Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions. Use when: shopify app, shopify, embedded app, polaris, app bridge.
.claude/skills/davila7-shopify-apps/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -15% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -11% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 2% | 0% |
Modern Shopify app template with React Router
Render app embedded in Shopify Admin
Secure webhook processing with HMAC verification
| Issue | Severity | Solution | |-------|----------|----------| | Issue | high | ## Respond immediately, process asynchronously | | Issue | high | ## Check rate limit headers | | Issue | high | ## Request protected customer data access | | Issue | medium | ## Use TOML only (recommended) | | Issue | medium | ## Handle both URL formats | | Issue | high | ## Use GraphQL for all new code | | Issue | high | ## Use latest App Bridge via script tag | | Issue | high | ## Implement all GDPR handlers |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,863 | 12,578 | -15% | 1 | 1 | 0% | 2,337 | 2,311 | -1% | 0 | 0 | — |
case-02 | fail→pass | 16,042 | 12,999 | -19% | 1 | 1 | 0% | 2,455 | 2,407 | -2% | 0 | 0 | — |
case-03 | pass→pass | 16,780 | 12,097 | -28% | 1 | 1 | 0% | 2,924 | 2,473 | -15% | 0 | 0 | — |
case-04 | pass→pass | 11,660 | 9,292 | -20% | 1 | 1 | 0% | 1,948 | 1,740 | -11% | 0 | 0 | — |
case-05 | pass→pass | 11,739 | 10,138 | -14% | 1 | 1 | 0% | 1,929 | 1,971 | +2% | 0 | 0 | — |
case-06 | pass→pass | 16,360 | 8,849 | -46% | 1 | 1 | 0% | 2,861 | 1,927 | -33% | 0 | 0 | — |
case-07 | pass→pass | 15,605 | 12,559 | -20% | 1 | 1 | 0% | 2,858 | 2,404 | -16% | 0 | 0 | — |
case-08 | pass→pass | 10,310 | 4,172 | -60% | 1 | 1 | 0% | 1,752 | 906 | -48% | 0 | 0 | — |
case-09 | pass→pass | 14,718 | 11,103 | -25% | 1 | 1 | 0% | 2,411 | 1,970 | -18% | 0 | 0 | — |
case-10 | fail→fail | 16,770 | 15,177 | -9% | 1 | 1 | 0% | 2,778 | 2,995 | +8% | 0 | 0 | — |
case-11 | pass→pass | 4,629 | 4,485 | -3% | 1 | 1 | 0% | 667 | 845 | +27% | 0 | 0 | — |
case-12 | pass→pass | 10,969 | 9,890 | -10% | 1 | 1 | 0% | 1,926 | 1,967 | +2% | 0 | 0 | — |
case-13 | pass→pass | 14,221 | 10,975 | -23% | 1 | 1 | 0% | 2,254 | 1,839 | -18% | 0 | 0 | — |
case-14 | pass→pass | 20,637 | 14,499 | -30% | 1 | 1 | 0% | 3,484 | 2,832 | -19% | 0 | 0 | — |
case-19 | pass→pass | 11,380 | 7,352 | -35% | 1 | 1 | 0% | 1,713 | 1,431 | -16% | 0 | 0 | — |
case-15 | pass→pass | 12,724 | 8,423 | -34% | 1 | 1 | 0% | 2,287 | 1,753 | -23% | 0 | 0 | — |
case-16 | pass→pass | 9,741 | 6,272 | -36% | 1 | 1 | 0% | 1,561 | 1,242 | -20% | 0 | 0 | — |
case-17 | pass→pass | 11,089 | 7,782 | -30% | 1 | 1 | 0% | 1,844 | 1,518 | -18% | 0 | 0 | — |
case-18 | pass→pass | 13,811 | 7,689 | -44% | 1 | 1 | 0% | 2,198 | 1,410 | -36% | 0 | 0 | — |
case-20 | pass→pass | 6,606 | 6,167 | -7% | 1 | 1 | 0% | 1,168 | 1,240 | +6% | 0 | 0 | — |
case-21 | pass→pass | 8,709 | 6,677 | -23% | 1 | 1 | 0% | 1,474 | 1,468 | -0% | 0 | 0 | — |
case-22 | pass→pass | 17,487 | 16,209 | -7% | 1 | 1 | 0% | 2,959 | 3,105 | +5% | 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 +9 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.