Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →This skill should be used when the user asks to "search for exposed devices on the internet," "perform Shodan reconnaissance," "find vulnerable services using Shodan," "scan IP ranges with Shodan," or "discover IoT devices and open ports." It provides comprehensive guidance for using Shodan's search engine, CLI, and API for penetration testing reconnaissance.
.claude/skills/dokhacgiakhoa-shodan-reconnaissance-and-pentesting/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 179% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 264% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 61% | 0% |
Provide systematic methodologies for leveraging Shodan as a reconnaissance tool during penetration testing engagements. This skill covers the Shodan web interface, command-line interface (CLI), REST API, search filters, on-demand scanning, and network monitoring capabilities for discovering exposed services, vulnerable systems, and IoT devices.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,374 | 28,545 | +86% | 1 | 1 | 0% | 1,971 | 5,497 | +179% | 0 | 0 | — |
case-02 | fail→pass | 16,255 | 14,850 | -9% | 1 | 1 | 0% | 1,957 | 1,971 | +1% | 0 | 0 | — |
case-03 | fail→fail | 16,820 | 13,090 | -22% | 1 | 1 | 0% | 1,879 | 2,811 | +50% | 0 | 0 | — |
case-04 | fail→fail | 12,126 | 15,348 | +27% | 1 | 1 | 0% | 1,469 | 1,999 | +36% | 0 | 0 | — |
case-05 | pass→pass | 2,658 | 8,963 | +237% | 1 | 1 | 0% | 319 | 1,161 | +264% | 0 | 0 | — |
case-06 | pass→pass | 10,490 | 9,795 | -7% | 1 | 1 | 0% | 1,004 | 1,612 | +61% | 0 | 0 | — |
case-07 | pass→pass | 7,908 | 7,407 | -6% | 1 | 1 | 0% | 1,521 | 2,318 | +52% | 0 | 0 | — |
case-08 | pass→pass | 9,339 | 10,721 | +15% | 1 | 1 | 0% | 679 | 1,806 | +166% | 0 | 0 | — |
case-09 | pass→pass | 9,440 | 8,342 | -12% | 1 | 1 | 0% | 674 | 1,331 | +97% | 0 | 0 | — |
case-10 | pass→pass | 8,691 | 3,637 | -58% | 1 | 1 | 0% | 665 | 1,439 | +116% | 0 | 0 | — |
case-11 | pass→pass | 11,547 | 19,606 | +70% | 1 | 1 | 0% | 645 | 1,666 | +158% | 0 | 0 | — |
case-12 | pass→pass | 9,281 | 8,431 | -9% | 1 | 1 | 0% | 794 | 1,490 | +88% | 0 | 0 | — |
case-13 | pass→pass | 8,550 | 6,305 | -26% | 1 | 1 | 0% | 1,454 | 1,969 | +35% | 0 | 0 | — |
case-14 | pass→pass | 8,607 | 8,283 | -4% | 1 | 1 | 0% | 677 | 1,432 | +112% | 0 | 0 | — |
case-15 | fail→fail | 9,344 | 10,524 | +13% | 1 | 1 | 0% | 768 | 1,881 | +145% | 0 | 0 | — |
case-16 | pass→pass | 18,311 | 19,616 | +7% | 1 | 1 | 0% | 2,279 | 3,532 | +55% | 0 | 0 | — |
case-17 | fail→pass | 27,051 | 22,807 | -16% | 1 | 1 | 0% | 2,397 | 2,785 | +16% | 0 | 0 | — |
case-18 | pass→pass | 12,021 | 14,537 | +21% | 1 | 1 | 0% | 1,124 | 2,318 | +106% | 0 | 0 | — |
case-19 | pass→pass | 4,185 | 3,905 | -7% | 1 | 1 | 0% | 710 | 1,380 | +94% | 0 | 0 | — |
case-20 | pass→pass | 9,366 | 10,841 | +16% | 1 | 1 | 0% | 824 | 1,892 | +130% | 0 | 0 | — |
case-21 | fail→fail | 10,369 | 12,986 | +25% | 1 | 1 | 0% | 914 | 2,260 | +147% | 0 | 0 | — |
case-22 | pass→pass | 9,717 | 8,939 | -8% | 1 | 1 | 0% | 773 | 1,443 | +87% | 0 | 0 | — |
case-23 | pass→pass | 9,949 | 9,728 | -2% | 1 | 1 | 0% | 902 | 1,759 | +95% | 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 +13 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.