Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Unified Reconnaissance Scanner
.claude/skills/shadd0wtaka-unified-recon/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 84% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -41% | 0% |
Unified Reconnaissance Scanner
Category: reconnaissance — Automated Reconnaissance
Unified Reconnaissance Scanner Kombiniert alle Tools für eine vollständige Enumeration
Usage: python unified_recon.py --target example.com python unified_recon.py --target example.com --full
pythonfrom tools.unified_recon import UnifiedReconScanner async def main(): tool = UnifiedReconScanner() result = await tool.__init__("target.com") print(result)
bashunified-recon --help
deep-recon --tool unified_recon --target example.comreconnaissancezen-agents_agent_run agent_type=reconnaissance tool=unified_reconPOST /tools/execute with {"tool_name": "unified_recon", "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 | 11,642 | 11,932 | +2% | 1 | 1 | 0% | 1,817 | 2,241 | +23% | 0 | 0 | — |
case-02 | fail→pass | 12,945 | 15,833 | +22% | 1 | 1 | 0% | 2,079 | 3,122 | +50% | 0 | 0 | — |
case-03 | fail→pass | 36,875 | 16,350 | -56% | 1 | 1 | 0% | 1,701 | 1,286 | -24% | 0 | 0 | — |
case-04 | fail→pass | 7,395 | 14,102 | +91% | 1 | 1 | 0% | 673 | 1,235 | +84% | 0 | 0 | — |
case-05 | pass→pass | 5,945 | 1,715 | -71% | 1 | 1 | 0% | 1,015 | 432 | -57% | 0 | 0 | — |
case-06 | fail→pass | 8,936 | 2,981 | -67% | 1 | 1 | 0% | 1,284 | 763 | -41% | 0 | 0 | — |
case-07 | pass→pass | 4,839 | 1,699 | -65% | 1 | 1 | 0% | 767 | 446 | -42% | 0 | 0 | — |
case-08 | fail→pass | 8,782 | 2,153 | -75% | 1 | 1 | 0% | 1,347 | 604 | -55% | 0 | 0 | — |
case-09 | pass→pass | 3,986 | 1,968 | -51% | 1 | 1 | 0% | 619 | 536 | -13% | 0 | 0 | — |
case-10 | fail→pass | 10,332 | 1,819 | -82% | 1 | 1 | 0% | 1,569 | 501 | -68% | 0 | 0 | — |
case-11 | fail→pass | 11,198 | 1,461 | -87% | 1 | 1 | 0% | 1,837 | 446 | -76% | 0 | 0 | — |
case-12 | pass→pass | 6,920 | 1,957 | -72% | 1 | 1 | 0% | 1,092 | 554 | -49% | 0 | 0 | — |
case-13 | pass→fail | 9,256 | 5,093 | -45% | 1 | 1 | 0% | 1,627 | 1,079 | -34% | 0 | 0 | — |
case-14 | fail→fail | 8,085 | 2,026 | -75% | 1 | 1 | 0% | 1,406 | 507 | -64% | 0 | 0 | — |
case-15 | pass→pass | 5,840 | 5,145 | -12% | 1 | 1 | 0% | 885 | 469 | -47% | 0 | 0 | — |
case-16 | fail→pass | 2,910 | 1,552 | -47% | 1 | 1 | 0% | 431 | 467 | +8% | 0 | 0 | — |
case-17 | fail→pass | 13,634 | 1,483 | -89% | 1 | 1 | 0% | 2,150 | 379 | -82% | 0 | 0 | — |
case-18 | fail→pass | 5,857 | 1,434 | -76% | 1 | 1 | 0% | 939 | 417 | -56% | 0 | 0 | — |
case-19 | fail→pass | 15,130 | 2,077 | -86% | 1 | 1 | 0% | 2,907 | 522 | -82% | 0 | 0 | — |
case-20 | fail→fail | 9,458 | 12,512 | +32% | 1 | 1 | 0% | 827 | 1,457 | +76% | 0 | 0 | — |
case-21 | fail→fail | 8,102 | 6,485 | -20% | 1 | 1 | 0% | 838 | 690 | -18% | 0 | 0 | — |
case-22 | pass→pass | 13,838 | 10,896 | -21% | 1 | 1 | 0% | 2,392 | 2,156 | -10% | 0 | 0 | — |
case-23 | fail→pass | 8,285 | 4,338 | -48% | 1 | 1 | 0% | 1,369 | 1,081 | -21% | 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 +52 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.