1 | 1 | 0% | 1,807 | 3,367 | +86% | 0 | 0 | — |
case-07 | pass→pass | 12,892 | 22,768 | +77% | 1 | 1 | 0% | 2,230 | 4,576 | +105% | 0 | 0 | — |
case-08 | pass→pass | 12,785 | 20,064 | +57% | 1 | 1 | 0% | 1,843 | 4,354 | +136% | 0 | 0 | — |
case-09 | pass→pass | 11,154 | 15,511 | +39% | 1 | 1 | 0% | 1,840 | 3,875 | +111% | 0 | 0 | — |
case-10 | pass→pass | 12,013 | 20,292 | +69% | 1 | 1 | 0% | 1,877 | 4,316 | +130% | 0 | 0 | — |
case-11 | pass→pass | 14,460 | 14,677 | +2% | 1 | 1 | 0% | 2,194 | 3,800 | +73% | 0 | 0 | — |
case-12 | pass→pass | 13,656 | 18,505 | +36% | 1 | 1 | 0% | 2,324 | 4,323 | +86% | 0 | 0 | — |
case-13 | pass→pass | 15,401 | 15,816 | +3% | 1 | 1 | 0% | 2,587 | 3,897 | +51% | 0 | 0 | — |
case-14 | pass→pass | 11,076 | 12,317 | +11% | 1 | 1 | 0% | 2,025 | 3,512 | +73% | 0 | 0 | — |
case-15 | pass→pass | 19,683 | 20,538 | +4% | 1 | 1 | 0% | 3,184 | 5,011 | +57% | 0 | 0 | — |
case-16 | pass→pass | 10,760 | 16,064 | +49% | 1 | 1 | 0% | 1,790 | 3,910 | +118% | 0 | 0 | — |
case-17 | pass→pass | 12,496 | 16,527 | +32% | 1 | 1 | 0% | 1,826 | 3,723 | +104% | 0 | 0 | — |
case-18 | pass→pass | 11,183 | 9,046 | -19% | 1 | 1 | 0% | 1,761 | 2,505 | +42% | 0 | 0 | — |
case-19 | fail→pass | 8,893 | 21,531 | +142% | 1 | 1 | 0% | 1,425 | 4,876 | +242% | 0 | 0 | — |
case-20 | pass→fail | 6,997 | 8,445 | +21% | 1 | 1 | 0% | 1,172 | 2,703 | +131% | 0 | 0 | — |
case-21 | fail→fail | 14,404 | 20,881 | +45% | 1 | 1 | 0% | 2,425 | 4,910 | +102% | 0 | 0 | — |
case-22 | fail→fail | 14,725 | 21,483 | +46% | 1 | 1 | 0% | 2,615 | 5,072 | +94% | 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. 22 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 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.