Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →IP address utilities — geolocation, subnet scanning, port discovery. Zero barrier — use with x-cmd or curl + standard networking tools. Use for "ip", "geolocation", "subnet", "port scan", "network".
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -20% | 0% |
IP address lookup, geolocation, subnet discovery, and port scanning.
bash# With x-cmd x ip # List all local IPs x ip geolite 8.8.8.8 # Geolocation lookup x ip info 192.168.1.0 # IP classification x ip map 192.168.1.0/24 # Discover active hosts x ip tps localhost # Port scan # Without x-cmd — use curl for geolocation curl -s "https://ipinfo.io/8.8.8.8/json" # Use standard tools for local IPs ifconfig | grep "inet " # macOS ip addr show # Linux
x ip ls — List all local IP addressesx ip geolite <ip> — Geolocation via ipinfo.iox ip info <ip> — IP class/type classificationx ip cidr <cidr> — CIDR range infox ip map <subnet> — ICMP ping sweepx ip tps <host> — TCP port scancurl https://ipinfo.io/<IP>/jsonifconfig, ip addr, hostname -Inc -zv, nmapStarting with the essentials. Will add:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,895 | 3,577 | -70% | 1 | 1 | 0% | 1,777 | 871 | -51% | 0 | 0 | — |
case-02 | fail→pass | 12,093 | 7,455 | -38% | 1 | 1 | 0% | 1,835 | 1,477 | -20% | 0 | 0 | — |
case-03 | fail→pass | 10,109 | 3,499 | -65% | 1 | 1 | 0% | 1,614 | 819 | -49% | 0 | 0 | — |
case-04 | fail→pass | 9,950 | 6,243 | -37% | 1 | 1 | 0% | 1,663 | 1,359 | -18% | 0 | 0 | — |
case-05 | pass→pass | 7,567 | 4,430 | -41% | 1 | 1 | 0% | 1,031 | 996 | -3% | 0 | 0 | — |
case-06 | fail→pass | 5,752 | 2,974 | -48% | 1 | 1 | 0% | 903 | 726 | -20% | 0 | 0 | — |
case-07 | fail→pass | 14,054 | 2,547 | -82% | 1 | 1 | 0% | 2,582 | 651 | -75% | 0 | 0 | — |
case-08 | fail→pass | 12,800 | 5,729 | -55% | 1 | 1 | 0% | 2,236 | 1,302 | -42% | 0 | 0 | — |
case-09 | pass→pass | 8,987 | 2,363 | -74% | 1 | 1 | 0% | 1,394 | 695 | -50% | 0 | 0 | — |
case-10 | fail→pass | 11,070 | 7,052 | -36% | 1 | 1 | 0% | 1,792 | 1,720 | -4% | 0 | 0 | — |
case-11 | fail→pass | 5,261 | 3,765 | -28% | 1 | 1 | 0% | 862 | 870 | +1% | 0 | 0 | — |
case-12 | pass→pass | 9,112 | 4,420 | -51% | 1 | 1 | 0% | 1,471 | 907 | -38% | 0 | 0 | — |
case-13 | pass→pass | 9,599 | 2,964 | -69% | 1 | 1 | 0% | 1,417 | 694 | -51% | 0 | 0 | — |
case-14 | pass→pass | 8,558 | 2,839 | -67% | 1 | 1 | 0% | 1,399 | 772 | -45% | 0 | 0 | — |
case-15 | fail→pass | 11,571 | 3,211 | -72% | 1 | 1 | 0% | 1,512 | 796 | -47% | 0 | 0 | — |
case-16 | fail→pass | 7,209 | 2,788 | -61% | 1 | 1 | 0% | 910 | 666 | -27% | 0 | 0 | — |
case-17 | pass→pass | 8,697 | 3,944 | -55% | 1 | 1 | 0% | 1,448 | 818 | -44% | 0 | 0 | — |
case-18 | pass→pass | 8,560 | 4,627 | -46% | 1 | 1 | 0% | 1,143 | 988 | -14% | 0 | 0 | — |
case-19 | pass→pass | 9,956 | 2,892 | -71% | 1 | 1 | 0% | 1,645 | 767 | -53% | 0 | 0 | — |
case-20 | pass→pass | 7,167 | 12,478 | +74% | 1 | 1 | 0% | 1,056 | 1,041 | -1% | 0 | 0 | — |
case-21 | pass→pass | 10,119 | 9,259 | -8% | 1 | 1 | 0% | 1,703 | 1,715 | +1% | 0 | 0 | — |
case-22 | pass→pass | 9,998 | 13,894 | +39% | 1 | 1 | 0% | 1,675 | 1,701 | +2% | 0 | 0 | — |
case-23 | pass→pass | 12,568 | 8,071 | -36% | 1 | 1 | 0% | 1,972 | 1,750 | -11% | 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. 23 cases were attempted. The headline lift of +48 percentage points is the difference between those two pass rates over the 23 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.