Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create custom external web service APIs for Moodle LMS. Use when implementing web services for course management, user tracking, quiz operations, or custom plugin functionality. Covers parameter validation, database operations, error handling, service registration, and Moodle coding standards.
.claude/skills/dokhacgiakhoa-moodle-external-api-development/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-18 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 13% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 14% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 31% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 3% | 0% |
This skill guides you through creating custom external web service APIs for Moodle LMS, following Moodle's external API framework and coding standards.
Moodle external APIs follow a strict three-method pattern:
execute_parameters() - Defines input parameter structureexecute() - Contains business logicexecute_returns() - Defines return structure| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 12,990 | 40,581 | +212% | 1 | 1 | 0% | 2,629 | 3,352 | +28% | 0 | 0 | — |
case-02 | fail→fail | 12,293 | 11,978 | -3% | 1 | 1 | 0% | 2,346 | 3,115 | +33% | 0 | 0 | — |
case-03 | pass→pass | 10,319 | 7,169 | -31% | 1 | 1 | 0% | 1,932 | 2,183 | +13% | 0 | 0 | — |
case-04 | pass→pass | 12,447 | 10,850 | -13% | 1 | 1 | 0% | 2,355 | 2,692 | +14% | 0 | 0 | — |
case-05 | fail→fail | 13,284 | 10,576 | -20% | 1 | 1 | 0% | 2,435 | 2,784 | +14% | 0 | 0 | — |
case-06 | pass→pass | 9,760 | 8,380 | -14% | 1 | 1 | 0% | 1,776 | 2,322 | +31% | 0 | 0 | — |
case-07 | pass→pass | 12,832 | 9,399 | -27% | 1 | 1 | 0% | 2,330 | 2,399 | +3% | 0 | 0 | — |
case-08 | pass→pass | 14,446 | 13,785 | -5% | 1 | 1 | 0% | 2,855 | 3,508 | +23% | 0 | 0 | — |
case-09 | pass→pass | 9,630 | 9,458 | -2% | 1 | 1 | 0% | 1,717 | 2,354 | +37% | 0 | 0 | — |
case-10 | pass→pass | 11,587 | 11,347 | -2% | 1 | 1 | 0% | 2,033 | 3,059 | +50% | 0 | 0 | — |
case-11 | pass→pass | 16,492 | 19,208 | +16% | 1 | 1 | 0% | 2,875 | 4,630 | +61% | 0 | 0 | — |
case-12 | pass→pass | 10,582 | 11,246 | +6% | 1 | 1 | 0% | 2,088 | 2,924 | +40% | 0 | 0 | — |
case-13 | pass→pass | 9,263 | 8,815 | -5% | 1 | 1 | 0% | 1,768 | 2,486 | +41% | 0 | 0 | — |
case-14 | pass→pass | 14,154 | 14,920 | +5% | 1 | 1 | 0% | 2,549 | 3,604 | +41% | 0 | 0 | — |
case-15 | pass→pass | 15,945 | 17,860 | +12% | 1 | 1 | 0% | 2,878 | 4,342 | +51% | 0 | 0 | — |
case-16 | pass→pass | 7,166 | 5,587 | -22% | 1 | 1 | 0% | 1,334 | 1,760 | +32% | 0 | 0 | — |
case-17 | pass→pass | 15,827 | 13,519 | -15% | 1 | 1 | 0% | 2,784 | 3,242 | +16% | 0 | 0 | — |
case-18 | fail→pass | 21,206 | 13,924 | -34% | 1 | 1 | 0% | 4,283 | 3,615 | -16% | 0 | 0 | — |
case-19 | pass→pass | 12,364 | 11,070 | -10% | 1 | 1 | 0% | 2,400 | 3,030 | +26% | 0 | 0 | — |
case-20 | pass→pass | 11,798 | 13,055 | +11% | 1 | 1 | 0% | 2,331 | 3,606 | +55% | 0 | 0 | — |
case-21 | pass→pass | 16,323 | 9,092 | -44% | 1 | 1 | 0% | 3,226 | 2,681 | -17% | 0 | 0 | — |
case-22 | pass→pass | 11,856 | 12,053 | +2% | 1 | 1 | 0% | 2,332 | 3,285 | +41% | 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 +5 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.