Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
.claude/skills/attack-tree-construction/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-10 | ✓→✓ | ＝ Same ✓ | -6% | 0% |
| case-11 | ✓→✓ | ＝ Same ✓ | 30% | 0% |
| case-09 | ✓→✓ | ＝ Same ✓ | 37% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 5% | 0% |
> ⚠️ AUTHORIZED USE ONLY > This skill is for educational purposes or authorized security assessments only. > You must have explicit, written permission from the system owner before using this tool. > Misuse of this tool is illegal and strictly prohibited.
> Mandatory confirmation gate > Before running any command that probes, exploits, changes, persists on, extracts data from, or attempts credential access against a target: > 1. Ask the user to state the exact target URL, IP, account, or resource. > 2. Ask the user to confirm written authorization and the permitted scope. > 3. Show the exact command(s) and explain their expected effect. > 4. Wait for explicit confirmation in the current conversation. > > Without that confirmation, remain read-only and provide defensive guidance only. Prefer a sandbox, disposable VM, or controlled lab.
> AUTHORIZED USE ONLY: Use this skill only for authorized security assessments, defensive validation, or controlled educational environments.
Systematic attack path visualization and analysis.
resources/implementation-playbook.md.resources/implementation-playbook.md for detailed patterns, templates, and examples.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | pass→pass | 20,780 | 16,091 | -23% | 1 | 1 | 0% | 3,619 | 3,404 | -6% | 0 | 0 | — |
case-11 | pass→pass | 16,972 | 17,466 | +3% | 1 | 1 | 0% | 2,037 | 2,642 | +30% | 0 | 0 | — |
case-09 | pass→pass | 19,048 | 20,253 | +6% | 1 | 1 | 0% | 2,305 | 3,164 | +37% | 0 | 0 | — |
case-01 | fail→fail | 20,924 | 21,703 | +4% | 1 | 1 | 0% | 2,813 | 3,190 | +13% | 0 | 0 | — |
case-02 | fail→fail | 18,619 | 21,528 | +16% | 1 | 1 | 0% | 3,306 | 4,581 | +39% | 0 | 0 | — |
case-03 | pass→pass | 14,539 | 11,541 | -21% | 1 | 1 | 0% | 2,709 | 2,847 | +5% | 0 | 0 | — |
case-04 | pass→pass | 11,785 | 13,895 | +18% | 1 | 1 | 0% | 1,872 | 2,814 | +50% | 0 | 0 | — |
case-05 | pass→pass | 11,962 | 9,289 | -22% | 1 | 1 | 0% | 1,836 | 1,945 | +6% | 0 | 0 | — |
case-06 | fail→fail | 14,203 | 17,224 | +21% | 1 | 1 | 0% | 2,584 | 3,564 | +38% | 0 | 0 | — |
case-07 | fail→fail | 17,222 | 25,560 | +48% | 1 | 1 | 0% | 1,960 | 3,220 | +64% | 0 | 0 | — |
case-08 | pass→pass | 16,819 | 19,986 | +19% | 1 | 1 | 0% | 2,342 | 3,112 | +33% | 0 | 0 | — |
case-12 | fail→pass | 11,684 | 28,606 | +145% | 1 | 1 | 0% | 1,920 | 1,943 | +1% | 0 | 0 | — |
case-13 | pass→pass | 18,938 | 21,015 | +11% | 1 | 1 | 0% | 2,144 | 2,797 | +30% | 0 | 0 | — |
case-14 | pass→pass | 17,322 | 18,104 | +5% | 1 | 1 | 0% | 1,517 | 2,194 | +45% | 0 | 0 | — |
case-15 | pass→pass | 11,024 | 10,552 | -4% | 1 | 1 | 0% | 1,056 | 1,565 | +48% | 0 | 0 | — |
case-16 | pass→pass | 14,419 | 8,786 | -39% | 1 | 1 | 0% | 2,541 | 1,997 | -21% | 0 | 0 | — |
case-17 | pass→pass | 25,409 | 26,479 | +4% | 1 | 1 | 0% | 2,157 | 3,641 | +69% | 0 | 0 | — |
case-18 | pass→pass | 18,903 | 16,662 | -12% | 1 | 1 | 0% | 3,129 | 3,450 | +10% | 0 | 0 | — |
case-19 | pass→pass | 20,639 | 14,489 | -30% | 1 | 1 | 0% | 3,878 | 3,355 | -13% | 0 | 0 | — |
case-20 | pass→pass | 29,627 | 17,744 | -40% | 1 | 1 | 0% | 3,244 | 3,411 | +5% | 0 | 0 | — |
case-21 | fail→fail | 23,909 | 15,385 | -36% | 1 | 1 | 0% | 1,748 | 2,012 | +15% | 0 | 0 | — |
case-22 | pass→pass | 7,553 | 13,973 | +85% | 1 | 1 | 0% | 667 | 1,780 | +167% | 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.
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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/28/2026 | +59% |
Other measured skills in the registry, with their headline benchmark lift.