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 "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters.
.claude/skills/dokhacgiakhoa-red-team-tools-and-methodology/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-01 | ✓→✗ | ▼ Worse | 36% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 0% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 31% | 0% |
Implement proven methodologies and tool workflows from top security researchers for effective reconnaissance, vulnerability discovery, and bug bounty hunting. Automate common tasks while maintaining thorough coverage of attack surfaces.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→fail | 24,272 | 33,429 | +38% | 1 | 1 | 0% | 4,428 | 6,013 | +36% | 0 | 0 | — |
case-02 | fail→fail | 18,656 | 24,493 | +31% | 1 | 1 | 0% | 2,974 | 3,676 | +24% | 0 | 0 | — |
case-03 | pass→pass | 25,937 | 24,899 | -4% | 1 | 1 | 0% | 4,432 | 4,413 | -0% | 0 | 0 | — |
case-04 | pass→pass | 18,285 | 22,505 | +23% | 1 | 1 | 0% | 3,027 | 3,971 | +31% | 0 | 0 | — |
case-05 | pass→pass | 22,821 | 19,970 | -12% | 1 | 1 | 0% | 3,444 | 3,936 | +14% | 0 | 0 | — |
case-06 | pass→pass | 17,202 | 18,848 | +10% | 1 | 1 | 0% | 2,495 | 3,505 | +40% | 0 | 0 | — |
case-07 | fail→fail | 22,104 | 21,101 | -5% | 1 | 1 | 0% | 3,918 | 2,474 | -37% | 0 | 0 | — |
case-08 | pass→pass | 18,064 | 14,467 | -20% | 1 | 1 | 0% | 2,617 | 3,102 | +19% | 0 | 0 | — |
case-09 | pass→pass | 18,991 | 20,567 | +8% | 1 | 1 | 0% | 3,194 | 4,044 | +27% | 0 | 0 | — |
case-10 | pass→pass | 17,661 | 21,479 | +22% | 1 | 1 | 0% | 2,951 | 4,327 | +47% | 0 | 0 | — |
case-11 | pass→pass | 22,033 | 19,556 | -11% | 1 | 1 | 0% | 3,229 | 4,125 | +28% | 0 | 0 | — |
case-12 | pass→pass | 16,305 | 22,122 | +36% | 1 | 1 | 0% | 2,635 | 3,346 | +27% | 0 | 0 | — |
case-13 | fail→pass | 19,383 | 20,732 | +7% | 1 | 1 | 0% | 3,071 | 3,782 | +23% | 0 | 0 | — |
case-14 | pass→pass | 21,697 | 18,778 | -13% | 1 | 1 | 0% | 3,493 | 3,910 | +12% | 0 | 0 | — |
case-15 | fail→pass | 19,835 | 23,410 | +18% | 1 | 1 | 0% | 2,260 | 3,078 | +36% | 0 | 0 | — |
case-16 | pass→pass | 17,419 | 13,216 | -24% | 1 | 1 | 0% | 2,966 | 2,909 | -2% | 0 | 0 | — |
case-17 | pass→pass | 17,391 | 11,899 | -32% | 1 | 1 | 0% | 2,914 | 2,800 | -4% | 0 | 0 | — |
case-18 | pass→pass | 15,733 | 17,223 | +9% | 1 | 1 | 0% | 2,449 | 3,782 | +54% | 0 | 0 | — |
case-19 | pass→pass | 14,288 | 9,045 | -37% | 1 | 1 | 0% | 2,325 | 2,141 | -8% | 0 | 0 | — |
case-20 | fail→fail | 26,270 | 13,601 | -48% | 1 | 1 | 0% | 962 | 3,249 | +238% | 0 | 0 | — |
case-21 | pass→pass | 31,513 | 28,125 | -11% | 1 | 1 | 0% | 5,017 | 5,653 | +13% | 0 | 0 | — |
case-22 | pass→pass | 22,894 | 17,000 | -26% | 1 | 1 | 0% | 3,301 | 3,501 | +6% | 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 +5 percentage points is the difference between those two pass rates over the 22 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.