Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Strategic advisory for edtech founders on FERPA/COPPA compliance, K-12 vs higher-ed vs L&D dynamics, district sales, and pricing. Use when scoping an edtech product or navigating procurement, or mentioning edtech, K-12, FERPA, COPPA, or LMS.
.claude/skills/borghei-edtech-advisor/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | 93% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -17% | 0% |
Strategic frameworks for education-technology founders, operators, and product leaders.
> Disclaimer: Frameworks and orientation only. Not legal advice. Edtech compliance (FERPA, COPPA, GDPR, state laws) requires specialist counsel. Use this skill to organize strategy.
edtech, K-12, higher education, higher ed, university, college, FERPA, COPPA, GDPR-K, student data, LMS, SIS, learning management, school district, RFP, district sales, corporate learning, L&D, training, certification
references/edtech_market_dynamics.mdpython scripts/student_data_compliance_checker.py description.txtreferences/student_data_privacy.mdTime Estimate: 4-6 weeks for first scope.
references/edtech_market_dynamics.mdTime Estimate: 4-8 weeks.
Time Estimate: 6-12 months for first major district win.
Scans a product description for indicators of student-data handling and likely compliance regime exposure (FERPA, COPPA, GDPR-K, state laws).
bashpython scripts/student_data_compliance_checker.py description.txt python scripts/student_data_compliance_checker.py description.txt --json
references/student_data_privacy.md — FERPA, COPPA, GDPR-K, state laws (SOPIPA, NY Ed Law 2-d, etc.)references/edtech_market_dynamics.md — K-12, Higher Ed, Corporate L&D, D2C — buyer, sales cycle, pricingassets/sdpa_inventory_template.md — Student Data Privacy Agreement and compliance posture templatelegal/ for SDPA / DPA contract reviewmarketing/launch-strategy for back-to-school launch timingc-level-advisor/cs-fundraising-advisor for edtech-specific fundraising| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 24,487 | 26,766 | +9% | 1 | 1 | 0% | 3,692 | 5,051 | +37% | 0 | 0 | — |
case-02 | fail→fail | 32,254 | 31,254 | -3% | 1 | 1 | 0% | 4,883 | 5,589 | +14% | 0 | 0 | — |
case-21 | pass→pass | 17,323 | 19,319 | +12% | 1 | 1 | 0% | 2,916 | 4,020 | +38% | 0 | 0 | — |
case-03 | pass→pass | 18,140 | 16,647 | -8% | 1 | 1 | 0% | 2,575 | 3,229 | +25% | 0 | 0 | — |
case-04 | pass→pass | 19,013 | 18,082 | -5% | 1 | 1 | 0% | 2,792 | 3,482 | +25% | 0 | 0 | — |
case-05 | pass→pass | 17,853 | 19,508 | +9% | 1 | 1 | 0% | 2,650 | 3,797 | +43% | 0 | 0 | — |
case-06 | pass→fail | 20,009 | 19,921 | -0% | 1 | 1 | 0% | 2,659 | 3,832 | +44% | 0 | 0 | — |
case-07 | fail→fail | 15,597 | 16,723 | +7% | 1 | 1 | 0% | 2,377 | 3,444 | +45% | 0 | 0 | — |
case-08 | pass→pass | 20,651 | 20,447 | -1% | 1 | 1 | 0% | 3,182 | 4,028 | +27% | 0 | 0 | — |
case-09 | pass→pass | 19,175 | 21,954 | +14% | 1 | 1 | 0% | 2,789 | 4,009 | +44% | 0 | 0 | — |
case-10 | pass→pass | 15,415 | 22,885 | +48% | 1 | 1 | 0% | 2,319 | 4,269 | +84% | 0 | 0 | — |
case-11 | pass→pass | 6,425 | 2,691 | -58% | 1 | 1 | 0% | 1,042 | 1,456 | +40% | 0 | 0 | — |
case-12 | fail→pass | 5,840 | 3,668 | -37% | 1 | 1 | 0% | 815 | 1,573 | +93% | 0 | 0 | — |
case-13 | fail→pass | 8,732 | 3,129 | -64% | 1 | 1 | 0% | 1,333 | 1,471 | +10% | 0 | 0 | — |
case-14 | fail→pass | 12,398 | 1,727 | -86% | 1 | 1 | 0% | 1,852 | 1,163 | -37% | 0 | 0 | — |
case-15 | pass→pass | 4,234 | 2,289 | -46% | 1 | 1 | 0% | 631 | 1,282 | +103% | 0 | 0 | — |
case-16 | pass→pass | 10,056 | 7,111 | -29% | 1 | 1 | 0% | 1,536 | 1,997 | +30% | 0 | 0 | — |
case-17 | fail→pass | 11,256 | 8,143 | -28% | 1 | 1 | 0% | 1,615 | 2,200 | +36% | 0 | 0 | — |
case-18 | fail→pass | 28,673 | 5,343 | -81% | 1 | 1 | 0% | 2,179 | 1,819 | -17% | 0 | 0 | — |
case-19 | fail→pass | 17,463 | 15,657 | -10% | 1 | 1 | 0% | 2,567 | 3,095 | +21% | 0 | 0 | — |
case-20 | pass→pass | 14,659 | 15,344 | +5% | 1 | 1 | 0% | 2,167 | 3,105 | +43% | 0 | 0 | — |
case-22 | pass→pass | 20,499 | 24,360 | +19% | 1 | 1 | 0% | 2,991 | 4,491 | +50% | 0 | 0 | — |
case-23 | fail→pass | 12,020 | 15,509 | +29% | 1 | 1 | 0% | 1,809 | 3,179 | +76% | 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 +26 percentage points is the difference between those two pass rates over the 23 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.