Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Take back control after identity theft — the right first moves, in the right order, so you contain the damage and rebuild. Use when asked what to do about identity theft, someone stole my identity, my details are being used fraudulently, or help me recover from fraud. Produces an immediate-actions checklist (freeze, report, secure), an evidence and reporting plan for the right authorities and institutions, a dispute path for fraudulent accounts/charges, and an ongoing-monitoring setup — flagging
.claude/skills/mohitagw15856-identity-theft-recovery/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 34% | 0% |
Identity theft feels chaotic, but recovery is a sequence: stop new damage, prove it happened, dispute what's fraudulent, and lock things down so it can't recur. This lays out those steps in order — what to do in the first hours, who to report to, and how to dispute fraudulent accounts — so you act decisively instead of panicking.
Ask for these if not provided:
Do now (in order)
Report: file official ID-theft report] · police report if criminal/required]. Keep the reference numbers. Document: log every contact — date, name, reference #. Dispute: fraudulent accounts/charges] in writing, citing your report; demand removal + written confirmation. Ongoing: fraud alert · monitoring · hardened logins.
> Use only official agency/bank websites and phone numbers — never a link or number from the suspicious message.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 22,875 | 20,272 | -11% | 1 | 1 | 0% | 2,878 | 3,411 | +19% | 0 | 0 | — |
case-02 | fail→fail | 26,776 | 25,800 | -4% | 1 | 1 | 0% | 3,452 | 3,832 | +11% | 0 | 0 | — |
case-03 | fail→pass | 23,812 | 26,452 | +11% | 1 | 1 | 0% | 3,139 | 3,862 | +23% | 0 | 0 | — |
case-04 | pass→pass | 20,946 | 15,189 | -27% | 1 | 1 | 0% | 2,505 | 3,256 | +30% | 0 | 0 | — |
case-05 | fail→fail | 14,121 | 17,483 | +24% | 1 | 1 | 0% | 2,294 | 2,842 | +24% | 0 | 0 | — |
case-06 | pass→pass | 20,976 | 13,934 | -34% | 1 | 1 | 0% | 2,580 | 3,186 | +23% | 0 | 0 | — |
case-07 | pass→pass | 15,387 | 15,958 | +4% | 1 | 1 | 0% | 1,761 | 2,806 | +59% | 0 | 0 | — |
case-08 | pass→pass | 22,347 | 12,006 | -46% | 1 | 1 | 0% | 3,010 | 2,932 | -3% | 0 | 0 | — |
case-09 | fail→fail | 19,924 | 16,199 | -19% | 1 | 1 | 0% | 2,416 | 2,805 | +16% | 0 | 0 | — |
case-10 | fail→pass | 16,896 | 13,549 | -20% | 1 | 1 | 0% | 2,020 | 3,372 | +67% | 0 | 0 | — |
case-11 | fail→pass | 24,427 | 18,168 | -26% | 1 | 1 | 0% | 3,093 | 3,814 | +23% | 0 | 0 | — |
case-12 | pass→pass | 15,739 | 13,722 | -13% | 1 | 1 | 0% | 2,507 | 3,298 | +32% | 0 | 0 | — |
case-13 | pass→pass | 16,200 | 17,327 | +7% | 1 | 1 | 0% | 2,048 | 2,977 | +45% | 0 | 0 | — |
case-14 | fail→fail | 14,326 | 14,049 | -2% | 1 | 1 | 0% | 2,438 | 3,292 | +35% | 0 | 0 | — |
case-15 | fail→pass | 13,424 | 17,473 | +30% | 1 | 1 | 0% | 2,269 | 3,043 | +34% | 0 | 0 | — |
case-16 | pass→pass | 19,405 | 16,395 | -16% | 1 | 1 | 0% | 2,436 | 2,974 | +22% | 0 | 0 | — |
case-17 | fail→pass | 14,023 | 12,475 | -11% | 1 | 1 | 0% | 2,502 | 3,184 | +27% | 0 | 0 | — |
case-18 | fail→pass | 17,150 | 17,989 | +5% | 1 | 1 | 0% | 2,235 | 3,222 | +44% | 0 | 0 | — |
case-19 | pass→pass | 16,872 | 15,354 | -9% | 1 | 1 | 0% | 2,089 | 2,922 | +40% | 0 | 0 | — |
case-20 | pass→pass | 24,321 | 19,734 | -19% | 1 | 1 | 0% | 3,044 | 4,408 | +45% | 0 | 0 | — |
case-21 | pass→pass | 22,227 | 21,465 | -3% | 1 | 1 | 0% | 2,760 | 3,134 | +14% | 0 | 0 | — |
case-22 | pass→pass | 12,457 | 13,349 | +7% | 1 | 1 | 0% | 1,226 | 2,342 | +91% | 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 +32 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.