Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Sherlock Integration - Social Media OSINT
.claude/skills/shadd0wtaka-sherlock/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -76% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -67% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -10% | 0% |
Sherlock Integration - Social Media OSINT
Category: reconnaissance — OSINT & Information Gathering
Sherlock Integration - Social Media OSINT Findet Benutzernamen auf über 400 Social Media Plattformen
pythonfrom tools.sherlock_integration import SherlockIntegration async def main(): tool = SherlockIntegration() result = await tool.__init__("target.com") print(result)
bashsherlock --help
deep-recon --tool sherlock_integration --target example.comreconnaissancezen-agents_agent_run agent_type=reconnaissance tool=sherlock_integrationPOST /tools/execute with {"tool_name": "sherlock_integration", "target": "example.com"}| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 6,995 | 7,712 | +10% | 1 | 1 | 0% | 1,003 | 1,436 | +43% | 0 | 0 | — |
case-02 | fail→fail | 8,490 | 10,083 | +19% | 1 | 1 | 0% | 1,172 | 1,938 | +65% | 0 | 0 | — |
case-03 | fail→fail | 8,703 | 7,981 | -8% | 1 | 1 | 0% | 1,367 | 855 | -37% | 0 | 0 | — |
case-04 | fail→pass | 11,924 | 965 | -92% | 1 | 1 | 0% | 1,420 | 341 | -76% | 0 | 0 | — |
case-05 | fail→pass | 11,309 | 2,612 | -77% | 1 | 1 | 0% | 1,959 | 643 | -67% | 0 | 0 | — |
case-06 | fail→pass | 5,542 | 2,141 | -61% | 1 | 1 | 0% | 813 | 518 | -36% | 0 | 0 | — |
case-07 | fail→pass | 4,892 | 3,339 | -32% | 1 | 1 | 0% | 891 | 801 | -10% | 0 | 0 | — |
case-08 | fail→pass | 15,870 | 3,115 | -80% | 1 | 1 | 0% | 2,819 | 503 | -82% | 0 | 0 | — |
case-09 | fail→pass | 9,462 | 4,084 | -57% | 1 | 1 | 0% | 1,748 | 577 | -67% | 0 | 0 | — |
case-10 | fail→pass | 4,528 | 2,857 | -37% | 1 | 1 | 0% | 753 | 410 | -46% | 0 | 0 | — |
case-11 | fail→pass | 6,186 | 1,950 | -68% | 1 | 1 | 0% | 971 | 391 | -60% | 0 | 0 | — |
case-12 | fail→fail | 5,239 | 4,962 | -5% | 1 | 1 | 0% | 927 | 1,084 | +17% | 0 | 0 | — |
case-13 | pass→pass | 4,378 | 7,270 | +66% | 1 | 1 | 0% | 680 | 497 | -27% | 0 | 0 | — |
case-14 | pass→pass | 9,086 | 1,577 | -83% | 1 | 1 | 0% | 1,404 | 470 | -67% | 0 | 0 | — |
case-15 | pass→pass | 7,390 | 1,457 | -80% | 1 | 1 | 0% | 1,313 | 372 | -72% | 0 | 0 | — |
case-16 | fail→pass | 10,435 | 3,756 | -64% | 1 | 1 | 0% | 1,771 | 496 | -72% | 0 | 0 | — |
case-17 | fail→pass | 17,203 | 11,608 | -33% | 1 | 1 | 0% | 3,007 | 553 | -82% | 0 | 0 | — |
case-18 | fail→pass | 6,640 | 11,503 | +73% | 1 | 1 | 0% | 997 | 341 | -66% | 0 | 0 | — |
case-19 | fail→pass | 8,491 | 5,281 | -38% | 1 | 1 | 0% | 1,406 | 1,164 | -17% | 0 | 0 | — |
case-20 | fail→fail | 14,017 | 22,707 | +62% | 1 | 1 | 0% | 1,737 | 1,395 | -20% | 0 | 0 | — |
case-21 | fail→fail | 15,751 | 17,604 | +12% | 1 | 1 | 0% | 995 | 1,325 | +33% | 0 | 0 | — |
case-22 | fail→pass | 12,191 | 4,999 | -59% | 1 | 1 | 0% | 1,370 | 983 | -28% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +64 percentage points is the difference between those two pass rates over the 21 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.