Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Respond to a rent increase strategically — check its validity first, price your alternatives honestly, then negotiate with the leverage tenants forget they have (turnover costs the landlord more than a compromise). Use when asked my rent is going up what can I do, negotiate my rent increase, is this increase even legal, or should I stay or move. Produces the validity checklist, the stay-vs-move math, the negotiation letter with its trade menu, and the decision timeline against the notice period.
.claude/skills/mohitagw15856-rent-increase-response/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 97% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 160% | 0% |
| case-11 | ✓→✗ | ▼ Worse | 92% | 0% |
A rent increase letter looks like a decree; it's usually an opening position. Tenants systematically underprice their own leverage — turnover costs a landlord real money (vacancy, turnover work, listing, the risk of a worse tenant), which means a good tenant proposing a middle number with a longer lease is often genuinely the landlord's best offer. This skill runs the response in the only sensible order: validity (is this increase properly noticed, and lawful where caps exist — flagged, not assumed), then the honest stay-vs-move math, then the negotiation those numbers arm.
Ask for these if not provided:
| Check | Category rule | This case | Flag | |---|---|---|---| Notice period/form · lease-term timing · regulation/cap question — each verify-locally]
Staying: +Δ×12]/yr · Moving: itemized] · Their side: vacancy + turnover estimate] → the zone where a deal beats both alternatives: range]
Verbatim: the record · the comps · the counter with its trade · warm close with the response-by date]
Today → letter → follow-up call → decision point → (if needed) housing search milestones → notice deadline on current lease]
> Rent-increase rules, caps, and notice requirements are jurisdiction-specific — verify the local categories before relying on them. Not legal advice.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 35,446 | 25,194 | -29% | 1 | 1 | 0% | 4,739 | 5,223 | +10% | 0 | 0 | — |
case-02 | fail→fail | 29,973 | 26,937 | -10% | 1 | 1 | 0% | 4,774 | 5,274 | +10% | 0 | 0 | — |
case-03 | fail→fail | 36,977 | 34,504 | -7% | 1 | 1 | 0% | 4,730 | 5,444 | +15% | 0 | 0 | — |
case-04 | fail→fail | 22,709 | 24,049 | +6% | 1 | 1 | 0% | 3,154 | 4,937 | +57% | 0 | 0 | — |
case-05 | fail→fail | 15,905 | 22,760 | +43% | 1 | 1 | 0% | 1,829 | 4,208 | +130% | 0 | 0 | — |
case-06 | fail→pass | 18,841 | 22,289 | +18% | 1 | 1 | 0% | 2,088 | 4,008 | +92% | 0 | 0 | — |
case-07 | fail→pass | 20,142 | 24,484 | +22% | 1 | 1 | 0% | 2,458 | 4,833 | +97% | 0 | 0 | — |
case-08 | pass→pass | 22,594 | 27,054 | +20% | 1 | 1 | 0% | 2,863 | 4,919 | +72% | 0 | 0 | — |
case-09 | pass→pass | 21,517 | 28,602 | +33% | 1 | 1 | 0% | 2,362 | 4,653 | +97% | 0 | 0 | — |
case-10 | fail→fail | 16,709 | 32,423 | +94% | 1 | 1 | 0% | 2,222 | 5,095 | +129% | 0 | 0 | — |
case-11 | pass→fail | 12,377 | 21,393 | +73% | 1 | 1 | 0% | 2,046 | 3,937 | +92% | 0 | 0 | — |
case-12 | fail→fail | 25,212 | 27,466 | +9% | 1 | 1 | 0% | 3,396 | 4,655 | +37% | 0 | 0 | — |
case-13 | fail→fail | 21,164 | 24,694 | +17% | 1 | 1 | 0% | 2,344 | 3,968 | +69% | 0 | 0 | — |
case-14 | fail→pass | 12,919 | 24,450 | +89% | 1 | 1 | 0% | 1,792 | 4,668 | +160% | 0 | 0 | — |
case-15 | pass→pass | 10,430 | 21,064 | +102% | 1 | 1 | 0% | 1,728 | 4,129 | +139% | 0 | 0 | — |
case-16 | fail→fail | 19,234 | 25,677 | +33% | 1 | 1 | 0% | 2,382 | 4,429 | +86% | 0 | 0 | — |
case-17 | pass→pass | 16,296 | 31,901 | +96% | 1 | 1 | 0% | 2,482 | 4,967 | +100% | 0 | 0 | — |
case-18 | fail→fail | 13,298 | 25,101 | +89% | 1 | 1 | 0% | 1,883 | 4,421 | +135% | 0 | 0 | — |
case-19 | pass→pass | 24,307 | 29,605 | +22% | 1 | 1 | 0% | 2,571 | 4,504 | +75% | 0 | 0 | — |
case-20 | pass→pass | 17,249 | 26,197 | +52% | 1 | 1 | 0% | 2,075 | 4,443 | +114% | 0 | 0 | — |
case-21 | pass→pass | 17,967 | 19,136 | +7% | 1 | 1 | 0% | 1,962 | 3,486 | +78% | 0 | 0 | — |
case-22 | pass→pass | 20,137 | 25,146 | +25% | 1 | 1 | 0% | 1,969 | 4,036 | +105% | 0 | 0 | — |
case-23 | pass→pass | 20,055 | 24,606 | +23% | 1 | 1 | 0% | 2,125 | 4,633 | +118% | 0 | 0 | — |
case-24 | pass→pass | 25,143 | 28,055 | +12% | 1 | 1 | 0% | 2,749 | 4,286 | +56% | 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. 24 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 24 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.