Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
.claude/skills/wshobson-stride-analysis-patterns/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -68% | 0% |
| case-04 | ✓→✓ | = Same ✓ | -12% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 27% | 0% |
Systematic threat identification using the STRIDE methodology.
S - Spoofing → Authentication threats
T - Tampering → Integrity threats
R - Repudiation → Non-repudiation threats
I - Information → Confidentiality threats
Disclosure
D - Denial of → Availability threats
Service
E - Elevation of → Authorization threats
Privilege| Category | Question | Control Family | | ------------------- | ----------------------------------------- | -------------- | | Spoofing | Can attacker pretend to be someone else? | Authentication | | Tampering | Can attacker modify data in transit/rest? | Integrity | | Repudiation | Can attacker deny actions? | Logging/Audit | | Info Disclosure | Can attacker access unauthorized data? | Encryption | | DoS | Can attacker disrupt availability? | Rate limiting | | Elevation | Can attacker gain higher privileges? | Authorization |
Full template library lives in references/details.md. Read that file when you need concrete templates for this skill.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 5,820 | 3,359 | -42% | 1 | 1 | 0% | 1,214 | 1,064 | -12% | 0 | 0 | — |
case-01 | pass→pass | 5,888 | 5,046 | -14% | 1 | 1 | 0% | 1,027 | 1,305 | +27% | 0 | 0 | — |
case-02 | fail→pass | 4,781 | 3,371 | -29% | 1 | 1 | 0% | 903 | 1,047 | +16% | 0 | 0 | — |
case-03 | pass→pass | 4,258 | 4,424 | +4% | 1 | 1 | 0% | 713 | 1,258 | +76% | 0 | 0 | — |
case-05 | fail→pass | 5,525 | 3,019 | -45% | 1 | 1 | 0% | 1,027 | 1,067 | +4% | 0 | 0 | — |
case-06 | pass→pass | 5,911 | 4,405 | -25% | 1 | 1 | 0% | 1,163 | 1,352 | +16% | 0 | 0 | — |
case-07 | pass→pass | 13,854 | 72,553 | +424% | 1 | 1 | 0% | 2,241 | 2,538 | +13% | 0 | 0 | — |
case-08 | pass→pass | 9,163 | 7,815 | -15% | 1 | 1 | 0% | 1,516 | 1,781 | +17% | 0 | 0 | — |
case-09 | pass→pass | 12,801 | 12,121 | -5% | 1 | 1 | 0% | 2,051 | 2,545 | +24% | 0 | 0 | — |
case-10 | pass→pass | 4,591 | 2,599 | -43% | 1 | 1 | 0% | 804 | 949 | +18% | 0 | 0 | — |
case-11 | pass→pass | 7,110 | 8,542 | +20% | 1 | 1 | 0% | 1,260 | 1,993 | +58% | 0 | 0 | — |
case-12 | fail→pass | 12,667 | 1,352 | -89% | 1 | 1 | 0% | 2,171 | 684 | -68% | 0 | 0 | — |
case-13 | pass→pass | 4,279 | 2,496 | -42% | 1 | 1 | 0% | 747 | 840 | +12% | 0 | 0 | — |
case-14 | pass→pass | 5,585 | 3,758 | -33% | 1 | 1 | 0% | 1,063 | 886 | -17% | 0 | 0 | — |
case-15 | pass→pass | 4,659 | 1,397 | -70% | 1 | 1 | 0% | 895 | 692 | -23% | 0 | 0 | — |
case-16 | pass→pass | 6,047 | 2,171 | -64% | 1 | 1 | 0% | 1,155 | 822 | -29% | 0 | 0 | — |
case-17 | pass→pass | 5,109 | 2,922 | -43% | 1 | 1 | 0% | 915 | 845 | -8% | 0 | 0 | — |
case-18 | pass→pass | 3,211 | 1,631 | -49% | 1 | 1 | 0% | 516 | 686 | +33% | 0 | 0 | — |
case-19 | pass→pass | 10,158 | 7,663 | -25% | 1 | 1 | 0% | 1,786 | 1,870 | +5% | 0 | 0 | — |
case-20 | pass→pass | 6,108 | 7,179 | +18% | 1 | 1 | 0% | 1,122 | 1,562 | +39% | 0 | 0 | — |
case-21 | pass→pass | 6,282 | 7,751 | +23% | 1 | 1 | 0% | 1,585 | 2,366 | +49% | 0 | 0 | — |
case-22 | pass→pass | 2,533 | 4,044 | +60% | 1 | 1 | 0% | 507 | 939 | +85% | 0 | 0 | — |
case-23 | pass→pass | 10,572 | 10,937 | +3% | 1 | 1 | 0% | 2,202 | 2,410 | +9% | 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 +13 percentage points is the difference between those two pass rates over the 23 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.