Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →This skill provides comprehensive guidance for reviewing code, features, and content for cultural sensitivity and Indigenous data sovereignty compliance.
.claude/skills/aiskillstore-cultural-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 119% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 115% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 11% | 0% |
This skill provides comprehensive guidance for reviewing code, features, and content for cultural sensitivity and Indigenous data sovereignty compliance.
Requirement: Storytellers maintain ownership of their narratives
Check for:
author_id and storyteller_idRequirement: Users decide who accesses their stories
Check for:
Requirement: Tiered access based on cultural sensitivity
Check for:
Requirement: Data can be exported or deleted anytime
Check for:
□ Authentication required (unless public embed)
□ Authorization checks ownership/permissions
□ Sensitivity level verified before action
□ Elder approval status checked for high/sacred
□ Audit log created for significant actions
□ Consent verified before distribution
□ Revocation cascades properly□ Cultural indicators are respectful
□ Sensitivity badges are clear
□ Elder approval status prominent
□ Consent status visible
□ Privacy level clearly shown
□ Revocation controls accessible
□ Trauma-informed animations (gentle)
□ Language is inclusive□ Tenant isolation maintained
□ Ownership fields populated
□ Consent fields checked
□ Audit trail created
□ Soft delete preferred over hard delete
□ Anonymization preserves audit trail| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 22,956 | 19,359 | -16% | 1 | 1 | 0% | 2,029 | 4,434 | +119% | 0 | 0 | — |
case-02 | fail→pass | 29,071 | 25,690 | -12% | 1 | 1 | 0% | 5,253 | 6,036 | +15% | 0 | 0 | — |
case-03 | fail→pass | 9,901 | 15,725 | +59% | 1 | 1 | 0% | 1,574 | 3,389 | +115% | 0 | 0 | — |
case-04 | pass→pass | 22,321 | 11,187 | -50% | 1 | 1 | 0% | 1,979 | 2,874 | +45% | 0 | 0 | — |
case-05 | pass→fail | 14,287 | 10,140 | -29% | 1 | 1 | 0% | 2,378 | 2,585 | +9% | 0 | 0 | — |
case-06 | pass→pass | 17,906 | 15,072 | -16% | 1 | 1 | 0% | 2,991 | 3,301 | +10% | 0 | 0 | — |
case-07 | fail→fail | 30,193 | 10,751 | -64% | 1 | 1 | 0% | 2,529 | 2,901 | +15% | 0 | 0 | — |
case-08 | pass→pass | 14,607 | 8,924 | -39% | 1 | 1 | 0% | 2,476 | 2,278 | -8% | 0 | 0 | — |
case-09 | fail→pass | 11,955 | 9,665 | -19% | 1 | 1 | 0% | 1,919 | 2,328 | +21% | 0 | 0 | — |
case-10 | fail→pass | 17,030 | 12,510 | -27% | 1 | 1 | 0% | 2,540 | 2,828 | +11% | 0 | 0 | — |
case-11 | fail→pass | 11,243 | 8,122 | -28% | 1 | 1 | 0% | 1,983 | 2,155 | +9% | 0 | 0 | — |
case-12 | fail→pass | 16,421 | 12,472 | -24% | 1 | 1 | 0% | 2,429 | 2,693 | +11% | 0 | 0 | — |
case-13 | fail→pass | 13,314 | 6,946 | -48% | 1 | 1 | 0% | 2,207 | 1,985 | -10% | 0 | 0 | — |
case-14 | pass→pass | 13,697 | 11,178 | -18% | 1 | 1 | 0% | 2,267 | 2,589 | +14% | 0 | 0 | — |
case-15 | fail→pass | 12,781 | 4,255 | -67% | 1 | 1 | 0% | 2,096 | 1,544 | -26% | 0 | 0 | — |
case-16 | fail→pass | 17,064 | 9,947 | -42% | 1 | 1 | 0% | 2,851 | 2,485 | -13% | 0 | 0 | — |
case-17 | fail→pass | 14,049 | 11,725 | -17% | 1 | 1 | 0% | 2,280 | 2,693 | +18% | 0 | 0 | — |
case-18 | pass→pass | 15,023 | 9,033 | -40% | 1 | 1 | 0% | 2,502 | 2,475 | -1% | 0 | 0 | — |
case-19 | pass→pass | 15,136 | 8,249 | -46% | 1 | 1 | 0% | 2,321 | 2,111 | -9% | 0 | 0 | — |
case-20 | pass→pass | 16,372 | 8,868 | -46% | 1 | 1 | 0% | 2,660 | 2,282 | -14% | 0 | 0 | — |
case-21 | pass→pass | 16,989 | 12,406 | -27% | 1 | 1 | 0% | 2,620 | 2,958 | +13% | 0 | 0 | — |
case-22 | pass→pass | 11,363 | 6,296 | -45% | 1 | 1 | 0% | 1,745 | 1,805 | +3% | 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 +45 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.