Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert patterns for Salesforce platform development including Lightning Web Components (LWC), Apex triggers and classes, REST/Bulk APIs, Connected Apps, and Salesforce DX with scratch orgs and 2nd generation packages (2GP). Use when: salesforce, sfdc, apex, lwc, lightning web components.
.claude/skills/davila7-salesforce-development/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-15 | ✓→✓ | = Same ✓ | -14% | 0% |
| case-16 | ✓→✓ | = Same ✓ | 4% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 9% | 0% |
Use @wire decorator for reactive data binding with Lightning Data Service or Apex methods. @wire fits LWC's reactive architecture and enables Salesforce performance optimizations.
Apex triggers must be bulkified to handle 200+ records per transaction. Use handler pattern for separation of concerns, testability, and recursion prevention.
Use Queueable Apex for async processing with support for non-primitive types, monitoring via AsyncApexJob, and job chaining. Limit: 50 jobs per transaction, 1 child job when chaining.
| Issue | Severity | Solution | |-------|----------|----------| | Issue | critical | See docs | | Issue | high | See docs | | Issue | medium | See docs | | Issue | high | See docs | | Issue | critical | See docs | | Issue | high | See docs | | Issue | high | See docs | | Issue | critical | See docs |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | pass→pass | 12,579 | 8,957 | -29% | 1 | 1 | 0% | 2,050 | 1,767 | -14% | 0 | 0 | — |
case-16 | pass→pass | 11,959 | 9,594 | -20% | 1 | 1 | 0% | 2,134 | 2,230 | +4% | 0 | 0 | — |
case-01 | fail→pass | 12,852 | 10,448 | -19% | 1 | 1 | 0% | 2,706 | 2,407 | -11% | 0 | 0 | — |
case-02 | pass→pass | 6,370 | 5,127 | -20% | 1 | 1 | 0% | 1,140 | 1,244 | +9% | 0 | 0 | — |
case-03 | pass→pass | 6,588 | 8,869 | +35% | 1 | 1 | 0% | 1,180 | 830 | -30% | 0 | 0 | — |
case-04 | pass→pass | 13,487 | 11,738 | -13% | 1 | 1 | 0% | 2,709 | 2,804 | +4% | 0 | 0 | — |
case-05 | pass→pass | 15,014 | 5,295 | -65% | 1 | 1 | 0% | 2,517 | 1,097 | -56% | 0 | 0 | — |
case-17 | fail→fail | 9,440 | 7,717 | -18% | 1 | 1 | 0% | 1,724 | 1,801 | +4% | 0 | 0 | — |
case-06 | pass→pass | 9,359 | 4,648 | -50% | 1 | 1 | 0% | 1,701 | 1,152 | -32% | 0 | 0 | — |
case-07 | pass→pass | 10,502 | 7,059 | -33% | 1 | 1 | 0% | 2,203 | 1,711 | -22% | 0 | 0 | — |
case-08 | fail→pass | 5,873 | 5,241 | -11% | 1 | 1 | 0% | 1,036 | 1,110 | +7% | 0 | 0 | — |
case-09 | fail→fail | 7,516 | 6,789 | -10% | 1 | 1 | 0% | 1,308 | 1,663 | +27% | 0 | 0 | — |
case-10 | pass→pass | 6,232 | 5,852 | -6% | 1 | 1 | 0% | 1,109 | 1,397 | +26% | 0 | 0 | — |
case-11 | pass→pass | 6,239 | 3,969 | -36% | 1 | 1 | 0% | 1,094 | 921 | -16% | 0 | 0 | — |
case-12 | pass→pass | 9,612 | 6,673 | -31% | 1 | 1 | 0% | 1,703 | 1,384 | -19% | 0 | 0 | — |
case-13 | pass→pass | 8,588 | 5,235 | -39% | 1 | 1 | 0% | 1,397 | 1,265 | -9% | 0 | 0 | — |
case-14 | pass→pass | 6,036 | 4,431 | -27% | 1 | 1 | 0% | 1,204 | 1,057 | -12% | 0 | 0 | — |
case-18 | fail→fail | 5,475 | 7,055 | +29% | 1 | 1 | 0% | 979 | 1,430 | +46% | 0 | 0 | — |
case-19 | pass→pass | 10,468 | 6,947 | -34% | 1 | 1 | 0% | 1,851 | 1,496 | -19% | 0 | 0 | — |
case-20 | pass→pass | 10,845 | 9,086 | -16% | 1 | 1 | 0% | 2,411 | 2,064 | -14% | 0 | 0 | — |
case-21 | pass→pass | 7,164 | 7,600 | +6% | 1 | 1 | 0% | 1,436 | 1,955 | +36% | 0 | 0 | — |
case-22 | pass→pass | 8,601 | 6,110 | -29% | 1 | 1 | 0% | 1,485 | 1,264 | -15% | 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.