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 "plan a red team engagement", "scope a penetration test", "design a security assessment methodology", "create rules of engagement", or "plan an adversary simulation".
.claude/skills/borghei-red-team/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 80% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -18% | 0% |
> Category: Engineering > Domain: Offensive Security
The Red Team skill provides tools for planning and scoping security engagements. It helps define rules of engagement, select methodologies, scope targets, plan attack phases, and generate engagement documentation.
Before planning the engagement, confirm these inputs. If any is unknown or vague, ASK — do not assume:
--target)--type)--compliance)Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
bash# Plan a red team engagement python scripts/engagement_planner.py --type red-team --target "web application" --duration 2w # Plan a penetration test python scripts/engagement_planner.py --type pentest --target "api,network" --duration 1w --compliance pci-dss # Generate rules of engagement document python scripts/engagement_planner.py --type red-team --target "full-org" --output engagement_plan.json --format json
| Tool | Purpose | Key Flags | |------|---------|-----------| | engagement_planner.py | Plan red team engagements with scope, rules, and methodology | --type, --target, --duration, --compliance |
Generates comprehensive engagement plans including:
engagement_planner.py--compliance flag for framework-specific requirements| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 22,792 | 19,614 | -14% | 1 | 1 | 0% | 3,412 | 3,685 | +8% | 0 | 0 | — |
case-02 | fail→fail | 18,882 | 22,906 | +21% | 1 | 1 | 0% | 3,240 | 3,802 | +17% | 0 | 0 | — |
case-03 | fail→pass | 20,470 | 20,672 | +1% | 1 | 1 | 0% | 3,514 | 4,388 | +25% | 0 | 0 | — |
case-04 | fail→pass | 17,640 | 22,938 | +30% | 1 | 1 | 0% | 2,658 | 3,620 | +36% | 0 | 0 | — |
case-05 | fail→pass | 5,237 | 4,035 | -23% | 1 | 1 | 0% | 796 | 1,433 | +80% | 0 | 0 | — |
case-06 | fail→pass | 10,730 | 17,416 | +62% | 1 | 1 | 0% | 1,572 | 1,587 | +1% | 0 | 0 | — |
case-07 | fail→fail | 6,840 | 4,506 | -34% | 1 | 1 | 0% | 1,144 | 1,461 | +28% | 0 | 0 | — |
case-08 | fail→pass | 8,420 | 2,469 | -71% | 1 | 1 | 0% | 1,223 | 999 | -18% | 0 | 0 | — |
case-09 | fail→pass | 12,384 | 5,901 | -52% | 1 | 1 | 0% | 860 | 854 | -1% | 0 | 0 | — |
case-10 | pass→pass | 9,231 | 5,110 | -45% | 1 | 1 | 0% | 1,204 | 1,444 | +20% | 0 | 0 | — |
case-11 | pass→pass | 8,861 | 1,733 | -80% | 1 | 1 | 0% | 1,253 | 910 | -27% | 0 | 0 | — |
case-12 | pass→pass | 6,453 | 7,451 | +15% | 1 | 1 | 0% | 943 | 1,793 | +90% | 0 | 0 | — |
case-13 | pass→pass | 5,304 | 3,653 | -31% | 1 | 1 | 0% | 753 | 1,149 | +53% | 0 | 0 | — |
case-14 | fail→pass | 8,662 | 2,746 | -68% | 1 | 1 | 0% | 1,265 | 1,082 | -14% | 0 | 0 | — |
case-15 | pass→pass | 9,925 | 6,876 | -31% | 1 | 1 | 0% | 1,334 | 1,618 | +21% | 0 | 0 | — |
case-16 | pass→pass | 9,954 | 5,401 | -46% | 1 | 1 | 0% | 1,545 | 1,439 | -7% | 0 | 0 | — |
case-17 | fail→pass | 13,461 | 5,873 | -56% | 1 | 1 | 0% | 1,894 | 1,461 | -23% | 0 | 0 | — |
case-18 | fail→fail | 7,532 | 2,753 | -63% | 1 | 1 | 0% | 1,077 | 1,071 | -1% | 0 | 0 | — |
case-19 | fail→fail | 8,112 | 2,760 | -66% | 1 | 1 | 0% | 1,220 | 1,095 | -10% | 0 | 0 | — |
case-20 | pass→pass | 3,252 | 4,569 | +40% | 1 | 1 | 0% | 502 | 1,093 | +118% | 0 | 0 | — |
case-21 | pass→pass | 1,950 | 2,585 | +33% | 1 | 1 | 0% | 252 | 991 | +293% | 0 | 0 | — |
case-22 | pass→pass | 2,420 | 3,053 | +26% | 1 | 1 | 0% | 333 | 1,069 | +221% | 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 +36 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.
Other measured skills in the registry, with their headline benchmark lift.