Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use to reset an employee's corporate account password following the IT security SOP. Use when a user reports they are locked out, forgot their password, or needs a password reset. Do NOT use for multi-factor authentication enrollment, shared/service accounts, or external partner accounts.
.claude/skills/bonaniibm-password-reset/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 8 |
| gemini-3.1-pro-preview | 100% | 1 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -67% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -68% | 0% |
A user is locked out of, or cannot sign in to, their corporate account and needs their password reset. For service/shared accounts or MFA enrollment, route elsewhere.
A user messages: "I'm locked out and can't get into my laptop." Verify identity, confirm it is a standard account, trigger the portal reset, and deliver the temporary credential securely with a forced change on first login.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,833 | 4,923 | -67% | 1 | 1 | 0% | 2,447 | 994 | -59% | 0 | 0 | — |
case-02 | fail→pass | 13,655 | 3,785 | -72% | 1 | 1 | 0% | 2,337 | 994 | -57% | 0 | 0 | — |
case-03 | fail→pass | 12,349 | 4,063 | -67% | 1 | 1 | 0% | 2,088 | 1,023 | -51% | 0 | 0 | — |
case-04 | fail→pass | 13,739 | 3,364 | -76% | 1 | 1 | 0% | 2,477 | 813 | -67% | 0 | 0 | — |
case-05 | fail→pass | 10,821 | 2,954 | -73% | 1 | 1 | 0% | 1,969 | 634 | -68% | 0 | 0 | — |
case-06 | fail→pass | 10,164 | 2,645 | -74% | 1 | 1 | 0% | 1,745 | 673 | -61% | 0 | 0 | — |
case-07 | fail→pass | 14,209 | 4,283 | -70% | 1 | 1 | 0% | 2,211 | 1,033 | -53% | 0 | 0 | — |
case-08 | pass→pass | 10,673 | 3,944 | -63% | 1 | 1 | 0% | 1,735 | 795 | -54% | 0 | 0 | — |
case-09 | pass→pass | 12,061 | 3,846 | -68% | 1 | 1 | 0% | 1,947 | 932 | -52% | 0 | 0 | — |
case-10 | fail→pass | 5,778 | 3,022 | -48% | 1 | 1 | 0% | 906 | 699 | -23% | 0 | 0 | — |
case-11 | pass→pass | 9,781 | 2,293 | -77% | 1 | 1 | 0% | 1,630 | 614 | -62% | 0 | 0 | — |
case-12 | pass→pass | 10,279 | 2,594 | -75% | 1 | 1 | 0% | 1,678 | 607 | -64% | 0 | 0 | — |
case-13 | fail→pass | 10,435 | 4,047 | -61% | 1 | 1 | 0% | 1,694 | 838 | -51% | 0 | 0 | — |
case-14 | pass→pass | 12,661 | 4,109 | -68% | 1 | 1 | 0% | 2,038 | 934 | -54% | 0 | 0 | — |
case-15 | fail→pass | 12,173 | 3,238 | -73% | 1 | 1 | 0% | 2,049 | 798 | -61% | 0 | 0 | — |
case-16 | pass→pass | 9,974 | 3,824 | -62% | 1 | 1 | 0% | 1,805 | 876 | -51% | 0 | 0 | — |
case-17 | fail→pass | 11,625 | 2,751 | -76% | 1 | 1 | 0% | 1,960 | 728 | -63% | 0 | 0 | — |
case-18 | pass→pass | 9,762 | 2,215 | -77% | 1 | 1 | 0% | 1,616 | 489 | -70% | 0 | 0 | — |
case-19 | fail→pass | 8,986 | 3,345 | -63% | 1 | 1 | 0% | 1,333 | 787 | -41% | 0 | 0 | — |
case-20 | pass→pass | 9,167 | 2,455 | -73% | 1 | 1 | 0% | 1,617 | 578 | -64% | 0 | 0 | — |
case-21 | fail→pass | 10,321 | 3,101 | -70% | 1 | 1 | 0% | 1,636 | 520 | -68% | 0 | 0 | — |
case-22 | pass→pass | 9,125 | 2,840 | -69% | 1 | 1 | 0% | 1,374 | 575 | -58% | 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 +59 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.