Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plan penetration test planner operations. Auto-activating skill for Security Advanced. Triggers on: penetration test planner, penetration test planner Part of the Security Advanced skill category. Use when writing or running tests. Trigger with phrases like "penetration test planner", "penetration planner", "penetration".
.claude/skills/dicklesworthstone-penetration-test-planner/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-17 | ✓→✗ | ▼ Worse | 49% | 0% |
| case-19 | ✓→✗ | ▼ Worse | 54% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 28% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 55% | 0% |
This skill provides automated assistance for penetration test planner tasks within the Security Advanced domain.
This skill activates automatically when you:
Example: Basic Usage Request: "Help me with penetration test planner" Result: Provides step-by-step guidance and generates appropriate configurations
| Error | Cause | Solution | |-------|-------|----------| | Configuration invalid | Missing required fields | Check documentation for required parameters | | Tool not found | Dependency not installed | Install required tools per prerequisites | | Permission denied | Insufficient access | Verify credentials and permissions |
Part of the Security Advanced skill category. Tags: pentesting, compliance, soc2, gdpr, threat-modeling
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 21,153 | 27,613 | +31% | 1 | 1 | 0% | 2,609 | 3,340 | +28% | 0 | 0 | — |
case-02 | pass→pass | 26,283 | 32,968 | +25% | 1 | 1 | 0% | 3,757 | 5,841 | +55% | 0 | 0 | — |
case-03 | pass→pass | 21,096 | 27,270 | +29% | 1 | 1 | 0% | 3,184 | 4,285 | +35% | 0 | 0 | — |
case-04 | pass→pass | 27,687 | 30,384 | +10% | 1 | 1 | 0% | 3,877 | 5,567 | +44% | 0 | 0 | — |
case-05 | pass→pass | 16,446 | 20,518 | +25% | 1 | 1 | 0% | 2,638 | 2,533 | -4% | 0 | 0 | — |
case-06 | pass→pass | 17,801 | 42,323 | +138% | 1 | 1 | 0% | 3,233 | 7,176 | +122% | 0 | 0 | — |
case-07 | pass→pass | 29,973 | 28,552 | -5% | 1 | 1 | 0% | 2,843 | 3,432 | +21% | 0 | 0 | — |
case-08 | pass→pass | 31,126 | 39,736 | +28% | 1 | 1 | 0% | 3,764 | 6,540 | +74% | 0 | 0 | — |
case-09 | pass→pass | 28,556 | 27,294 | -4% | 1 | 1 | 0% | 4,740 | 3,311 | -30% | 0 | 0 | — |
case-10 | fail→pass | 21,239 | 29,373 | +38% | 1 | 1 | 0% | 2,244 | 3,229 | +44% | 0 | 0 | — |
case-22 | pass→pass | 23,979 | 46,849 | +95% | 1 | 1 | 0% | 3,445 | 6,722 | +95% | 0 | 0 | — |
case-11 | pass→pass | 16,083 | 20,220 | +26% | 1 | 1 | 0% | 2,968 | 2,986 | +1% | 0 | 0 | — |
case-12 | pass→pass | 21,947 | 17,702 | -19% | 1 | 1 | 0% | 2,535 | 2,539 | +0% | 0 | 0 | — |
case-13 | pass→pass | 21,814 | 27,603 | +27% | 1 | 1 | 0% | 3,816 | 5,072 | +33% | 0 | 0 | — |
case-14 | pass→pass | 24,629 | 26,987 | +10% | 1 | 1 | 0% | 2,577 | 2,922 | +13% | 0 | 0 | — |
case-15 | pass→pass | 18,007 | 23,635 | +31% | 1 | 1 | 0% | 1,923 | 2,330 | +21% | 0 | 0 | — |
case-16 | pass→pass | 22,750 | 21,280 | -6% | 1 | 1 | 0% | 3,834 | 2,693 | -30% | 0 | 0 | — |
case-17 | pass→fail | 19,598 | 31,728 | +62% | 1 | 1 | 0% | 2,942 | 4,393 | +49% | 0 | 0 | — |
case-18 | pass→pass | 25,389 | 24,079 | -5% | 1 | 1 | 0% | 4,137 | 2,878 | -30% | 0 | 0 | — |
case-19 | pass→fail | 26,680 | 39,457 | +48% | 1 | 1 | 0% | 4,247 | 6,558 | +54% | 0 | 0 | — |
case-20 | pass→pass | 22,152 | 28,360 | +28% | 1 | 1 | 0% | 3,298 | 5,992 | +82% | 0 | 0 | — |
case-21 | fail→fail | 20,675 | 29,420 | +42% | 1 | 1 | 0% | 3,197 | 5,030 | +57% | 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. 2 cases got worse with the skill loaded, and they are 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.